{ "status": "complete", "run": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921", "source": "/data/HDD1/tjut-yinhanqing/repo/demo/low-repetition-20260921", "protocol": { "artifact_scope": "original_baseline_qualitative_demo", "metric_tuning": false, "changes_original_weights": false, "eligible_as_default_model": false, "not_final_paper_result": true, "created": "2026-09-21T10:07:21.442702+08:00", "source": "/data/HDD1/tjut-yinhanqing/repo/demo/low-repetition-20260921", "source_manifest_sha256": "1a9ff6a5cb2be1d0c797570045df9c284be2a709ffd58d7cf7f3a8821756e04f", "songs": 5, "prefix_bars": 8, "target_bars": 32, "role_mapping": "grid_onset_v2", "models": [ "mupt", "notagen", "amadeus", "beat", "music2music", "text2midi" ], "visible_information": "Only eight GT prefix bars and prefix-derived text; actual future withheld.", "selection": "The five contexts already displayed before baseline generation; fixed seed per context; no metric-based selection.", "generation": "Existing cross-model adapters with fixed sampling parameters and native context limits.", "rendering": { "sample_rate": 44100, "common_gain": 1, "per_clip_normalization": false, "soundfont_sha256": "9a57fb3b6714e69dda12390e351b087e81fc3b1eca15c6b4bbe172799f4cf3cd", "chorus": false, "reverb": false }, "duration_policy": "Present the original observed prefix and native generated notes, up to the 32-bar target. MP3 playback ends at the last note plus up to 1.5 seconds of release tail; no silent padding. Original padded WAV masters remain in the source archive.", "limitations": "Qualitative comparison using model-specific MIDI/token/ABC adapters; not a matched training or unbiased evaluation." }, "models": { "mupt": { "checkpoint": "/data/HDD1/tjut-yinhanqing/repo/baseline/MuPT-main/model/MuPT-v1-8192-1.97B", "sha256": "5c92f4135b558bede523143bb2ff000f717cc1a2c6c30f39a8cdd1370d10ed35", "precision": "float16", "context_tokens": 8192, "parameters": 1965688320, "sampling": { "temperature": 1, "top_p": 0.95, "top_k": 0 }, "sampling_scope": "Fixed pilot sampling", "adaptation": "MIDI to sixteenth-grid ABC; interleaved voices per model card; preserve observed voice programs", "bridge_version": "v3: N voices have N-1 separating barlines; <|> explicitly closes the observed prefix", "decoding": "Positionally decode voices; absent trailing voices silent; new unlabelled voices use GM program 0; retain timing violations" }, "notagen": { "checkpoint": "/data/HDD1/tjut-yinhanqing/repo/baseline/NotaGen-main/model/weights_notagen_pretrain-finetune-RL3_beta_0.1_lambda_10_p_size_16_p_length_1024_p_layers_20_c_layers_6_h_size_1280_lr_1e-06_batch_1.pth", "sha256": "10bc04de11c42d1e15e84555f7dc15a18528312ea71f079b7a3e6f5f9eaca2fd", "precision": "float32", "context_patches": 1024, "patch_characters": 16, "sampling": { "temperature": 1.2, "top_p": 0.9, "top_k": 9 }, "adaptation": "MIDI to sixteenth-grid ABC; native patch stream with requested total length; preserve observed voice programs" }, "amadeus": { "checkpoint": "/data/HDD1/tjut-yinhanqing/repo/baseline/Amadeus-main/model/Amadeus-S/Amadeus-S/files/checkpoints/iter103662_loss-0.2098.pt", "sha256": "ef24dbb197cf9abf81e1363144738a2a92bf515a1d26a3c5e35ff05bb15109c4", "precision": "float32", "sampling": { "temperature": 1.15, "top_p": 0.99 }, "context_tokens": 3072, "conditioning": "Native NB prefix with prefix-only text and prefix-derived chords; no future controls", "adaptation": "Official NB tokenization/shift and observed bar-boundary selection; local loop fixes official conditional cache unpack bug" }, "beat": { "checkpoint": "/data/HDD1/tjut-yinhanqing/repo/baseline/BEAT-code-main/checkpoints/multitrack/backbone.pt", "sha256": "32b2cd345c6b19f5b7ed45187f9a321b39efe09a348085047c8615e8ea3fa4be", "sampling": { "temperature": 1, "top_p": 0.95 }, "precision": "float32", "context_tokens": 2048 }, "music2music": { "checkpoint": "/data/HDD1/tjut-yinhanqing/repo/baseline/music2music_code-master/model/m2m_pt", "sha256": "c74187603ec6a569597054dbd97d8e1b1f82e36085f9ebdb8696060eef728a79", "sampling": { "temperature": 1, "top_p": 0.95, "top_k": 0 }, "precision": "float32", "context_tokens": 2048, "sampling_scope": "Fixed pilot sampling, not an author-reported optimum" }, "text2midi": { "checkpoint": "/data/HDD1/tjut-yinhanqing/repo/baseline/Text2midi-main/model/text2midi/pytorch_model.bin", "sha256": "d94e8d7dda9207ed734268933629d4a4b7a1a6ce84c77299f610d3470448bfc1", "sampling": { "temperature": 1, "top_p": 1, "top_k": 0 }, "precision": "float32", "context_tokens": 2048, "adaptation": "Prime the unchanged causal decoder with observed MIDI tokens; text is prefix-only metadata. Cache unchanged T5 output.", "official_native_task": "text-to-MIDI" } }, "rendering": { "sample_rate": 44100, "common_gain": 1, "per_clip_normalization": false, "soundfont_sha256": "9a57fb3b6714e69dda12390e351b087e81fc3b1eca15c6b4bbe172799f4cf3cd", "chorus": false, "reverb": false }, "clips": [ { "song_id": "song-1", "window": "Track01646.npz:73", "model": "mupt", "name": "MuPT 1.97B", "midi": "assets/song-1_mupt.mid", "mp3": "assets/song-1_mupt.mp3", "wav": "assets/song-1_mupt.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/mupt/song-1/result.json", "source_midi_sha256": "0b754fa68866f832c4669ded40be89c6007622efc574e37b1454812f4383b464", "seed": 20260921, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 16.1875, "prefix_seconds": 16, "duration": 80, "audio_duration": 49.92, "notes": 658, "peak": 0.2171579748392105, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 2670, "total_tokens": 6766, "decoded_bars": 21, "observed_voices": 5, "decoded_voices": 7, "unlabelled_extra_voice_program": 0, "reached_requested_boundary": false }, "metrics": { "rbde": 4.035862674649516, "rhythm_jsd": 0.20755178026994411, "chroma_jsd": 0.6922838502201529, "role_structure_error": 0.3837195543221507, "tsse": 0.7197709498458761 }, "diagnostics": { "notes": 658, "sounding_bars": 16.1875, "empty_bar_rate": 0.46875, "role_assignments": [ { "program": 0, "drum": false, "notes": 273, "role": "chords" }, { "program": 32, "drum": false, "notes": 53, "role": "bass" }, { "program": 0, "drum": false, "notes": 79, "role": "chords" }, { "program": 0, "drum": true, "notes": 169, "role": "drums" }, { "program": 24, "drum": false, "notes": 24, "role": "accompaniment" }, { "program": 0, "drum": false, "notes": 24, "role": "melody" }, { "program": 0, "drum": false, "notes": 36, "role": "melody" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 21, 21, 21, 21, 21, 21, 21 ], "violation_count": 13, "violations": [ { "voice": 1, "bar": 8, "offset_beats": 32, "duration_beats": 5 }, { "voice": 1, "bar": 9, "offset_beats": 37, "duration_beats": 5 }, { "voice": 1, "bar": 10, "offset_beats": 42, "duration_beats": 5 }, { "voice": 1, "bar": 11, "offset_beats": 47, "duration_beats": 5 }, { "voice": 1, "bar": 12, "offset_beats": 52, "duration_beats": 5 }, { "voice": 1, "bar": 13, "offset_beats": 57, "duration_beats": 5 }, { "voice": 1, "bar": 14, "offset_beats": 62, "duration_beats": 5 }, { "voice": 1, "bar": 15, "offset_beats": 67, "duration_beats": 5 }, { "voice": 1, "bar": 16, "offset_beats": 72, "duration_beats": 5 }, { "voice": 1, "bar": 17, "offset_beats": 77, "duration_beats": 5 }, { "voice": 1, "bar": 18, "offset_beats": 82, "duration_beats": 5 }, { "voice": 1, "bar": 19, "offset_beats": 87, "duration_beats": 5 }, { "voice": 1, "bar": 20, "offset_beats": 92, "duration_beats": 5 } ] }, "listening_note": "Native output: 16.2 / 32 bars. This run ended before the requested 32-bar boundary. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "8812d8772462f56992dc8ff0a98fc0f204542eb8acf0a01c61d2e5bd026114ec", "mp3": "d55061242b554be93cd3650d0da455ef820da04e1cd2d85ecb50e3e931abce53", "wav": "0275732ff136063272e5f95e61122a664fc63340680454d166516541c90c7715" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-1_mupt.wav", "source_wav_sha256": "0275732ff136063272e5f95e61122a664fc63340680454d166516541c90c7715", "source_mp3_sha256": "9ee76f1b226b31a6f4c61856943e4de55fe07565cf6837503162107c3c4974f2", "source_audio_duration": 81.528163, "last_note_end_seconds": 48.375, "trim_end_seconds": 49.875, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-2", "window": "Track01631.npz:32", "model": "mupt", "name": "MuPT 1.97B", "midi": "assets/song-2_mupt.mid", "mp3": "assets/song-2_mupt.mp3", "wav": "assets/song-2_mupt.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/mupt/song-2/result.json", "source_midi_sha256": "96d37efa86c1332c27b62774ac79691aebfd9b7aec5d96c39b338691cdbf46da", "seed": 20260922, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 4.375, "prefix_seconds": 18.916159559985374, "duration": 94.58079779992687, "audio_duration": 30.798367, "notes": 611, "peak": 0.33230891823768616, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 18.816145124716552, "generation": { "prefix_tokens": 3422, "total_tokens": 7518, "decoded_bars": 12, "observed_voices": 5, "decoded_voices": 8, "unlabelled_extra_voice_program": 0, "reached_requested_boundary": false }, "metrics": { "rbde": 4.510973481259029, "rhythm_jsd": 0.2465591483393025, "chroma_jsd": 0.9093376362151224, "role_structure_error": 0.34415142564741935, "tsse": 0.531465438080223 }, "diagnostics": { "notes": 611, "sounding_bars": 4.375, "empty_bar_rate": 0.84375, "role_assignments": [ { "program": 0, "drum": false, "notes": 15, "role": "melody" }, { "program": 32, "drum": false, "notes": 20, "role": "bass" }, { "program": 0, "drum": false, "notes": 87, "role": "chords" }, { "program": 0, "drum": true, "notes": 135, "role": "drums" }, { "program": 24, "drum": false, "notes": 201, "role": "chords" }, { "program": 0, "drum": false, "notes": 84, "role": "chords" }, { "program": 0, "drum": false, "notes": 51, "role": "chords" }, { "program": 0, "drum": false, "notes": 18, "role": "accompaniment" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 12, 12, 12, 12, 12, 12, 12, 12 ], "violation_count": 17, "violations": [ { "voice": 1, "bar": 9, "offset_beats": 36, "duration_beats": 4.5 }, { "voice": 1, "bar": 10, "offset_beats": 40.5, "duration_beats": 4.5 }, { "voice": 1, "bar": 11, "offset_beats": 45, "duration_beats": 4.5 }, { "voice": 5, "bar": 8, "offset_beats": 32, "duration_beats": 4.5 }, { "voice": 5, "bar": 9, "offset_beats": 36.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 10, "offset_beats": 40.25, "duration_beats": 4 }, { "voice": 5, "bar": 11, "offset_beats": 44.25, "duration_beats": 4.249603174603174 }, { "voice": 6, "bar": 10, "offset_beats": 40, "duration_beats": 4.5 }, { "voice": 6, "bar": 11, "offset_beats": 44.5, "duration_beats": 4.25 }, { "voice": 7, "bar": 8, "offset_beats": 32, "duration_beats": 4.25 }, { "voice": 7, "bar": 9, "offset_beats": 36.25, "duration_beats": 4 }, { "voice": 7, "bar": 10, "offset_beats": 40.25, "duration_beats": 4 }, { "voice": 7, "bar": 11, "offset_beats": 44.25, "duration_beats": 2.75 }, { "voice": 8, "bar": 8, "offset_beats": 32, "duration_beats": 5 }, { "voice": 8, "bar": 9, "offset_beats": 37, "duration_beats": 4 }, { "voice": 8, "bar": 10, "offset_beats": 41, "duration_beats": 4 }, { "voice": 8, "bar": 11, "offset_beats": 45, "duration_beats": 4 } ] }, "listening_note": "Native output: 4.4 / 32 bars. This run ended before the requested 32-bar boundary. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "9a40b25d95a1516818f91ccf5136b0d76be495ca42e62b2a48b67dc554b6f711", "mp3": "6858609c324e478e0f42780222b1bbebfc8978f12779be5b1be86c0225020fa7", "wav": "d13e12961dcd5e44f38c256d19d77611517107be769a8d11ef203ea6f88dd11a" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-2_mupt.wav", "source_wav_sha256": "d13e12961dcd5e44f38c256d19d77611517107be769a8d11ef203ea6f88dd11a", "source_mp3_sha256": "42c511b1ee9c267356241684dd826e997350c64f22180352db577b15ed76e464", "source_audio_duration": 96.130612, "last_note_end_seconds": 29.260934319352376, "trim_end_seconds": 30.760934319352376, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-3", "window": "Track01672.npz:16", "model": "mupt", "name": "MuPT 1.97B", "midi": "assets/song-3_mupt.mid", "mp3": "assets/song-3_mupt.mp3", "wav": "assets/song-3_mupt.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/mupt/song-3/result.json", "source_midi_sha256": "75b885479bf99dc6ffb38b1e45b464dc4dda481bb67765d26e74ea8e99747918", "seed": 20260923, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 13.125, "prefix_seconds": 15.238080359925418, "duration": 76.1904017996271, "audio_duration": 41.769796, "notes": 1003, "peak": 0.40005943179130554, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.138072562358277, "generation": { "prefix_tokens": 2532, "total_tokens": 6628, "decoded_bars": 17, "observed_voices": 5, "decoded_voices": 6, "unlabelled_extra_voice_program": 0, "reached_requested_boundary": false }, "metrics": { "rbde": 0.7504720138278295, "rhythm_jsd": 0.16554374819632456, "chroma_jsd": 0.8009641277301096, "role_structure_error": 0.1530785647784228, "tsse": 0.7261092087593276 }, "diagnostics": { "notes": 1003, "sounding_bars": 13.125, "empty_bar_rate": 0.5625, "role_assignments": [ { "program": 0, "drum": false, "notes": 43, "role": "melody" }, { "program": 32, "drum": false, "notes": 51, "role": "bass" }, { "program": 0, "drum": false, "notes": 359, "role": "chords" }, { "program": 0, "drum": true, "notes": 174, "role": "drums" }, { "program": 24, "drum": false, "notes": 163, "role": "chords" }, { "program": 0, "drum": false, "notes": 213, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 17, 17, 17, 17, 17, 17 ], "violation_count": 43, "violations": [ { "voice": 1, "bar": 8, "offset_beats": 32, "duration_beats": 4.75 }, { "voice": 1, "bar": 9, "offset_beats": 36.75, "duration_beats": 5.5 }, { "voice": 1, "bar": 10, "offset_beats": 42.25, "duration_beats": 5.75 }, { "voice": 1, "bar": 11, "offset_beats": 48, "duration_beats": 5.75 }, { "voice": 1, "bar": 12, "offset_beats": 53.75, "duration_beats": 6 }, { "voice": 1, "bar": 13, "offset_beats": 59.75, "duration_beats": 6 }, { "voice": 1, "bar": 14, "offset_beats": 65.75, "duration_beats": 6.25 }, { "voice": 1, "bar": 15, "offset_beats": 72, "duration_beats": 6.25 }, { "voice": 1, "bar": 16, "offset_beats": 78.25, "duration_beats": 6.25 }, { "voice": 2, "bar": 10, "offset_beats": 40, "duration_beats": 4.25 }, { "voice": 2, "bar": 11, "offset_beats": 44.25, "duration_beats": 4.25 }, { "voice": 2, "bar": 12, "offset_beats": 48.5, "duration_beats": 4.5 }, { "voice": 2, "bar": 13, "offset_beats": 53, "duration_beats": 4.5 }, { "voice": 2, "bar": 14, "offset_beats": 57.5, "duration_beats": 4.5 }, { "voice": 2, "bar": 15, "offset_beats": 62, "duration_beats": 4.75 }, { "voice": 2, "bar": 16, "offset_beats": 66.75, "duration_beats": 4.5 }, { "voice": 3, "bar": 9, "offset_beats": 36, "duration_beats": 4.5 }, { "voice": 3, "bar": 10, "offset_beats": 40.5, "duration_beats": 4.5 }, { "voice": 3, "bar": 11, "offset_beats": 45, "duration_beats": 4.5 }, { "voice": 3, "bar": 12, "offset_beats": 49.5, "duration_beats": 5 }, { "voice": 3, "bar": 13, "offset_beats": 54.5, "duration_beats": 5 }, { "voice": 3, "bar": 14, "offset_beats": 59.5, "duration_beats": 5 }, { "voice": 3, "bar": 15, "offset_beats": 64.5, "duration_beats": 5 }, { "voice": 3, "bar": 16, "offset_beats": 69.5, "duration_beats": 3.75 }, { "voice": 4, "bar": 9, "offset_beats": 36, "duration_beats": 4.25 }, { "voice": 4, "bar": 10, "offset_beats": 40.25, "duration_beats": 4.25 }, { "voice": 4, "bar": 11, "offset_beats": 44.5, "duration_beats": 4.25 }, { "voice": 4, "bar": 12, "offset_beats": 48.75, "duration_beats": 4.5 }, { "voice": 4, "bar": 13, "offset_beats": 53.25, "duration_beats": 4.5 }, { "voice": 4, "bar": 14, "offset_beats": 57.75, "duration_beats": 4.5 }, { "voice": 4, "bar": 15, "offset_beats": 62.25, "duration_beats": 4.5 }, { "voice": 4, "bar": 16, "offset_beats": 66.75, "duration_beats": 4 }, { "voice": 5, "bar": 12, "offset_beats": 48, "duration_beats": 4.25 }, { "voice": 5, "bar": 13, "offset_beats": 52.25, "duration_beats": 4.5 }, { "voice": 5, "bar": 14, "offset_beats": 56.75, "duration_beats": 4.5 }, { "voice": 5, "bar": 15, "offset_beats": 61.25, "duration_beats": 4.5 }, { "voice": 5, "bar": 16, "offset_beats": 65.75, "duration_beats": 4 }, { "voice": 6, "bar": 11, "offset_beats": 44, "duration_beats": 4.25 }, { "voice": 6, "bar": 12, "offset_beats": 48.25, "duration_beats": 4.75 }, { "voice": 6, "bar": 13, "offset_beats": 53, "duration_beats": 4.5 }, { "voice": 6, "bar": 14, "offset_beats": 57.5, "duration_beats": 4.5 }, { "voice": 6, "bar": 15, "offset_beats": 62, "duration_beats": 4.5 }, { "voice": 6, "bar": 16, "offset_beats": 66.5, "duration_beats": 4 } ] }, "listening_note": "Native output: 13.1 / 32 bars. This run ended before the requested 32-bar boundary. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "90cd6e5e1c89b819489acb7599980bef7991d5351e67cf690d1fed532cec0c65", "mp3": "c8e7ff8bc3d7fa7e48fb16919f75b4aecb5768a06eb8748ee05c4221b741b029", "wav": "0a16aaeecd3b22cd0872be426485d086d51bb7e7f128558f8ee76762182219b2" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-3_mupt.wav", "source_wav_sha256": "0a16aaeecd3b22cd0872be426485d086d51bb7e7f128558f8ee76762182219b2", "source_mp3_sha256": "b0dd25856469162c63d29e86cdc39ac7dbff8b0621eab39dd6243c3c6f34b9b7", "source_audio_duration": 77.740408, "last_note_end_seconds": 40.238055950428055, "trim_end_seconds": 41.738055950428055, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-4", "window": "Track01657.npz:25", "model": "mupt", "name": "MuPT 1.97B", "midi": "assets/song-4_mupt.mid", "mp3": "assets/song-4_mupt.mp3", "wav": "assets/song-4_mupt.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/mupt/song-4/result.json", "source_midi_sha256": "99cfd42588759d1ca2c9823ee65612c330d582a9444a6cdd0efcf96bf9cd9d38", "seed": 20260924, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 15.625, "prefix_seconds": 16, "duration": 80, "audio_duration": 48.796735, "notes": 545, "peak": 0.22759996354579926, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 1718, "total_tokens": 5814, "decoded_bars": 24, "observed_voices": 5, "decoded_voices": 7, "unlabelled_extra_voice_program": 0, "reached_requested_boundary": false }, "metrics": { "rbde": 0.6488585844610916, "rhythm_jsd": 0.04194722779243606, "chroma_jsd": 0.6072115968671365, "role_structure_error": 0.1657093862596294, "tsse": 0.7234646069845481 }, "diagnostics": { "notes": 545, "sounding_bars": 15.625, "empty_bar_rate": 0.5, "role_assignments": [ { "program": 0, "drum": false, "notes": 43, "role": "melody" }, { "program": 32, "drum": false, "notes": 46, "role": "bass" }, { "program": 0, "drum": false, "notes": 83, "role": "chords" }, { "program": 0, "drum": true, "notes": 130, "role": "drums" }, { "program": 24, "drum": false, "notes": 100, "role": "accompaniment" }, { "program": 0, "drum": false, "notes": 72, "role": "accompaniment" }, { "program": 0, "drum": false, "notes": 71, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 24, 24, 24, 24, 24, 24, 24 ], "violation_count": 104, "violations": [ { "voice": 1, "bar": 9, "offset_beats": 33.5, "duration_beats": 4 }, { "voice": 1, "bar": 10, "offset_beats": 37.5, "duration_beats": 3.75 }, { "voice": 1, "bar": 11, "offset_beats": 41.25, "duration_beats": 4.25 }, { "voice": 1, "bar": 12, "offset_beats": 45.5, "duration_beats": 4 }, { "voice": 1, "bar": 13, "offset_beats": 49.5, "duration_beats": 4 }, { "voice": 1, "bar": 14, "offset_beats": 53.5, "duration_beats": 4 }, { "voice": 1, "bar": 15, "offset_beats": 57.5, "duration_beats": 4 }, { "voice": 1, "bar": 16, "offset_beats": 61.5, "duration_beats": 4 }, { "voice": 1, "bar": 17, "offset_beats": 65.5, "duration_beats": 4 }, { "voice": 1, "bar": 18, "offset_beats": 69.5, "duration_beats": 4 }, { "voice": 1, "bar": 19, "offset_beats": 73.5, "duration_beats": 4 }, { "voice": 1, "bar": 20, "offset_beats": 77.5, "duration_beats": 4 }, { "voice": 1, "bar": 21, "offset_beats": 81.5, "duration_beats": 4 }, { "voice": 1, "bar": 22, "offset_beats": 85.5, "duration_beats": 4 }, { "voice": 1, "bar": 23, "offset_beats": 89.5, "duration_beats": 4 }, { "voice": 2, "bar": 9, "offset_beats": 34.25, "duration_beats": 3.5 }, { "voice": 2, "bar": 10, "offset_beats": 37.75, "duration_beats": 3.5 }, { "voice": 2, "bar": 11, "offset_beats": 41.25, "duration_beats": 4 }, { "voice": 2, "bar": 12, "offset_beats": 45.25, "duration_beats": 3.75 }, { "voice": 2, "bar": 13, "offset_beats": 49, "duration_beats": 3.75 }, { "voice": 2, "bar": 14, "offset_beats": 52.75, "duration_beats": 4 }, { "voice": 2, "bar": 15, "offset_beats": 56.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 16, "offset_beats": 60.5, "duration_beats": 4 }, { "voice": 2, "bar": 17, "offset_beats": 64.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 18, "offset_beats": 68.25, "duration_beats": 3.75 }, { "voice": 2, "bar": 19, "offset_beats": 72, "duration_beats": 4 }, { "voice": 2, "bar": 20, "offset_beats": 76, "duration_beats": 4 }, { "voice": 2, "bar": 21, "offset_beats": 80, "duration_beats": 4 }, { "voice": 2, "bar": 22, "offset_beats": 84, "duration_beats": 4 }, { "voice": 2, "bar": 23, "offset_beats": 88, "duration_beats": 4 }, { "voice": 3, "bar": 9, "offset_beats": 34.25, "duration_beats": 3.75 }, { "voice": 3, "bar": 10, "offset_beats": 38, "duration_beats": 4 }, { "voice": 3, "bar": 11, "offset_beats": 42, "duration_beats": 3.75 }, { "voice": 3, "bar": 12, "offset_beats": 45.75, "duration_beats": 4.25 }, { "voice": 3, "bar": 13, "offset_beats": 50, "duration_beats": 4 }, { "voice": 3, "bar": 14, "offset_beats": 54, "duration_beats": 4 }, { "voice": 3, "bar": 15, "offset_beats": 58, "duration_beats": 4 }, { "voice": 3, "bar": 16, "offset_beats": 62, "duration_beats": 4 }, { "voice": 3, "bar": 17, "offset_beats": 66, "duration_beats": 4 }, { "voice": 3, "bar": 18, "offset_beats": 70, "duration_beats": 4 }, { "voice": 3, "bar": 19, "offset_beats": 74, "duration_beats": 4.25 }, { "voice": 3, "bar": 20, "offset_beats": 78.25, "duration_beats": 4.25 }, { "voice": 3, "bar": 21, "offset_beats": 82.5, "duration_beats": 4 }, { "voice": 3, "bar": 22, "offset_beats": 86.5, "duration_beats": 4 }, { "voice": 3, "bar": 23, "offset_beats": 90.5, "duration_beats": 4 }, { "voice": 4, "bar": 9, "offset_beats": 34.25, "duration_beats": 3.75 }, { "voice": 4, "bar": 10, "offset_beats": 38, "duration_beats": 3.75 }, { "voice": 4, "bar": 11, "offset_beats": 41.75, "duration_beats": 4 }, { "voice": 4, "bar": 12, "offset_beats": 45.75, "duration_beats": 4 }, { "voice": 4, "bar": 13, "offset_beats": 49.75, "duration_beats": 4 }, { "voice": 4, "bar": 14, "offset_beats": 53.75, "duration_beats": 4 }, { "voice": 4, "bar": 15, "offset_beats": 57.75, "duration_beats": 4 }, { "voice": 4, "bar": 16, "offset_beats": 61.75, "duration_beats": 4 }, { "voice": 4, "bar": 17, "offset_beats": 65.75, "duration_beats": 4 }, { "voice": 4, "bar": 18, "offset_beats": 69.75, "duration_beats": 4 }, { "voice": 4, "bar": 19, "offset_beats": 73.75, "duration_beats": 4.25 }, { "voice": 4, "bar": 20, "offset_beats": 78, "duration_beats": 4.25 }, { "voice": 4, "bar": 21, "offset_beats": 82.25, "duration_beats": 4.25 }, { "voice": 4, "bar": 22, "offset_beats": 86.5, "duration_beats": 4.25 }, { "voice": 4, "bar": 23, "offset_beats": 90.75, "duration_beats": 1.5 }, { "voice": 5, "bar": 9, "offset_beats": 34, "duration_beats": 3.5 }, { "voice": 5, "bar": 10, "offset_beats": 37.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 11, "offset_beats": 41.25, "duration_beats": 4.25 }, { "voice": 5, "bar": 12, "offset_beats": 45.5, "duration_beats": 4 }, { "voice": 5, "bar": 13, "offset_beats": 49.5, "duration_beats": 4 }, { "voice": 5, "bar": 14, "offset_beats": 53.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 15, "offset_beats": 57.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 16, "offset_beats": 61, "duration_beats": 3.75 }, { "voice": 5, "bar": 17, "offset_beats": 64.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 18, "offset_beats": 68.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 19, "offset_beats": 72.25, "duration_beats": 4 }, { "voice": 5, "bar": 20, "offset_beats": 76.25, "duration_beats": 4 }, { "voice": 5, "bar": 21, "offset_beats": 80.25, "duration_beats": 4 }, { "voice": 5, "bar": 22, "offset_beats": 84.25, "duration_beats": 4 }, { "voice": 5, "bar": 23, "offset_beats": 88.25, "duration_beats": 4 }, { "voice": 6, "bar": 9, "offset_beats": 33.5, "duration_beats": 2 }, { "voice": 6, "bar": 10, "offset_beats": 35.5, "duration_beats": 2.375 }, { "voice": 6, "bar": 11, "offset_beats": 37.875, "duration_beats": 2.25 }, { "voice": 6, "bar": 12, "offset_beats": 40.125, "duration_beats": 2.25 }, { "voice": 6, "bar": 13, "offset_beats": 42.375, "duration_beats": 2.25 }, { "voice": 6, "bar": 14, "offset_beats": 44.625, "duration_beats": 2.25 }, { "voice": 6, "bar": 15, "offset_beats": 46.875, "duration_beats": 2.25 }, { "voice": 6, "bar": 16, "offset_beats": 49.125, "duration_beats": 2.5 }, { "voice": 6, "bar": 17, "offset_beats": 51.625, "duration_beats": 2.25 }, { "voice": 6, "bar": 18, "offset_beats": 53.875, "duration_beats": 2.25 }, { "voice": 6, "bar": 19, "offset_beats": 56.125, "duration_beats": 2.25 }, { "voice": 6, "bar": 20, "offset_beats": 58.375, "duration_beats": 2.5 }, { "voice": 6, "bar": 21, "offset_beats": 60.875, "duration_beats": 2.5 }, { "voice": 6, "bar": 22, "offset_beats": 63.375, "duration_beats": 2.25 }, { "voice": 6, "bar": 23, "offset_beats": 65.625, "duration_beats": 4 }, { "voice": 7, "bar": 10, "offset_beats": 37.75, "duration_beats": 1.75 }, { "voice": 7, "bar": 11, "offset_beats": 39.5, "duration_beats": 1.75 }, { "voice": 7, "bar": 12, "offset_beats": 41.25, "duration_beats": 1.625 }, { "voice": 7, "bar": 13, "offset_beats": 42.875, "duration_beats": 1.75 }, { "voice": 7, "bar": 14, "offset_beats": 44.625, "duration_beats": 1.75 }, { "voice": 7, "bar": 15, "offset_beats": 46.375, "duration_beats": 1.75 }, { "voice": 7, "bar": 16, "offset_beats": 48.125, "duration_beats": 1.875 }, { "voice": 7, "bar": 17, "offset_beats": 50, "duration_beats": 1.75 }, { "voice": 7, "bar": 18, "offset_beats": 51.75, "duration_beats": 1.75 }, { "voice": 7, "bar": 19, "offset_beats": 53.5, "duration_beats": 2 }, { "voice": 7, "bar": 20, "offset_beats": 55.5, "duration_beats": 2 }, { "voice": 7, "bar": 21, "offset_beats": 57.5, "duration_beats": 2 }, { "voice": 7, "bar": 22, "offset_beats": 59.5, "duration_beats": 2 }, { "voice": 7, "bar": 23, "offset_beats": 61.5, "duration_beats": 4 } ] }, "listening_note": "Native output: 15.6 / 32 bars. This run ended before the requested 32-bar boundary. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "c8811ed0febbeb05e2edc9719b41a96a63588a94b38fca77bd97b415b00b485c", "mp3": "dfb6f36389dade8591484b9078f0c71110d6c0ae90ea896ef75d750461cb7da7", "wav": "8a42fc632a765f8050bcceb2bf5acccfe183b6359edef1782369e6c3062f4983" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-4_mupt.wav", "source_wav_sha256": "8a42fc632a765f8050bcceb2bf5acccfe183b6359edef1782369e6c3062f4983", "source_mp3_sha256": "a861954b9fd7b221554adf0bfc2704b5ce633edf3eef68c5a2d0ae3d2efb9633", "source_audio_duration": 81.528163, "last_note_end_seconds": 47.25, "trim_end_seconds": 48.75, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-5", "window": "Track01527.npz:112", "model": "mupt", "name": "MuPT 1.97B", "midi": "assets/song-5_mupt.mid", "mp3": "assets/song-5_mupt.mp3", "wav": "assets/song-5_mupt.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/mupt/song-5/result.json", "source_midi_sha256": "874e5b81aca883c5472570a0003c28e85716409222c00733c588828ee620ea60", "seed": 20260925, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 9, "prefix_seconds": 11.99923150692855, "duration": 59.996157534642755, "audio_duration": 27.036735, "notes": 1241, "peak": 0.36702871322631836, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 11.899229024943311, "generation": { "prefix_tokens": 1983, "total_tokens": 6079, "decoded_bars": 17, "observed_voices": 5, "decoded_voices": 7, "unlabelled_extra_voice_program": 0, "reached_requested_boundary": false }, "metrics": { "rbde": 1.0053350532616343, "rhythm_jsd": 0.09939164707997826, "chroma_jsd": 0.7954836352555257, "role_structure_error": 0.14069306863201347, "tsse": 0.6696210559920053 }, "diagnostics": { "notes": 1241, "sounding_bars": 9, "empty_bar_rate": 0.71875, "role_assignments": [ { "program": 0, "drum": false, "notes": 29, "role": "melody" }, { "program": 32, "drum": false, "notes": 13, "role": "bass" }, { "program": 0, "drum": false, "notes": 74, "role": "chords" }, { "program": 0, "drum": true, "notes": 121, "role": "drums" }, { "program": 24, "drum": false, "notes": 168, "role": "chords" }, { "program": 0, "drum": false, "notes": 440, "role": "chords" }, { "program": 0, "drum": false, "notes": 396, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 17, 17, 17, 17, 17, 17, 17 ], "violation_count": 23, "violations": [ { "voice": 1, "bar": 9, "offset_beats": 36, "duration_beats": 4.5 }, { "voice": 1, "bar": 10, "offset_beats": 40.5, "duration_beats": 4.5 }, { "voice": 1, "bar": 11, "offset_beats": 45, "duration_beats": 4.5 }, { "voice": 1, "bar": 12, "offset_beats": 49.5, "duration_beats": 4 }, { "voice": 1, "bar": 13, "offset_beats": 53.5, "duration_beats": 4 }, { "voice": 1, "bar": 14, "offset_beats": 57.5, "duration_beats": 4 }, { "voice": 1, "bar": 15, "offset_beats": 61.5, "duration_beats": 4 }, { "voice": 1, "bar": 16, "offset_beats": 65.5, "duration_beats": 4 }, { "voice": 6, "bar": 9, "offset_beats": 35.75, "duration_beats": 3.75 }, { "voice": 6, "bar": 10, "offset_beats": 39.5, "duration_beats": 3.75 }, { "voice": 6, "bar": 11, "offset_beats": 43.25, "duration_beats": 3.75 }, { "voice": 6, "bar": 12, "offset_beats": 47, "duration_beats": 3.75 }, { "voice": 6, "bar": 13, "offset_beats": 50.75, "duration_beats": 3.75 }, { "voice": 6, "bar": 14, "offset_beats": 54.5, "duration_beats": 3.75 }, { "voice": 6, "bar": 15, "offset_beats": 58.25, "duration_beats": 3.75 }, { "voice": 6, "bar": 16, "offset_beats": 62, "duration_beats": 4 }, { "voice": 7, "bar": 10, "offset_beats": 39.75, "duration_beats": 3.75 }, { "voice": 7, "bar": 11, "offset_beats": 43.5, "duration_beats": 3.75 }, { "voice": 7, "bar": 12, "offset_beats": 47.25, "duration_beats": 3.75 }, { "voice": 7, "bar": 13, "offset_beats": 51, "duration_beats": 3.75 }, { "voice": 7, "bar": 14, "offset_beats": 54.75, "duration_beats": 3.75 }, { "voice": 7, "bar": 15, "offset_beats": 58.5, "duration_beats": 3.75 }, { "voice": 7, "bar": 16, "offset_beats": 62.25, "duration_beats": 4 } ] }, "listening_note": "Native output: 9.0 / 32 bars. This run ended before the requested 32-bar boundary. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "2b68a93f7e6158842444c560510724a7964783422475db4d6d938c904e182be5", "mp3": "4e1d0923ff24f1073f48af6af6eaf4566bc7ea1a56d69ca26e5cea0997f86f8c", "wav": "43cf7d53b292843ae487b73624c1b5a5ca4f1334f7ed45c5b85b5d1da4211342" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-5_mupt.wav", "source_wav_sha256": "43cf7d53b292843ae487b73624c1b5a5ca4f1334f7ed45c5b85b5d1da4211342", "source_mp3_sha256": "6fa7ff3d1e3a1d3b5a12a114bc91e006fd8f574bb0725bae18242310013ef815", "source_audio_duration": 61.54449, "last_note_end_seconds": 25.498366952223172, "trim_end_seconds": 26.998366952223172, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-1", "window": "Track01646.npz:73", "model": "notagen", "name": "NotaGen RL3", "midi": "assets/song-1_notagen.mid", "mp3": "assets/song-1_notagen.mp3", "wav": "assets/song-1_notagen.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/notagen/song-1/result.json", "source_midi_sha256": "ec9c6c0a021329e725dafe7da72a4d826d0d00b5a9918e1109f2d3989d23f12a", "seed": 20260921, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 23.1875, "prefix_seconds": 16, "duration": 80, "audio_duration": 63.921633, "notes": 1391, "peak": 0.24266661703586578, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_patches": 219, "total_patches": 1024, "decoded_bars": 31, "stop_reason": "context_limit", "reached_requested_boundary": false }, "metrics": { "rbde": 0.7503722776079306, "rhythm_jsd": 0.0476735270924906, "chroma_jsd": 0.6385839408739892, "role_structure_error": 0.13854179002547581, "tsse": 0.6235064018400148 }, "diagnostics": { "notes": 1391, "sounding_bars": 23.1875, "empty_bar_rate": 0.25, "role_assignments": [ { "program": 0, "drum": false, "notes": 324, "role": "chords" }, { "program": 32, "drum": false, "notes": 114, "role": "bass" }, { "program": 0, "drum": false, "notes": 460, "role": "accompaniment" }, { "program": 0, "drum": true, "notes": 308, "role": "drums" }, { "program": 24, "drum": false, "notes": 185, "role": "accompaniment" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 31, 31, 31, 31, 31 ], "violation_count": 69, "violations": [ { "voice": 1, "bar": 12, "offset_beats": 48, "duration_beats": 4.5 }, { "voice": 1, "bar": 13, "offset_beats": 52.5, "duration_beats": 4.5 }, { "voice": 1, "bar": 14, "offset_beats": 57, "duration_beats": 4 }, { "voice": 1, "bar": 15, "offset_beats": 61, "duration_beats": 4 }, { "voice": 1, "bar": 16, "offset_beats": 65, "duration_beats": 4 }, { "voice": 1, "bar": 17, "offset_beats": 69, "duration_beats": 4 }, { "voice": 1, "bar": 18, "offset_beats": 73, "duration_beats": 4 }, { "voice": 1, "bar": 19, "offset_beats": 77, "duration_beats": 4 }, { "voice": 1, "bar": 20, "offset_beats": 81, "duration_beats": 4 }, { "voice": 1, "bar": 21, "offset_beats": 85, "duration_beats": 4 }, { "voice": 1, "bar": 22, "offset_beats": 89, "duration_beats": 4 }, { "voice": 1, "bar": 23, "offset_beats": 93, "duration_beats": 4 }, { "voice": 1, "bar": 24, "offset_beats": 97, "duration_beats": 4 }, { "voice": 1, "bar": 25, "offset_beats": 101, "duration_beats": 4 }, { "voice": 1, "bar": 26, "offset_beats": 105, "duration_beats": 4 }, { "voice": 1, "bar": 27, "offset_beats": 109, "duration_beats": 4 }, { "voice": 1, "bar": 28, "offset_beats": 113, "duration_beats": 4 }, { "voice": 1, "bar": 29, "offset_beats": 117, "duration_beats": 4 }, { "voice": 1, "bar": 30, "offset_beats": 121, "duration_beats": 4 }, { "voice": 2, "bar": 13, "offset_beats": 51.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 14, "offset_beats": 55, "duration_beats": 3.5 }, { "voice": 2, "bar": 15, "offset_beats": 58.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 16, "offset_beats": 62, "duration_beats": 3.5 }, { "voice": 2, "bar": 17, "offset_beats": 65.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 18, "offset_beats": 69, "duration_beats": 3.5 }, { "voice": 2, "bar": 19, "offset_beats": 72.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 20, "offset_beats": 76, "duration_beats": 3.5 }, { "voice": 2, "bar": 21, "offset_beats": 79.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 22, "offset_beats": 83, "duration_beats": 3.5 }, { "voice": 2, "bar": 23, "offset_beats": 86.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 24, "offset_beats": 90, "duration_beats": 3.5 }, { "voice": 2, "bar": 25, "offset_beats": 93.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 26, "offset_beats": 97, "duration_beats": 3.5 }, { "voice": 2, "bar": 27, "offset_beats": 100.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 28, "offset_beats": 104, "duration_beats": 3.5 }, { "voice": 2, "bar": 29, "offset_beats": 107.5, "duration_beats": 4 }, { "voice": 2, "bar": 30, "offset_beats": 111.5, "duration_beats": 4 }, { "voice": 3, "bar": 13, "offset_beats": 51.75, "duration_beats": 3.5 }, { "voice": 3, "bar": 14, "offset_beats": 55.25, "duration_beats": 3.75 }, { "voice": 3, "bar": 15, "offset_beats": 59, "duration_beats": 3.75 }, { "voice": 3, "bar": 16, "offset_beats": 62.75, "duration_beats": 3.75 }, { "voice": 3, "bar": 17, "offset_beats": 66.5, "duration_beats": 3.75 }, { "voice": 3, "bar": 18, "offset_beats": 70.25, "duration_beats": 3.75 }, { "voice": 3, "bar": 19, "offset_beats": 74, "duration_beats": 3.75 }, { "voice": 3, "bar": 20, "offset_beats": 77.75, "duration_beats": 3.5 }, { "voice": 3, "bar": 21, "offset_beats": 81.25, "duration_beats": 3.5 }, { "voice": 3, "bar": 22, "offset_beats": 84.75, "duration_beats": 3.5 }, { "voice": 3, "bar": 23, "offset_beats": 88.25, "duration_beats": 3.5 }, { "voice": 3, "bar": 24, "offset_beats": 91.75, "duration_beats": 3.5 }, { "voice": 3, "bar": 25, "offset_beats": 95.25, "duration_beats": 3.5 }, { "voice": 3, "bar": 26, "offset_beats": 98.75, "duration_beats": 3.5 }, { "voice": 3, "bar": 27, "offset_beats": 102.25, "duration_beats": 3.5 }, { "voice": 3, "bar": 28, "offset_beats": 105.75, "duration_beats": 3.5 }, { "voice": 3, "bar": 29, "offset_beats": 109.25, "duration_beats": 3.5 }, { "voice": 3, "bar": 30, "offset_beats": 112.75, "duration_beats": 3.5 }, { "voice": 5, "bar": 17, "offset_beats": 67.5, "duration_beats": 4 }, { "voice": 5, "bar": 18, "offset_beats": 71.5, "duration_beats": 4 }, { "voice": 5, "bar": 19, "offset_beats": 75.5, "duration_beats": 4 }, { "voice": 5, "bar": 20, "offset_beats": 79.5, "duration_beats": 4 }, { "voice": 5, "bar": 21, "offset_beats": 83.5, "duration_beats": 4 }, { "voice": 5, "bar": 22, "offset_beats": 87.5, "duration_beats": 4 }, { "voice": 5, "bar": 23, "offset_beats": 91.5, "duration_beats": 4 }, { "voice": 5, "bar": 24, "offset_beats": 95.5, "duration_beats": 4 }, { "voice": 5, "bar": 25, "offset_beats": 99.5, "duration_beats": 4 }, { "voice": 5, "bar": 26, "offset_beats": 103.5, "duration_beats": 4 }, { "voice": 5, "bar": 27, "offset_beats": 107.5, "duration_beats": 4 }, { "voice": 5, "bar": 28, "offset_beats": 111.5, "duration_beats": 4 }, { "voice": 5, "bar": 29, "offset_beats": 115.5, "duration_beats": 4 }, { "voice": 5, "bar": 30, "offset_beats": 119.5, "duration_beats": 4 } ] }, "listening_note": "Native output: 23.2 / 32 bars. Reached the 1,024-patch context limit in this run. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "2c3bd4a15f2e5b59716f4a0fd52fb783eefa5059138a283eebe6e263d9f17962", "mp3": "849ed857e742fdcaef3f77defaedfb1d41a77de52c4e8acba7e1e2d967cb9e75", "wav": "e50c19a867ba280f27084e7eb791b390277f7ab93bef4aef39706cf93481e7d2" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-1_notagen.wav", "source_wav_sha256": "e50c19a867ba280f27084e7eb791b390277f7ab93bef4aef39706cf93481e7d2", "source_mp3_sha256": "1c25ba47c6a59f22fc99a678fad2b12159d6a6abb10362c62a1b8406c16347eb", "source_audio_duration": 81.528163, "last_note_end_seconds": 62.375, "trim_end_seconds": 63.875, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-2", "window": "Track01631.npz:32", "model": "notagen", "name": "NotaGen RL3", "midi": "assets/song-2_notagen.mid", "mp3": "assets/song-2_notagen.mp3", "wav": "assets/song-2_notagen.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/notagen/song-2/result.json", "source_midi_sha256": "6b632f3a4395521958ce21644eb7513aabcc325409f5c97ea90fdd3d383f2fa6", "seed": 20260922, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 18, "prefix_seconds": 18.916159559985374, "duration": 94.58079779992687, "audio_duration": 63.007347, "notes": 1395, "peak": 0.33230891823768616, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 18.816145124716552, "generation": { "prefix_patches": 277, "total_patches": 1024, "decoded_bars": 24, "stop_reason": "context_limit", "reached_requested_boundary": false }, "metrics": { "rbde": 0.40294108148754554, "rhythm_jsd": 0.09940967264074563, "chroma_jsd": 0.6946375125343643, "role_structure_error": 0.22498462294468985, "tsse": 0.7090511821684923 }, "diagnostics": { "notes": 1395, "sounding_bars": 18, "empty_bar_rate": 0.4375, "role_assignments": [ { "program": 0, "drum": false, "notes": 64, "role": "melody" }, { "program": 32, "drum": false, "notes": 128, "role": "bass" }, { "program": 0, "drum": false, "notes": 273, "role": "chords" }, { "program": 0, "drum": true, "notes": 467, "role": "drums" }, { "program": 24, "drum": false, "notes": 463, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 24, 24, 25, 24, 24 ], "violation_count": 69, "violations": [ { "voice": 1, "bar": 9, "offset_beats": 35.5, "duration_beats": 3.5 }, { "voice": 1, "bar": 10, "offset_beats": 39, "duration_beats": 3.5 }, { "voice": 1, "bar": 11, "offset_beats": 42.5, "duration_beats": 3.5 }, { "voice": 1, "bar": 12, "offset_beats": 46, "duration_beats": 3.5 }, { "voice": 1, "bar": 13, "offset_beats": 49.5, "duration_beats": 3.5 }, { "voice": 1, "bar": 14, "offset_beats": 53, "duration_beats": 3.5 }, { "voice": 1, "bar": 15, "offset_beats": 56.5, "duration_beats": 3.5 }, { "voice": 1, "bar": 16, "offset_beats": 60, "duration_beats": 3.5 }, { "voice": 1, "bar": 17, "offset_beats": 63.5, "duration_beats": 3.5 }, { "voice": 1, "bar": 18, "offset_beats": 67, "duration_beats": 3.5 }, { "voice": 1, "bar": 19, "offset_beats": 70.5, "duration_beats": 3.5 }, { "voice": 1, "bar": 20, "offset_beats": 74, "duration_beats": 3.5 }, { "voice": 1, "bar": 21, "offset_beats": 77.5, "duration_beats": 3.5 }, { "voice": 1, "bar": 22, "offset_beats": 81, "duration_beats": 3.5 }, { "voice": 1, "bar": 23, "offset_beats": 84.5, "duration_beats": 3.5 }, { "voice": 2, "bar": 9, "offset_beats": 35.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 10, "offset_beats": 39.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 11, "offset_beats": 43.25, "duration_beats": 3.75 }, { "voice": 2, "bar": 12, "offset_beats": 47, "duration_beats": 3.75 }, { "voice": 2, "bar": 13, "offset_beats": 50.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 14, "offset_beats": 54.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 15, "offset_beats": 58.25, "duration_beats": 3.75 }, { "voice": 2, "bar": 16, "offset_beats": 62, "duration_beats": 3.75 }, { "voice": 2, "bar": 17, "offset_beats": 65.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 18, "offset_beats": 69.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 19, "offset_beats": 73.25, "duration_beats": 3.75 }, { "voice": 2, "bar": 20, "offset_beats": 77, "duration_beats": 3.75 }, { "voice": 2, "bar": 21, "offset_beats": 80.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 22, "offset_beats": 84.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 23, "offset_beats": 88.25, "duration_beats": 3.75 }, { "voice": 3, "bar": 16, "offset_beats": 64, "duration_beats": 4.75 }, { "voice": 3, "bar": 17, "offset_beats": 68.75, "duration_beats": 4.75 }, { "voice": 3, "bar": 18, "offset_beats": 73.5, "duration_beats": 4.75 }, { "voice": 3, "bar": 19, "offset_beats": 78.25, "duration_beats": 4.75 }, { "voice": 3, "bar": 20, "offset_beats": 83, "duration_beats": 4.75 }, { "voice": 3, "bar": 21, "offset_beats": 87.75, "duration_beats": 4.75 }, { "voice": 3, "bar": 22, "offset_beats": 92.5, "duration_beats": 5 }, { "voice": 3, "bar": 23, "offset_beats": 97.5, "duration_beats": 1.75 }, { "voice": 3, "bar": 24, "offset_beats": 99.25, "duration_beats": 4.75 }, { "voice": 4, "bar": 9, "offset_beats": 35.5, "duration_beats": 3.75 }, { "voice": 4, "bar": 10, "offset_beats": 39.25, "duration_beats": 3.75 }, { "voice": 4, "bar": 11, "offset_beats": 43, "duration_beats": 4 }, { "voice": 4, "bar": 12, "offset_beats": 47, "duration_beats": 3.75 }, { "voice": 4, "bar": 13, "offset_beats": 50.75, "duration_beats": 3.75 }, { "voice": 4, "bar": 14, "offset_beats": 54.5, "duration_beats": 4 }, { "voice": 4, "bar": 15, "offset_beats": 58.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 16, "offset_beats": 62, "duration_beats": 3.75 }, { "voice": 4, "bar": 17, "offset_beats": 65.75, "duration_beats": 3.75 }, { "voice": 4, "bar": 18, "offset_beats": 69.5, "duration_beats": 3.75 }, { "voice": 4, "bar": 19, "offset_beats": 73.25, "duration_beats": 3.75 }, { "voice": 4, "bar": 20, "offset_beats": 77, "duration_beats": 3.75 }, { "voice": 4, "bar": 21, "offset_beats": 80.75, "duration_beats": 3.75 }, { "voice": 4, "bar": 22, "offset_beats": 84.5, "duration_beats": 3.75 }, { "voice": 4, "bar": 23, "offset_beats": 88.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 9, "offset_beats": 35.75, "duration_beats": 3.5 }, { "voice": 5, "bar": 10, "offset_beats": 39.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 11, "offset_beats": 43, "duration_beats": 3.5 }, { "voice": 5, "bar": 12, "offset_beats": 46.5, "duration_beats": 3.25 }, { "voice": 5, "bar": 13, "offset_beats": 49.75, "duration_beats": 3.25 }, { "voice": 5, "bar": 14, "offset_beats": 53, "duration_beats": 3.5 }, { "voice": 5, "bar": 15, "offset_beats": 56.5, "duration_beats": 3.25 }, { "voice": 5, "bar": 16, "offset_beats": 59.75, "duration_beats": 3.25 }, { "voice": 5, "bar": 17, "offset_beats": 63, "duration_beats": 3.75 }, { "voice": 5, "bar": 18, "offset_beats": 66.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 19, "offset_beats": 70.5, "duration_beats": 4.25 }, { "voice": 5, "bar": 20, "offset_beats": 74.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 21, "offset_beats": 78.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 22, "offset_beats": 82.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 23, "offset_beats": 86, "duration_beats": 3 } ] }, "listening_note": "Native output: 18.0 / 32 bars. Reached the 1,024-patch context limit in this run. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "a7da429a021ab127d9bde16bcc99758dcd24b4742c72de8aab7aaa0e6375d53f", "mp3": "2f8739c84f3db8a794968c479b206b00a5014513bd4227a1a71701b04eb22a8c", "wav": "5c73a00caaa322d09d6355b11d2f1742f4dd90864ea3bf7af3ac9c7d8d15e769" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-2_notagen.wav", "source_wav_sha256": "5c73a00caaa322d09d6355b11d2f1742f4dd90864ea3bf7af3ac9c7d8d15e769", "source_mp3_sha256": "013a020c03800bb5e30a02206f836ad3bbe5646c2ebacfad6575302592e82293", "source_audio_duration": 96.130612, "last_note_end_seconds": 61.477518569952466, "trim_end_seconds": 62.977518569952466, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-3", "window": "Track01672.npz:16", "model": "notagen", "name": "NotaGen RL3", "midi": "assets/song-3_notagen.mid", "mp3": "assets/song-3_notagen.mp3", "wav": "assets/song-3_notagen.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/notagen/song-3/result.json", "source_midi_sha256": "05edcbcd2bf1c1fefd694c99075f76ca04bd3fb4e19db7d3fcfe30d414e60be0", "seed": 20260923, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 32, "prefix_seconds": 15.238080359925418, "duration": 76.1904017996271, "audio_duration": 77.740408, "notes": 2509, "peak": 0.40005943179130554, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.138072562358277, "generation": { "prefix_patches": 215, "total_patches": 1024, "decoded_bars": 34, "stop_reason": "context_limit", "reached_requested_boundary": false }, "metrics": { "rbde": 7.054487014345163, "rhythm_jsd": 0.4568512980274891, "chroma_jsd": 0.43068932453436626, "role_structure_error": 0.5101978424987788, "tsse": 0.04924698756893823 }, "diagnostics": { "notes": 2509, "sounding_bars": 32, "empty_bar_rate": 0, "role_assignments": [ { "program": 0, "drum": false, "notes": 80, "role": "accompaniment" }, { "program": 32, "drum": false, "notes": 112, "role": "bass" }, { "program": 0, "drum": false, "notes": 989, "role": "chords" }, { "program": 0, "drum": true, "notes": 389, "role": "drums" }, { "program": 24, "drum": false, "notes": 939, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 34, 34, 34, 34, 34 ], "violation_count": 130, "violations": [ { "voice": 1, "bar": 8, "offset_beats": 32, "duration_beats": 4.75 }, { "voice": 1, "bar": 9, "offset_beats": 36.75, "duration_beats": 4.25 }, { "voice": 1, "bar": 10, "offset_beats": 41, "duration_beats": 4.5 }, { "voice": 1, "bar": 11, "offset_beats": 45.5, "duration_beats": 4.5 }, { "voice": 1, "bar": 12, "offset_beats": 50, "duration_beats": 4.5 }, { "voice": 1, "bar": 13, "offset_beats": 54.5, "duration_beats": 4.5 }, { "voice": 1, "bar": 14, "offset_beats": 59, "duration_beats": 9.5 }, { "voice": 1, "bar": 15, "offset_beats": 68.5, "duration_beats": 9.5 }, { "voice": 1, "bar": 16, "offset_beats": 78, "duration_beats": 5 }, { "voice": 1, "bar": 17, "offset_beats": 83, "duration_beats": 5 }, { "voice": 1, "bar": 18, "offset_beats": 88, "duration_beats": 5 }, { "voice": 1, "bar": 19, "offset_beats": 93, "duration_beats": 5 }, { "voice": 1, "bar": 20, "offset_beats": 98, "duration_beats": 5 }, { "voice": 1, "bar": 21, "offset_beats": 103, "duration_beats": 5 }, { "voice": 1, "bar": 22, "offset_beats": 108, "duration_beats": 5 }, { "voice": 1, "bar": 23, "offset_beats": 113, "duration_beats": 5 }, { "voice": 1, "bar": 24, "offset_beats": 118, "duration_beats": 5 }, { "voice": 1, "bar": 25, "offset_beats": 123, "duration_beats": 5 }, { "voice": 1, "bar": 26, "offset_beats": 128, "duration_beats": 5 }, { "voice": 1, "bar": 27, "offset_beats": 133, "duration_beats": 5 }, { "voice": 1, "bar": 28, "offset_beats": 138, "duration_beats": 5 }, { "voice": 1, "bar": 29, "offset_beats": 143, "duration_beats": 5 }, { "voice": 1, "bar": 30, "offset_beats": 148, "duration_beats": 5 }, { "voice": 1, "bar": 31, "offset_beats": 153, "duration_beats": 5 }, { "voice": 1, "bar": 32, "offset_beats": 158, "duration_beats": 5 }, { "voice": 1, "bar": 33, "offset_beats": 163, "duration_beats": 5 }, { "voice": 2, "bar": 8, "offset_beats": 32, "duration_beats": 4.75 }, { "voice": 2, "bar": 9, "offset_beats": 36.75, "duration_beats": 4.75 }, { "voice": 2, "bar": 10, "offset_beats": 41.5, "duration_beats": 4.75 }, { "voice": 2, "bar": 11, "offset_beats": 46.25, "duration_beats": 4.75 }, { "voice": 2, "bar": 12, "offset_beats": 51, "duration_beats": 4.75 }, { "voice": 2, "bar": 13, "offset_beats": 55.75, "duration_beats": 4.75 }, { "voice": 2, "bar": 14, "offset_beats": 60.5, "duration_beats": 4.75 }, { "voice": 2, "bar": 15, "offset_beats": 65.25, "duration_beats": 4.75 }, { "voice": 2, "bar": 16, "offset_beats": 70, "duration_beats": 4.75 }, { "voice": 2, "bar": 17, "offset_beats": 74.75, "duration_beats": 4.75 }, { "voice": 2, "bar": 18, "offset_beats": 79.5, "duration_beats": 4.75 }, { "voice": 2, "bar": 19, "offset_beats": 84.25, "duration_beats": 4.75 }, { "voice": 2, "bar": 20, "offset_beats": 89, "duration_beats": 4.75 }, { "voice": 2, "bar": 21, "offset_beats": 93.75, "duration_beats": 4.75 }, { "voice": 2, "bar": 22, "offset_beats": 98.5, "duration_beats": 4.75 }, { "voice": 2, "bar": 23, "offset_beats": 103.25, "duration_beats": 4.75 }, { "voice": 2, "bar": 24, "offset_beats": 108, "duration_beats": 4.75 }, { "voice": 2, "bar": 25, "offset_beats": 112.75, "duration_beats": 4.75 }, { "voice": 2, "bar": 26, "offset_beats": 117.5, "duration_beats": 4.75 }, { "voice": 2, "bar": 27, "offset_beats": 122.25, "duration_beats": 4.75 }, { "voice": 2, "bar": 28, "offset_beats": 127, "duration_beats": 4.75 }, { "voice": 2, "bar": 29, "offset_beats": 131.75, "duration_beats": 4.75 }, { "voice": 2, "bar": 30, "offset_beats": 136.5, "duration_beats": 4.75 }, { "voice": 2, "bar": 31, "offset_beats": 141.25, "duration_beats": 4.75 }, { "voice": 2, "bar": 32, "offset_beats": 146, "duration_beats": 4.75 }, { "voice": 2, "bar": 33, "offset_beats": 150.75, "duration_beats": 4.75 }, { "voice": 3, "bar": 8, "offset_beats": 32, "duration_beats": 4.5 }, { "voice": 3, "bar": 9, "offset_beats": 36.5, "duration_beats": 4.75 }, { "voice": 3, "bar": 10, "offset_beats": 41.25, "duration_beats": 5 }, { "voice": 3, "bar": 11, "offset_beats": 46.25, "duration_beats": 5 }, { "voice": 3, "bar": 12, "offset_beats": 51.25, "duration_beats": 5 }, { "voice": 3, "bar": 13, "offset_beats": 56.25, "duration_beats": 5 }, { "voice": 3, "bar": 14, "offset_beats": 61.25, "duration_beats": 5 }, { "voice": 3, "bar": 15, "offset_beats": 66.25, "duration_beats": 5 }, { "voice": 3, "bar": 16, "offset_beats": 71.25, "duration_beats": 5 }, { "voice": 3, "bar": 17, "offset_beats": 76.25, "duration_beats": 5 }, { "voice": 3, "bar": 18, "offset_beats": 81.25, "duration_beats": 5 }, { "voice": 3, "bar": 19, "offset_beats": 86.25, "duration_beats": 5 }, { "voice": 3, "bar": 20, "offset_beats": 91.25, "duration_beats": 5 }, { "voice": 3, "bar": 21, "offset_beats": 96.25, "duration_beats": 5 }, { "voice": 3, "bar": 22, "offset_beats": 101.25, "duration_beats": 5 }, { "voice": 3, "bar": 23, "offset_beats": 106.25, "duration_beats": 5 }, { "voice": 3, "bar": 24, "offset_beats": 111.25, "duration_beats": 5 }, { "voice": 3, "bar": 25, "offset_beats": 116.25, "duration_beats": 5 }, { "voice": 3, "bar": 26, "offset_beats": 121.25, "duration_beats": 5 }, { "voice": 3, "bar": 27, "offset_beats": 126.25, "duration_beats": 5 }, { "voice": 3, "bar": 28, "offset_beats": 131.25, "duration_beats": 5 }, { "voice": 3, "bar": 29, "offset_beats": 136.25, "duration_beats": 5 }, { "voice": 3, "bar": 30, "offset_beats": 141.25, "duration_beats": 5 }, { "voice": 3, "bar": 31, "offset_beats": 146.25, "duration_beats": 5 }, { "voice": 3, "bar": 32, "offset_beats": 151.25, "duration_beats": 5 }, { "voice": 3, "bar": 33, "offset_beats": 156.25, "duration_beats": 5 }, { "voice": 4, "bar": 8, "offset_beats": 32, "duration_beats": 4.5 }, { "voice": 4, "bar": 9, "offset_beats": 36.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 10, "offset_beats": 41, "duration_beats": 4.5 }, { "voice": 4, "bar": 11, "offset_beats": 45.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 12, "offset_beats": 50, "duration_beats": 4.5 }, { "voice": 4, "bar": 13, "offset_beats": 54.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 14, "offset_beats": 59, "duration_beats": 4.5 }, { "voice": 4, "bar": 15, "offset_beats": 63.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 16, "offset_beats": 68, "duration_beats": 4.5 }, { "voice": 4, "bar": 17, "offset_beats": 72.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 18, "offset_beats": 77, "duration_beats": 4.5 }, { "voice": 4, "bar": 19, "offset_beats": 81.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 20, "offset_beats": 86, "duration_beats": 4.5 }, { "voice": 4, "bar": 21, "offset_beats": 90.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 22, "offset_beats": 95, "duration_beats": 4.5 }, { "voice": 4, "bar": 23, "offset_beats": 99.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 24, "offset_beats": 104, "duration_beats": 4.5 }, { "voice": 4, "bar": 25, "offset_beats": 108.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 26, "offset_beats": 113, "duration_beats": 4.5 }, { "voice": 4, "bar": 27, "offset_beats": 117.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 28, "offset_beats": 122, "duration_beats": 4.5 }, { "voice": 4, "bar": 29, "offset_beats": 126.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 30, "offset_beats": 131, "duration_beats": 4.5 }, { "voice": 4, "bar": 31, "offset_beats": 135.5, "duration_beats": 4.5 }, { "voice": 4, "bar": 32, "offset_beats": 140, "duration_beats": 4.5 }, { "voice": 4, "bar": 33, "offset_beats": 144.5, "duration_beats": 4.25 }, { "voice": 5, "bar": 8, "offset_beats": 32, "duration_beats": 4.75 }, { "voice": 5, "bar": 9, "offset_beats": 36.75, "duration_beats": 4.75 }, { "voice": 5, "bar": 10, "offset_beats": 41.5, "duration_beats": 4.75 }, { "voice": 5, "bar": 11, "offset_beats": 46.25, "duration_beats": 4.75 }, { "voice": 5, "bar": 12, "offset_beats": 51, "duration_beats": 4.5 }, { "voice": 5, "bar": 13, "offset_beats": 55.5, "duration_beats": 4.5 }, { "voice": 5, "bar": 14, "offset_beats": 60, "duration_beats": 4.75 }, { "voice": 5, "bar": 15, "offset_beats": 64.75, "duration_beats": 4.75 }, { "voice": 5, "bar": 16, "offset_beats": 69.5, "duration_beats": 4.5 }, { "voice": 5, "bar": 17, "offset_beats": 74, "duration_beats": 4.5 }, { "voice": 5, "bar": 18, "offset_beats": 78.5, "duration_beats": 4.5 }, { "voice": 5, "bar": 19, "offset_beats": 83, "duration_beats": 4.5 }, { "voice": 5, "bar": 20, "offset_beats": 87.5, "duration_beats": 4.75 }, { "voice": 5, "bar": 21, "offset_beats": 92.25, "duration_beats": 4.75 }, { "voice": 5, "bar": 22, "offset_beats": 97, "duration_beats": 4.75 }, { "voice": 5, "bar": 23, "offset_beats": 101.75, "duration_beats": 4.75 }, { "voice": 5, "bar": 24, "offset_beats": 106.5, "duration_beats": 4.5 }, { "voice": 5, "bar": 25, "offset_beats": 111, "duration_beats": 4.5 }, { "voice": 5, "bar": 26, "offset_beats": 115.5, "duration_beats": 4.75 }, { "voice": 5, "bar": 27, "offset_beats": 120.25, "duration_beats": 4.75 }, { "voice": 5, "bar": 28, "offset_beats": 125, "duration_beats": 4.5 }, { "voice": 5, "bar": 29, "offset_beats": 129.5, "duration_beats": 4.5 }, { "voice": 5, "bar": 30, "offset_beats": 134, "duration_beats": 4.5 }, { "voice": 5, "bar": 31, "offset_beats": 138.5, "duration_beats": 4.5 }, { "voice": 5, "bar": 32, "offset_beats": 143, "duration_beats": 4.75 }, { "voice": 5, "bar": 33, "offset_beats": 147.75, "duration_beats": 4 } ] }, "listening_note": "Native output: 32.0 / 32 bars. Reached the 1,024-patch context limit in this run. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "1a846fc378a807d3abc663ada6a8481b256d0878860c29f53e3e973528fef5a8", "mp3": "33cc2efaeb2fadb562380d425ba8b9ab5e5bba13242347f44eb0469a2de7697f", "wav": "479d46fe86088c10970e32ce20195dc2d38c918d48ec328a1343f0825b8ef9ff" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-3_notagen.wav", "source_wav_sha256": "479d46fe86088c10970e32ce20195dc2d38c918d48ec328a1343f0825b8ef9ff", "source_mp3_sha256": "33cc2efaeb2fadb562380d425ba8b9ab5e5bba13242347f44eb0469a2de7697f", "source_audio_duration": 77.740408, "last_note_end_seconds": 76.19040179962708, "trim_end_seconds": 77.69040179962708, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-4", "window": "Track01657.npz:25", "model": "notagen", "name": "NotaGen RL3", "midi": "assets/song-4_notagen.mid", "mp3": "assets/song-4_notagen.mp3", "wav": "assets/song-4_notagen.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/notagen/song-4/result.json", "source_midi_sha256": "a605630867ac1c255dbf25b01d25052bb63a90c007396abf247d7af401c224c9", "seed": 20260924, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 31.4375, "prefix_seconds": 16, "duration": 80, "audio_duration": 80.404898, "notes": 937, "peak": 0.22759996354579926, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_patches": 157, "total_patches": 632, "decoded_bars": 40, "stop_reason": "requested_boundary", "reached_requested_boundary": true }, "metrics": { "rbde": 3.696826793712362, "rhythm_jsd": 0.2624430667133125, "chroma_jsd": 0.4131690231765833, "role_structure_error": 0.4422082721962045, "tsse": 0.14177475907382214 }, "diagnostics": { "notes": 937, "sounding_bars": 31.4375, "empty_bar_rate": 0, "role_assignments": [ { "program": 0, "drum": false, "notes": 64, "role": "melody" }, { "program": 32, "drum": false, "notes": 68, "role": "bass" }, { "program": 0, "drum": false, "notes": 326, "role": "chords" }, { "program": 0, "drum": true, "notes": 289, "role": "drums" }, { "program": 24, "drum": false, "notes": 190, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 40, 40, 40, 40, 40 ], "violation_count": 154, "violations": [ { "voice": 1, "bar": 8, "offset_beats": 32, "duration_beats": 4.25 }, { "voice": 1, "bar": 9, "offset_beats": 36.25, "duration_beats": 3.5 }, { "voice": 1, "bar": 10, "offset_beats": 39.75, "duration_beats": 4 }, { "voice": 1, "bar": 11, "offset_beats": 43.75, "duration_beats": 4 }, { "voice": 1, "bar": 12, "offset_beats": 47.75, "duration_beats": 4 }, { "voice": 1, "bar": 13, "offset_beats": 51.75, "duration_beats": 3.75 }, { "voice": 1, "bar": 14, "offset_beats": 55.5, "duration_beats": 4 }, { "voice": 1, "bar": 15, "offset_beats": 59.5, "duration_beats": 4 }, { "voice": 1, "bar": 16, "offset_beats": 63.5, "duration_beats": 3.75 }, { "voice": 1, "bar": 17, "offset_beats": 67.25, "duration_beats": 3.75 }, { "voice": 1, "bar": 18, "offset_beats": 71, "duration_beats": 3.75 }, { "voice": 1, "bar": 19, "offset_beats": 74.75, "duration_beats": 3.75 }, { "voice": 1, "bar": 20, "offset_beats": 78.5, "duration_beats": 3.75 }, { "voice": 1, "bar": 21, "offset_beats": 82.25, "duration_beats": 3.75 }, { "voice": 1, "bar": 22, "offset_beats": 86, "duration_beats": 4 }, { "voice": 1, "bar": 23, "offset_beats": 90, "duration_beats": 4 }, { "voice": 1, "bar": 24, "offset_beats": 94, "duration_beats": 4 }, { "voice": 1, "bar": 25, "offset_beats": 98, "duration_beats": 4 }, { "voice": 1, "bar": 26, "offset_beats": 102, "duration_beats": 4 }, { "voice": 1, "bar": 27, "offset_beats": 106, "duration_beats": 4 }, { "voice": 1, "bar": 28, "offset_beats": 110, "duration_beats": 4 }, { "voice": 1, "bar": 29, "offset_beats": 114, "duration_beats": 4 }, { "voice": 1, "bar": 30, "offset_beats": 118, "duration_beats": 4 }, { "voice": 1, "bar": 31, "offset_beats": 122, "duration_beats": 4 }, { "voice": 1, "bar": 32, "offset_beats": 126, "duration_beats": 4 }, { "voice": 1, "bar": 33, "offset_beats": 130, "duration_beats": 4 }, { "voice": 1, "bar": 34, "offset_beats": 134, "duration_beats": 4 }, { "voice": 1, "bar": 35, "offset_beats": 138, "duration_beats": 4 }, { "voice": 1, "bar": 36, "offset_beats": 142, "duration_beats": 4 }, { "voice": 1, "bar": 37, "offset_beats": 146, "duration_beats": 4 }, { "voice": 1, "bar": 38, "offset_beats": 150, "duration_beats": 4 }, { "voice": 1, "bar": 39, "offset_beats": 154, "duration_beats": 4 }, { "voice": 2, "bar": 9, "offset_beats": 35.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 10, "offset_beats": 39.25, "duration_beats": 3.5 }, { "voice": 2, "bar": 11, "offset_beats": 42.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 12, "offset_beats": 46.5, "duration_beats": 4 }, { "voice": 2, "bar": 13, "offset_beats": 50.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 14, "offset_beats": 54.25, "duration_beats": 4 }, { "voice": 2, "bar": 15, "offset_beats": 58.25, "duration_beats": 3.75 }, { "voice": 2, "bar": 16, "offset_beats": 62, "duration_beats": 3.75 }, { "voice": 2, "bar": 17, "offset_beats": 65.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 18, "offset_beats": 69.5, "duration_beats": 3.75 }, { "voice": 2, "bar": 19, "offset_beats": 73.25, "duration_beats": 3.75 }, { "voice": 2, "bar": 20, "offset_beats": 77, "duration_beats": 3.75 }, { "voice": 2, "bar": 21, "offset_beats": 80.75, "duration_beats": 3.75 }, { "voice": 2, "bar": 22, "offset_beats": 84.5, "duration_beats": 4 }, { "voice": 2, "bar": 23, "offset_beats": 88.5, "duration_beats": 4 }, { "voice": 2, "bar": 24, "offset_beats": 92.5, "duration_beats": 4 }, { "voice": 2, "bar": 25, "offset_beats": 96.5, "duration_beats": 4 }, { "voice": 2, "bar": 26, "offset_beats": 100.5, "duration_beats": 4 }, { "voice": 2, "bar": 27, "offset_beats": 104.5, "duration_beats": 4 }, { "voice": 2, "bar": 28, "offset_beats": 108.5, "duration_beats": 4 }, { "voice": 2, "bar": 29, "offset_beats": 112.5, "duration_beats": 4 }, { "voice": 2, "bar": 30, "offset_beats": 116.5, "duration_beats": 4 }, { "voice": 2, "bar": 31, "offset_beats": 120.5, "duration_beats": 4 }, { "voice": 2, "bar": 32, "offset_beats": 124.5, "duration_beats": 4 }, { "voice": 2, "bar": 33, "offset_beats": 128.5, "duration_beats": 4 }, { "voice": 2, "bar": 34, "offset_beats": 132.5, "duration_beats": 4 }, { "voice": 2, "bar": 35, "offset_beats": 136.5, "duration_beats": 4 }, { "voice": 2, "bar": 36, "offset_beats": 140.5, "duration_beats": 4 }, { "voice": 2, "bar": 37, "offset_beats": 144.5, "duration_beats": 4 }, { "voice": 2, "bar": 38, "offset_beats": 148.5, "duration_beats": 4 }, { "voice": 2, "bar": 39, "offset_beats": 152.5, "duration_beats": 4 }, { "voice": 3, "bar": 10, "offset_beats": 39.75, "duration_beats": 3.5 }, { "voice": 3, "bar": 11, "offset_beats": 43.25, "duration_beats": 3.75 }, { "voice": 3, "bar": 12, "offset_beats": 47, "duration_beats": 3.75 }, { "voice": 3, "bar": 13, "offset_beats": 50.75, "duration_beats": 3.75 }, { "voice": 3, "bar": 14, "offset_beats": 54.5, "duration_beats": 3.75 }, { "voice": 3, "bar": 15, "offset_beats": 58.25, "duration_beats": 3.75 }, { "voice": 3, "bar": 16, "offset_beats": 62, "duration_beats": 3.75 }, { "voice": 3, "bar": 17, "offset_beats": 65.75, "duration_beats": 3.75 }, { "voice": 3, "bar": 18, "offset_beats": 69.5, "duration_beats": 3.75 }, { "voice": 3, "bar": 19, "offset_beats": 73.25, "duration_beats": 3.75 }, { "voice": 3, "bar": 20, "offset_beats": 77, "duration_beats": 3.75 }, { "voice": 3, "bar": 21, "offset_beats": 80.75, "duration_beats": 3.75 }, { "voice": 3, "bar": 22, "offset_beats": 84.5, "duration_beats": 4 }, { "voice": 3, "bar": 23, "offset_beats": 88.5, "duration_beats": 4 }, { "voice": 3, "bar": 24, "offset_beats": 92.5, "duration_beats": 4 }, { "voice": 3, "bar": 25, "offset_beats": 96.5, "duration_beats": 4 }, { "voice": 3, "bar": 26, "offset_beats": 100.5, "duration_beats": 4 }, { "voice": 3, "bar": 27, "offset_beats": 104.5, "duration_beats": 4 }, { "voice": 3, "bar": 28, "offset_beats": 108.5, "duration_beats": 4 }, { "voice": 3, "bar": 29, "offset_beats": 112.5, "duration_beats": 4 }, { "voice": 3, "bar": 30, "offset_beats": 116.5, "duration_beats": 4 }, { "voice": 3, "bar": 31, "offset_beats": 120.5, "duration_beats": 4 }, { "voice": 3, "bar": 32, "offset_beats": 124.5, "duration_beats": 4 }, { "voice": 3, "bar": 33, "offset_beats": 128.5, "duration_beats": 4 }, { "voice": 3, "bar": 34, "offset_beats": 132.5, "duration_beats": 4 }, { "voice": 3, "bar": 35, "offset_beats": 136.5, "duration_beats": 4 }, { "voice": 3, "bar": 36, "offset_beats": 140.5, "duration_beats": 4 }, { "voice": 3, "bar": 37, "offset_beats": 144.5, "duration_beats": 4 }, { "voice": 3, "bar": 38, "offset_beats": 148.5, "duration_beats": 4 }, { "voice": 3, "bar": 39, "offset_beats": 152.5, "duration_beats": 4 }, { "voice": 4, "bar": 9, "offset_beats": 35.75, "duration_beats": 3.75 }, { "voice": 4, "bar": 10, "offset_beats": 39.5, "duration_beats": 3.75 }, { "voice": 4, "bar": 11, "offset_beats": 43.25, "duration_beats": 3.75 }, { "voice": 4, "bar": 12, "offset_beats": 47, "duration_beats": 3.5 }, { "voice": 4, "bar": 13, "offset_beats": 50.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 14, "offset_beats": 54, "duration_beats": 3.5 }, { "voice": 4, "bar": 15, "offset_beats": 57.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 16, "offset_beats": 61, "duration_beats": 3.5 }, { "voice": 4, "bar": 17, "offset_beats": 64.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 18, "offset_beats": 68, "duration_beats": 3.5 }, { "voice": 4, "bar": 19, "offset_beats": 71.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 20, "offset_beats": 75, "duration_beats": 3.5 }, { "voice": 4, "bar": 21, "offset_beats": 78.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 22, "offset_beats": 82, "duration_beats": 3.5 }, { "voice": 4, "bar": 23, "offset_beats": 85.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 24, "offset_beats": 89, "duration_beats": 3.5 }, { "voice": 4, "bar": 25, "offset_beats": 92.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 26, "offset_beats": 96, "duration_beats": 3.5 }, { "voice": 4, "bar": 27, "offset_beats": 99.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 28, "offset_beats": 103, "duration_beats": 3.5 }, { "voice": 4, "bar": 29, "offset_beats": 106.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 30, "offset_beats": 110, "duration_beats": 3.5 }, { "voice": 4, "bar": 31, "offset_beats": 113.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 32, "offset_beats": 117, "duration_beats": 3.5 }, { "voice": 4, "bar": 33, "offset_beats": 120.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 34, "offset_beats": 124, "duration_beats": 3.5 }, { "voice": 4, "bar": 35, "offset_beats": 127.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 36, "offset_beats": 131, "duration_beats": 3.5 }, { "voice": 4, "bar": 37, "offset_beats": 134.5, "duration_beats": 3.5 }, { "voice": 4, "bar": 38, "offset_beats": 138, "duration_beats": 3.5 }, { "voice": 4, "bar": 39, "offset_beats": 141.5, "duration_beats": 3.5 }, { "voice": 5, "bar": 10, "offset_beats": 39.75, "duration_beats": 4 }, { "voice": 5, "bar": 11, "offset_beats": 43.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 12, "offset_beats": 47.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 13, "offset_beats": 51.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 14, "offset_beats": 55, "duration_beats": 3.75 }, { "voice": 5, "bar": 15, "offset_beats": 58.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 16, "offset_beats": 62.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 17, "offset_beats": 66.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 18, "offset_beats": 70, "duration_beats": 3.75 }, { "voice": 5, "bar": 19, "offset_beats": 73.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 20, "offset_beats": 77.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 21, "offset_beats": 81.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 22, "offset_beats": 85, "duration_beats": 3.75 }, { "voice": 5, "bar": 23, "offset_beats": 88.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 24, "offset_beats": 92.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 25, "offset_beats": 96.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 26, "offset_beats": 100, "duration_beats": 3.75 }, { "voice": 5, "bar": 27, "offset_beats": 103.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 28, "offset_beats": 107.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 29, "offset_beats": 111.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 30, "offset_beats": 115, "duration_beats": 3.75 }, { "voice": 5, "bar": 31, "offset_beats": 118.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 32, "offset_beats": 122.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 33, "offset_beats": 126.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 34, "offset_beats": 130, "duration_beats": 3.75 }, { "voice": 5, "bar": 35, "offset_beats": 133.75, "duration_beats": 3.75 }, { "voice": 5, "bar": 36, "offset_beats": 137.5, "duration_beats": 3.75 }, { "voice": 5, "bar": 37, "offset_beats": 141.25, "duration_beats": 3.75 }, { "voice": 5, "bar": 38, "offset_beats": 145, "duration_beats": 3.75 }, { "voice": 5, "bar": 39, "offset_beats": 148.75, "duration_beats": 3.75 } ] }, "listening_note": "Native output: 31.4 / 32 bars. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "f4d0c284674a6a45d23ce71eaf44772a023eaf545fbccdc2d37f55dd72b00f6f", "mp3": "f48f4e965e8044574f249805dcccd415c5c42e74ffbd2627b2710dff815cc28e", "wav": "292d4598caababca630ad83d46b5b4b05783febed635fc1bed952ec9c873d7b4" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-4_notagen.wav", "source_wav_sha256": "292d4598caababca630ad83d46b5b4b05783febed635fc1bed952ec9c873d7b4", "source_mp3_sha256": "d8cfa81b9499cb053d3009945ffee78da5a64cce6888a31cf2481f7253295812", "source_audio_duration": 81.528163, "last_note_end_seconds": 78.875, "trim_end_seconds": 80.375, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-5", "window": "Track01527.npz:112", "model": "notagen", "name": "NotaGen RL3", "midi": "assets/song-5_notagen.mid", "mp3": "assets/song-5_notagen.mp3", "wav": "assets/song-5_notagen.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/notagen/song-5/result.json", "source_midi_sha256": "19aa9f5e91f74cf30701474ebec3f961dec7ae50e7751b3aa5bb5bc8d883291e", "seed": 20260925, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 31.375, "prefix_seconds": 11.99923150692855, "duration": 59.996157534642755, "audio_duration": 60.604082, "notes": 1709, "peak": 0.36702871322631836, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 11.899229024943311, "generation": { "prefix_patches": 172, "total_patches": 694, "decoded_bars": 40, "stop_reason": "requested_boundary", "reached_requested_boundary": true }, "metrics": { "rbde": 0.1447515501367929, "rhythm_jsd": 0.11882209413181326, "chroma_jsd": 0.36499610078440814, "role_structure_error": 0.1235969971765763, "tsse": 0.16734146330036456 }, "diagnostics": { "notes": 1709, "sounding_bars": 31.375, "empty_bar_rate": 0, "role_assignments": [ { "program": 0, "drum": false, "notes": 70, "role": "melody" }, { "program": 32, "drum": false, "notes": 129, "role": "bass" }, { "program": 0, "drum": false, "notes": 332, "role": "chords" }, { "program": 0, "drum": true, "notes": 283, "role": "drums" }, { "program": 24, "drum": false, "notes": 895, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": { "aligned_4_4": false, "measure_counts": [ 40, 40, 40, 40, 40 ], "violation_count": 62, "violations": [ { "voice": 3, "bar": 9, "offset_beats": 35.75, "duration_beats": 3.75 }, { "voice": 3, "bar": 10, "offset_beats": 39.5, "duration_beats": 4 }, { "voice": 3, "bar": 11, "offset_beats": 43.5, "duration_beats": 4 }, { "voice": 3, "bar": 12, "offset_beats": 47.5, "duration_beats": 4 }, { "voice": 3, "bar": 13, "offset_beats": 51.5, "duration_beats": 4 }, { "voice": 3, "bar": 14, "offset_beats": 55.5, "duration_beats": 4 }, { "voice": 3, "bar": 15, "offset_beats": 59.5, "duration_beats": 4 }, { "voice": 3, "bar": 16, "offset_beats": 63.5, "duration_beats": 4 }, { "voice": 3, "bar": 17, "offset_beats": 67.5, "duration_beats": 4 }, { "voice": 3, "bar": 18, "offset_beats": 71.5, "duration_beats": 4 }, { "voice": 3, "bar": 19, "offset_beats": 75.5, "duration_beats": 4 }, { "voice": 3, "bar": 20, "offset_beats": 79.5, "duration_beats": 4 }, { "voice": 3, "bar": 21, "offset_beats": 83.5, "duration_beats": 4 }, { "voice": 3, "bar": 22, "offset_beats": 87.5, "duration_beats": 4 }, { "voice": 3, "bar": 23, "offset_beats": 91.5, "duration_beats": 4 }, { "voice": 3, "bar": 24, "offset_beats": 95.5, "duration_beats": 4 }, { "voice": 3, "bar": 25, "offset_beats": 99.5, "duration_beats": 4 }, { "voice": 3, "bar": 26, "offset_beats": 103.5, "duration_beats": 4 }, { "voice": 3, "bar": 27, "offset_beats": 107.5, "duration_beats": 4 }, { "voice": 3, "bar": 28, "offset_beats": 111.5, "duration_beats": 4 }, { "voice": 3, "bar": 29, "offset_beats": 115.5, "duration_beats": 4 }, { "voice": 3, "bar": 30, "offset_beats": 119.5, "duration_beats": 4 }, { "voice": 3, "bar": 31, "offset_beats": 123.5, "duration_beats": 4 }, { "voice": 3, "bar": 32, "offset_beats": 127.5, "duration_beats": 4 }, { "voice": 3, "bar": 33, "offset_beats": 131.5, "duration_beats": 4 }, { "voice": 3, "bar": 34, "offset_beats": 135.5, "duration_beats": 4 }, { "voice": 3, "bar": 35, "offset_beats": 139.5, "duration_beats": 4 }, { "voice": 3, "bar": 36, "offset_beats": 143.5, "duration_beats": 4 }, { "voice": 3, "bar": 37, "offset_beats": 147.5, "duration_beats": 4 }, { "voice": 3, "bar": 38, "offset_beats": 151.5, "duration_beats": 4 }, { "voice": 3, "bar": 39, "offset_beats": 155.5, "duration_beats": 4 }, { "voice": 4, "bar": 9, "offset_beats": 36, "duration_beats": 4.5 }, { "voice": 4, "bar": 10, "offset_beats": 40.5, "duration_beats": 4 }, { "voice": 4, "bar": 11, "offset_beats": 44.5, "duration_beats": 4 }, { "voice": 4, "bar": 12, "offset_beats": 48.5, "duration_beats": 4 }, { "voice": 4, "bar": 13, "offset_beats": 52.5, "duration_beats": 4 }, { "voice": 4, "bar": 14, "offset_beats": 56.5, "duration_beats": 4 }, { "voice": 4, "bar": 15, "offset_beats": 60.5, "duration_beats": 4 }, { "voice": 4, "bar": 16, "offset_beats": 64.5, "duration_beats": 4 }, { "voice": 4, "bar": 17, "offset_beats": 68.5, "duration_beats": 4 }, { "voice": 4, "bar": 18, "offset_beats": 72.5, "duration_beats": 4 }, { "voice": 4, "bar": 19, "offset_beats": 76.5, "duration_beats": 4 }, { "voice": 4, "bar": 20, "offset_beats": 80.5, "duration_beats": 4 }, { "voice": 4, "bar": 21, "offset_beats": 84.5, "duration_beats": 4 }, { "voice": 4, "bar": 22, "offset_beats": 88.5, "duration_beats": 4 }, { "voice": 4, "bar": 23, "offset_beats": 92.5, "duration_beats": 4 }, { "voice": 4, "bar": 24, "offset_beats": 96.5, "duration_beats": 4 }, { "voice": 4, "bar": 25, "offset_beats": 100.5, "duration_beats": 4 }, { "voice": 4, "bar": 26, "offset_beats": 104.5, "duration_beats": 4 }, { "voice": 4, "bar": 27, "offset_beats": 108.5, "duration_beats": 4 }, { "voice": 4, "bar": 28, "offset_beats": 112.5, "duration_beats": 4 }, { "voice": 4, "bar": 29, "offset_beats": 116.5, "duration_beats": 4 }, { "voice": 4, "bar": 30, "offset_beats": 120.5, "duration_beats": 4 }, { "voice": 4, "bar": 31, "offset_beats": 124.5, "duration_beats": 4 }, { "voice": 4, "bar": 32, "offset_beats": 128.5, "duration_beats": 4 }, { "voice": 4, "bar": 33, "offset_beats": 132.5, "duration_beats": 4 }, { "voice": 4, "bar": 34, "offset_beats": 136.5, "duration_beats": 4 }, { "voice": 4, "bar": 35, "offset_beats": 140.5, "duration_beats": 4 }, { "voice": 4, "bar": 36, "offset_beats": 144.5, "duration_beats": 4 }, { "voice": 4, "bar": 37, "offset_beats": 148.5, "duration_beats": 4 }, { "voice": 4, "bar": 38, "offset_beats": 152.5, "duration_beats": 4 }, { "voice": 4, "bar": 39, "offset_beats": 156.5, "duration_beats": 4 } ] }, "listening_note": "Native output: 31.4 / 32 bars. Irregular ABC bar lengths are preserved.", "hashes": { "mid": "5eac02a9286cf422f084d152441220d8a9505861e40e8fe20b06e65bc8597330", "mp3": "da8282016f239f7bd90df7beafb611fa00bc25d1a89d41633700668955a65650", "wav": "8632f520490cae084238cbad4196e4965ef1587a6a1df8914a1156c0ee6289dc" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-5_notagen.wav", "source_wav_sha256": "8632f520490cae084238cbad4196e4965ef1587a6a1df8914a1156c0ee6289dc", "source_mp3_sha256": "5416dd17df7f31bc8ff130f1661b273a3469e5e209ae5ba30a0c37d8487e0103", "source_audio_duration": 61.54449, "last_note_end_seconds": 59.05871757316396, "trim_end_seconds": 60.55871757316396, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-1", "window": "Track01646.npz:73", "model": "amadeus", "name": "Amadeus-S", "midi": "assets/song-1_amadeus.mid", "mp3": "assets/song-1_amadeus.mp3", "wav": "assets/song-1_amadeus.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/amadeus/song-1/result.json", "source_midi_sha256": "eb11a5518bbd2a350a0b2cc298de97d0f063a08eab001b8455999b415509e762", "seed": 20260921, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 32, "prefix_seconds": 16, "duration": 80, "audio_duration": 81.528163, "notes": 1790, "peak": 0.2013261318206787, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 429, "total_tokens": 2220, "total_bar_tokens": 41, "reached_requested_boundary": true, "conditioning": "NB music prefix + observed text" }, "metrics": { "rbde": 0.3024421044751384, "rhythm_jsd": 0.02090826162474919, "chroma_jsd": 0.3287673683223908, "role_structure_error": 0.16143402959766606, "tsse": 0.08189820403411065 }, "diagnostics": { "notes": 1790, "sounding_bars": 32, "empty_bar_rate": 0, "role_assignments": [ { "program": 0, "drum": false, "notes": 926, "role": "chords" }, { "program": 32, "drum": false, "notes": 125, "role": "bass" }, { "program": 114, "drum": true, "notes": 478, "role": "drums" }, { "program": 24, "drum": false, "notes": 261, "role": "accompaniment" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 32.0 / 32 bars.", "hashes": { "mid": "c809243f91cb1586536c473a65e428e14540f71a2753e09f5648e283d2f7e0eb", "mp3": "6737bdd8a7a67a7a91c5fdf9ee21e1ba91886a10df9188cad373845607b40d32", "wav": "b77e0c4939dbc6d4b1a1f4230074d806810d34be1f63fdfa9ade052e91c9274e" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-1_amadeus.wav", "source_wav_sha256": "b77e0c4939dbc6d4b1a1f4230074d806810d34be1f63fdfa9ade052e91c9274e", "source_mp3_sha256": "6737bdd8a7a67a7a91c5fdf9ee21e1ba91886a10df9188cad373845607b40d32", "source_audio_duration": 81.528163, "last_note_end_seconds": 80, "trim_end_seconds": 81.5, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-2", "window": "Track01631.npz:32", "model": "amadeus", "name": "Amadeus-S", "midi": "assets/song-2_amadeus.mid", "mp3": "assets/song-2_amadeus.mp3", "wav": "assets/song-2_amadeus.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/amadeus/song-2/result.json", "source_midi_sha256": "17c60f7e20427443a4bf2fe04f17c7b027d0c14170c209697048d42e7b82d4a3", "seed": 20260922, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 26, "prefix_seconds": 18.916159559985374, "duration": 94.58079779992687, "audio_duration": 81.92, "notes": 2607, "peak": 0.3838651180267334, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 18.816145124716552, "generation": { "prefix_tokens": 463, "total_tokens": 3072, "total_bar_tokens": 34, "reached_requested_boundary": false, "conditioning": "NB music prefix + observed text" }, "metrics": { "rbde": 3.5848493773866053, "rhythm_jsd": 0.20633632084463885, "chroma_jsd": 0.4661379438827892, "role_structure_error": 0.47574090155183796, "tsse": 0.5610993008572618 }, "diagnostics": { "notes": 2607, "sounding_bars": 26, "empty_bar_rate": 0.1875, "role_assignments": [ { "program": 0, "drum": false, "notes": 748, "role": "chords" }, { "program": 24, "drum": false, "notes": 796, "role": "chords" }, { "program": 32, "drum": false, "notes": 191, "role": "bass" }, { "program": 114, "drum": true, "notes": 872, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 26.0 / 32 bars. Reached the 3,072-token context limit in this run.", "hashes": { "mid": "df59e6c2f75d6cfdbb5297968e0cad43c40f320c2b1472ca6c762a263dbf56f7", "mp3": "2cd3f0c0cfaab4d6c76193dff685f6f6b11e5f92a94eb01647c1359b23a6bb42", "wav": "849bae82fc7dbead6d1e0594edc712bae00e0b6c67de30f04a2a4aa246637fa3" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-2_amadeus.wav", "source_wav_sha256": "849bae82fc7dbead6d1e0594edc712bae00e0b6c67de30f04a2a4aa246637fa3", "source_mp3_sha256": "9fcac4765e107f0c47774850e724ecb7e23b3c5ad9b5f20a31cacb06dfff937d", "source_audio_duration": 96.130612, "last_note_end_seconds": 80.39367812993784, "trim_end_seconds": 81.89367812993784, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-3", "window": "Track01672.npz:16", "model": "amadeus", "name": "Amadeus-S", "midi": "assets/song-3_amadeus.mid", "mp3": "assets/song-3_amadeus.mp3", "wav": "assets/song-3_amadeus.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/amadeus/song-3/result.json", "source_midi_sha256": "1b93dc4e5398bfddf289c0a44d4fcbd41817455c4bc0baa92698d4015640095d", "seed": 20260923, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 27.375, "prefix_seconds": 15.238080359925418, "duration": 76.1904017996271, "audio_duration": 68.91102, "notes": 2660, "peak": 0.49114295840263367, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.138072562358277, "generation": { "prefix_tokens": 411, "total_tokens": 3072, "total_bar_tokens": 36, "reached_requested_boundary": false, "conditioning": "NB music prefix + observed text" }, "metrics": { "rbde": 3.7186867059515745, "rhythm_jsd": 0.25200160382659925, "chroma_jsd": 0.4568641523276734, "role_structure_error": 0.47866653167796236, "tsse": 0.4774152389257028 }, "diagnostics": { "notes": 2660, "sounding_bars": 27.375, "empty_bar_rate": 0.125, "role_assignments": [ { "program": 0, "drum": false, "notes": 651, "role": "chords" }, { "program": 24, "drum": false, "notes": 1161, "role": "chords" }, { "program": 32, "drum": false, "notes": 153, "role": "bass" }, { "program": 114, "drum": true, "notes": 695, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 27.4 / 32 bars. Reached the 3,072-token context limit in this run.", "hashes": { "mid": "3ed7b8ef6b3eee9ff2705380099e5bbb4bf4b8610c80303936f70e8cb6177376", "mp3": "1dd67a8b0746509aeb717a1e2e5634f79517475da98a9dcb06644d665bafa4ae", "wav": "6448ca500bd11858ea50d4baafacb4d11a49446c971bb85b9e4e0fe8519ab380" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-3_amadeus.wav", "source_wav_sha256": "6448ca500bd11858ea50d4baafacb4d11a49446c971bb85b9e4e0fe8519ab380", "source_mp3_sha256": "5e8ce06bee20217f31a20ebc0a49ec3b6e168712fb21ef9ce9709b3c8c3edd00", "source_audio_duration": 77.740408, "last_note_end_seconds": 67.3808865915452, "trim_end_seconds": 68.8808865915452, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-4", "window": "Track01657.npz:25", "model": "amadeus", "name": "Amadeus-S", "midi": "assets/song-4_amadeus.mid", "mp3": "assets/song-4_amadeus.mp3", "wav": "assets/song-4_amadeus.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/amadeus/song-4/result.json", "source_midi_sha256": "c99c85458d8e983973895e70f43f20ac663370aed7a0963062d4fc31d882f52c", "seed": 20260924, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 32, "prefix_seconds": 16, "duration": 80, "audio_duration": 81.528163, "notes": 1118, "peak": 0.22759996354579926, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 210, "total_tokens": 1329, "total_bar_tokens": 41, "reached_requested_boundary": true, "conditioning": "NB music prefix + observed text" }, "metrics": { "rbde": 7.186425899933066, "rhythm_jsd": 0.359855751182458, "chroma_jsd": 0.2655278431273009, "role_structure_error": 0.5819015146646538, "tsse": 0.08146766535316555 }, "diagnostics": { "notes": 1118, "sounding_bars": 32, "empty_bar_rate": 0, "role_assignments": [ { "program": 0, "drum": false, "notes": 439, "role": "chords" }, { "program": 24, "drum": false, "notes": 315, "role": "chords" }, { "program": 32, "drum": false, "notes": 104, "role": "bass" }, { "program": 114, "drum": true, "notes": 260, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 32.0 / 32 bars.", "hashes": { "mid": "23bd54ab5da3acde81da202cfe41e6abf1c8f1424fd4e19ef3b5c6d0bd237df8", "mp3": "faab0c71d90bf4252d5d302a6677d991f758939db5a9d392e9d936658fcb83bf", "wav": "83188649c31b87b8a7710dcc6bf8d489217fbf41535a88640061f7afea1077a1" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-4_amadeus.wav", "source_wav_sha256": "83188649c31b87b8a7710dcc6bf8d489217fbf41535a88640061f7afea1077a1", "source_mp3_sha256": "faab0c71d90bf4252d5d302a6677d991f758939db5a9d392e9d936658fcb83bf", "source_audio_duration": 81.528163, "last_note_end_seconds": 80, "trim_end_seconds": 81.5, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-5", "window": "Track01527.npz:112", "model": "amadeus", "name": "Amadeus-S", "midi": "assets/song-5_amadeus.mid", "mp3": "assets/song-5_amadeus.mp3", "wav": "assets/song-5_amadeus.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/amadeus/song-5/result.json", "source_midi_sha256": "7a1423310b246ce723fba91b3f8f22cfd01f8e6b12d1b1a805dc9586ff336ac9", "seed": 20260925, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 32, "prefix_seconds": 11.99923150692855, "duration": 59.996157534642755, "audio_duration": 61.54449, "notes": 1411, "peak": 0.4368843138217926, "prefix_notes_identical": true, "prefix_audio_identical": true, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "prefix_audio_checked_seconds": 11.899229024943311, "generation": { "prefix_tokens": 434, "total_tokens": 1847, "total_bar_tokens": 41, "reached_requested_boundary": true, "conditioning": "NB music prefix + observed text" }, "metrics": { "rbde": 3.5274298450952677, "rhythm_jsd": 0.20707153935892067, "chroma_jsd": 0.331127424424262, "role_structure_error": 0.46669370265540583, "tsse": 0.14575767584434868 }, "diagnostics": { "notes": 1411, "sounding_bars": 32, "empty_bar_rate": 0, "role_assignments": [ { "program": 0, "drum": false, "notes": 312, "role": "chords" }, { "program": 24, "drum": false, "notes": 713, "role": "chords" }, { "program": 32, "drum": false, "notes": 129, "role": "bass" }, { "program": 114, "drum": true, "notes": 257, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 32.0 / 32 bars.", "hashes": { "mid": "2a1e3317302b55f21cacb6edc7b8fe4dcad9f449600883944945f043c127a80f", "mp3": "ad1c6967bd95e3b8c616400a21fa9ce5d04b7dcdaf9a0a0fd9e78f0c94ec55de", "wav": "1726287afd73fa5d46db674745a589a45d5c6fdc63888146a04e4e38c782c35a" }, "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-5_amadeus.wav", "source_wav_sha256": "1726287afd73fa5d46db674745a589a45d5c6fdc63888146a04e4e38c782c35a", "source_mp3_sha256": "ad1c6967bd95e3b8c616400a21fa9ce5d04b7dcdaf9a0a0fd9e78f0c94ec55de", "source_audio_duration": 61.54449, "last_note_end_seconds": 59.996157534642755, "trim_end_seconds": 61.496157534642755, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-1", "window": "Track01646.npz:73", "model": "beat", "name": "BEAT", "midi": "assets/song-1_beat.mid", "mp3": "assets/song-1_beat.mp3", "wav": "assets/song-1_beat.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/beat/song-1/result.json", "source_midi_sha256": "ec8aa9092da6846b05f5e85ba1305180dac5c226d1a057b532acbb4c3aa9cb26", "seed": 20260921, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 5.75, "prefix_seconds": 16, "duration": 80, "audio_duration": 29.048163, "notes": 252, "peak": 0.2013261318206787, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 1226, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 14, "stopped_at_eos": false, "reached_requested_boundary": false }, "metrics": { "rbde": 1.4735908216194804, "rhythm_jsd": 0.11788313170780172, "chroma_jsd": 0.8735496164392292, "role_structure_error": 0.20882004237229385, "tsse": 0.5736025284394844 }, "diagnostics": { "notes": 252, "sounding_bars": 5.75, "empty_bar_rate": 0.8125, "role_assignments": [ { "program": 0, "drum": false, "notes": 140, "role": "chords" }, { "program": 24, "drum": false, "notes": 34, "role": "accompaniment" }, { "program": 32, "drum": false, "notes": 1, "role": "bass" }, { "program": 0, "drum": true, "notes": 77, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 5.8 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "9ec8052df2b72461bc396e0c322c79a0fb129eb9ebe1160b134d7c4814e33847", "mp3": "4e74f73bdcdfcc9a71a52a586ca876cc84edac6c908eb76de9f98cf562107574", "wav": "2e8a0288ac658e48ce75886d695a170c0ec088f17138818cbd10a8820a65e322" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-1_beat.wav", "source_wav_sha256": "2e8a0288ac658e48ce75886d695a170c0ec088f17138818cbd10a8820a65e322", "source_mp3_sha256": "fefafe5363b51e63b6d3caa07830a726dc458aa17ce10090cfb4d9500573c6a8", "source_audio_duration": 81.528163, "last_note_end_seconds": 27.5, "trim_end_seconds": 29, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-2", "window": "Track01631.npz:32", "model": "beat", "name": "BEAT", "midi": "assets/song-2_beat.mid", "mp3": "assets/song-2_beat.mp3", "wav": "assets/song-2_beat.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/short_prefix_fallback/models/beat/song-2/result.json", "source_midi_sha256": "e9b7d5803a5cc7392f8c2972835b27994dde3cb012480b9dd793e7f5d6307c35", "seed": 20260921, "model_input_bars": 4, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 3.25, "prefix_seconds": 18.916159559985374, "duration": 94.58079779992687, "audio_duration": 28.133878, "notes": 303, "peak": 0.33230891823768616, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 18.816145124716552, "generation": { "prefix_tokens": 1122, "encoded_prefix_bars_before_boundary_crop": 4, "total_tokens": 2048, "total_bar_tokens": 8, "stopped_at_eos": false, "reached_requested_boundary": false }, "metrics": { "rbde": 4.557565011014119, "rhythm_jsd": 0.18510845138310564, "chroma_jsd": 0.9175443989818153, "role_structure_error": 0.4692614867658892, "tsse": 0.4863853807653225 }, "diagnostics": { "notes": 303, "sounding_bars": 3.25, "empty_bar_rate": 0.875, "role_assignments": [ { "program": 0, "drum": false, "notes": 75, "role": "chords" }, { "program": 24, "drum": false, "notes": 104, "role": "chords" }, { "program": 32, "drum": false, "notes": 24, "role": "bass" }, { "program": 0, "drum": true, "notes": 100, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 3.3 / 32 bars. Reached the 2,048-token context limit in this run. Uses the last 4 GT context bars to fit the model context limit.", "hashes": { "mid": "434e2beda1ee19ffc0a4bd6d387504396e003c8a570def49b58dcc08e8851c27", "mp3": "124f90e430f99ec7b004b707f032ca6f8b5bd5f3f9109a08461c014405b81141", "wav": "3e938f9e7d48e617894e402dcc9ebe9ed774179ea896ee99609a4cc9e2decd67" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-2_beat.wav", "source_wav_sha256": "3e938f9e7d48e617894e402dcc9ebe9ed774179ea896ee99609a4cc9e2decd67", "source_mp3_sha256": "7b617668ef8e86cdb50e62a8b1d62e53aa30cf598c285bbd9b5601dec5912014", "source_audio_duration": 96.130612, "last_note_end_seconds": 26.60084938122943, "trim_end_seconds": 28.10084938122943, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-3", "window": "Track01672.npz:16", "model": "beat", "name": "BEAT", "midi": "assets/song-3_beat.mid", "mp3": "assets/song-3_beat.mp3", "wav": "assets/song-3_beat.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/beat/song-3/result.json", "source_midi_sha256": "6c09bff9c9389b25e5e30849ac4e6a8e68fc74a2b688b89d8cfb51c9e0b07d0b", "seed": 20260923, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 3.25, "prefix_seconds": 15.238080359925418, "duration": 76.1904017996271, "audio_duration": 22.961633, "notes": 141, "peak": 0.40005943179130554, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.138072562358277, "generation": { "prefix_tokens": 1472, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 12, "stopped_at_eos": false, "reached_requested_boundary": false }, "metrics": { "rbde": 4.670062351147792, "rhythm_jsd": 0.22181909910788142, "chroma_jsd": 0.9195132347222446, "role_structure_error": 0.4854629363655883, "tsse": 0.47982522088519236 }, "diagnostics": { "notes": 141, "sounding_bars": 3.25, "empty_bar_rate": 0.875, "role_assignments": [ { "program": 0, "drum": false, "notes": 66, "role": "chords" }, { "program": 24, "drum": false, "notes": 15, "role": "chords" }, { "program": 32, "drum": false, "notes": 12, "role": "bass" }, { "program": 0, "drum": true, "notes": 48, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 3.3 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "3ae1545f6c2ff837dcc33352aa4b3d8385cf25e771ca383771594333caab28b8", "mp3": "435c8a94eb0e5080ed15d0207cb286b61dfbe78e2c33d218f5fac9c2537054f3", "wav": "9237ad978a58591ee114869448b61a2dab0d977dc32dcf180b4a061aa02b2c0e" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-3_beat.wav", "source_wav_sha256": "9237ad978a58591ee114869448b61a2dab0d977dc32dcf180b4a061aa02b2c0e", "source_mp3_sha256": "81686e4c600e72ef5259332b04bb798d96648c7f5f6956938cf24a43fb33aed3", "source_audio_duration": 77.740408, "last_note_end_seconds": 21.42855050614512, "trim_end_seconds": 22.92855050614512, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-4", "window": "Track01657.npz:25", "model": "beat", "name": "BEAT", "midi": "assets/song-4_beat.mid", "mp3": "assets/song-4_beat.mp3", "wav": "assets/song-4_beat.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/beat/song-4/result.json", "source_midi_sha256": "11184a4cea22161731f7cfcc0b34051952a4096c50bad0ddb5c2b965abd37530", "seed": 20260924, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 6, "prefix_seconds": 16, "duration": 80, "audio_duration": 29.54449, "notes": 176, "peak": 0.22759996354579926, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 1234, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 14, "stopped_at_eos": false, "reached_requested_boundary": false }, "metrics": { "rbde": 4.677866617337087, "rhythm_jsd": 0.34048902410983944, "chroma_jsd": 0.8696923183869361, "role_structure_error": 0.420230373684283, "tsse": 0.5669724037125227 }, "diagnostics": { "notes": 176, "sounding_bars": 6, "empty_bar_rate": 0.8125, "role_assignments": [ { "program": 0, "drum": false, "notes": 84, "role": "chords" }, { "program": 24, "drum": false, "notes": 25, "role": "accompaniment" }, { "program": 32, "drum": false, "notes": 13, "role": "bass" }, { "program": 0, "drum": true, "notes": 54, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 6.0 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "8d7c05f1e6712f6dd257f8efbef3fea9c61e14b674514881fe70991a7d7cc135", "mp3": "3f21415f1e7164cd50d961fd7707da95b7ed8a8f4b9fd6a3e1aca2b576f333aa", "wav": "e4424d51fd0a698de978f85b850d9d74dda6e92e2e0a49335e3e43e4a3bc38ba" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-4_beat.wav", "source_wav_sha256": "e4424d51fd0a698de978f85b850d9d74dda6e92e2e0a49335e3e43e4a3bc38ba", "source_mp3_sha256": "9ca4b10ac4c1a7676663b61169055181077b7bf5ebc25ddc064298134fb47a26", "source_audio_duration": 81.528163, "last_note_end_seconds": 28, "trim_end_seconds": 29.5, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-5", "window": "Track01527.npz:112", "model": "beat", "name": "BEAT", "midi": "assets/song-5_beat.mid", "mp3": "assets/song-5_beat.mp3", "wav": "assets/song-5_beat.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/beat/song-5/result.json", "source_midi_sha256": "c0de292b6845fd3beb971b584a16d77b72b6689cf8736d31785b9adc6090f98e", "seed": 20260925, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 3.25, "prefix_seconds": 11.99923150692855, "duration": 59.996157534642755, "audio_duration": 18.416327, "notes": 194, "peak": 0.36702871322631836, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 11.899229024943311, "generation": { "prefix_tokens": 1428, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 12, "stopped_at_eos": false, "reached_requested_boundary": false }, "metrics": { "rbde": 8.05536539955556, "rhythm_jsd": 0.3691558782855611, "chroma_jsd": 0.9210425616940758, "role_structure_error": 0.48623840089981857, "tsse": 0.5168345993857641 }, "diagnostics": { "notes": 194, "sounding_bars": 3.25, "empty_bar_rate": 0.875, "role_assignments": [ { "program": 0, "drum": false, "notes": 36, "role": "accompaniment" }, { "program": 24, "drum": false, "notes": 118, "role": "chords" }, { "program": 32, "drum": false, "notes": 17, "role": "bass" }, { "program": 0, "drum": true, "notes": 23, "role": "drums" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 3.3 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "dcc119a8c28fc5448c2e456be275bec0ae7829e585ec2b2a3667ad8254546c5d", "mp3": "a1c7b7e3d41cf6b7d14fd0885eefba8a91b7c33b3813b8a56675ff11b0668f64", "wav": "23bf99b55e3bc89eb867b69475b4dfc888fe223bfac1486b68fc1f207ac3ffa3" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-5_beat.wav", "source_wav_sha256": "23bf99b55e3bc89eb867b69475b4dfc888fe223bfac1486b68fc1f207ac3ffa3", "source_mp3_sha256": "629ac0a333e80969c0c8bf41af072dfcc7f2e41ec788b4538138f5c7c32e8268", "source_audio_duration": 61.54449, "last_note_end_seconds": 16.873919306618276, "trim_end_seconds": 18.373919306618276, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-1", "window": "Track01646.npz:73", "model": "music2music", "name": "Music2Music-PT", "midi": "assets/song-1_music2music.mid", "mp3": "assets/song-1_music2music.mp3", "wav": "assets/song-1_music2music.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/music2music/song-1/result.json", "source_midi_sha256": "b08053f2c08856c5e59aceb252b0156dc11b5fc497811612d416e97df58faaac", "seed": 20260921, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 10, "prefix_seconds": 16, "duration": 80, "audio_duration": 37.537959, "notes": 527, "peak": 0.23219062387943268, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 815, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 18, "reached_requested_boundary": false }, "metrics": { "rbde": 10.432320927714882, "rhythm_jsd": 0.5013606315079193, "chroma_jsd": 0.7857375996664948, "role_structure_error": 0.8521918422890741, "tsse": 0.6753692394607709 }, "diagnostics": { "notes": 527, "sounding_bars": 10, "empty_bar_rate": 0.6875, "role_assignments": [ { "program": 0, "drum": false, "notes": 417, "role": "chords" }, { "program": 24, "drum": false, "notes": 110, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 10.0 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "a0954b7f2dd6d76000291e241b41722605ff233fbdf7c04f5d78cfb4898b729b", "mp3": "659b41cec44442b0e4ee0c6006e483c60ae51cfdf3833169567ddd20b337e23a", "wav": "82eccf9af70ecc5c4f0edde80ee1115115ff915794bfc4cc27d6b609dd8f3e98" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-1_music2music.wav", "source_wav_sha256": "82eccf9af70ecc5c4f0edde80ee1115115ff915794bfc4cc27d6b609dd8f3e98", "source_mp3_sha256": "b599db85a0603ebb2829900b0199e8fe7e3c2f0aec2ab9354e83545fb0dd8035", "source_audio_duration": 81.528163, "last_note_end_seconds": 36, "trim_end_seconds": 37.5, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-2", "window": "Track01631.npz:32", "model": "music2music", "name": "Music2Music-PT", "midi": "assets/song-2_music2music.mid", "mp3": "assets/song-2_music2music.mp3", "wav": "assets/song-2_music2music.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/music2music/song-2/result.json", "source_midi_sha256": "5724639d92b253896f0348cc977bb624509afd496ef47097576c44080a3c83dd", "seed": 20260922, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 5, "prefix_seconds": 18.916159559985374, "duration": 94.58079779992687, "audio_duration": 32.287347, "notes": 389, "peak": 0.3337804675102234, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 18.816145124716552, "generation": { "prefix_tokens": 894, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 13, "reached_requested_boundary": false }, "metrics": { "rbde": 7.751898634593587, "rhythm_jsd": 0.3568256439315878, "chroma_jsd": 0.918104698781457, "role_structure_error": 0.6746735222564931, "tsse": 0.5314012388920085 }, "diagnostics": { "notes": 389, "sounding_bars": 5, "empty_bar_rate": 0.84375, "role_assignments": [ { "program": 24, "drum": false, "notes": 192, "role": "chords" }, { "program": 0, "drum": false, "notes": 157, "role": "chords" }, { "program": 32, "drum": false, "notes": 40, "role": "bass" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 5.0 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "a90cac955ffd46f1c68ef4e543185472dd0eb51101966f2a957a98b8ddad177a", "mp3": "8b4aa19c7b15cf080bf914c4e7311d5815eb0c5abf4427f5cefb25a95f03fa03", "wav": "4b24be00440952205f7731f7dd8c1440acc607ff56b6d14e3d273ed2d0a78602" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-2_music2music.wav", "source_wav_sha256": "4b24be00440952205f7731f7dd8c1440acc607ff56b6d14e3d273ed2d0a78602", "source_mp3_sha256": "0cd0c3acd693e992f291fbb8685f128e9b56951a3cfbd69040d111ac297b7d94", "source_audio_duration": 96.130612, "last_note_end_seconds": 30.738759284976233, "trim_end_seconds": 32.23875928497623, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-3", "window": "Track01672.npz:16", "model": "music2music", "name": "Music2Music-PT", "midi": "assets/song-3_music2music.mid", "mp3": "assets/song-3_music2music.mp3", "wav": "assets/song-3_music2music.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/music2music/song-3/result.json", "source_midi_sha256": "2262d73ecb8921eb08982e274580d3faaef1a3de4910cb03129856b5a045de1b", "seed": 20260923, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 6.9375, "prefix_seconds": 15.238080359925418, "duration": 76.1904017996271, "audio_duration": 29.988571, "notes": 517, "peak": 0.40005943179130554, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.138072562358277, "generation": { "prefix_tokens": 758, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 15, "reached_requested_boundary": false }, "metrics": { "rbde": 7.752749472567174, "rhythm_jsd": 0.37877538530292365, "chroma_jsd": 0.8858308222435042, "role_structure_error": 0.6889423038618889, "tsse": 0.5935987947089653 }, "diagnostics": { "notes": 517, "sounding_bars": 6.9375, "empty_bar_rate": 0.78125, "role_assignments": [ { "program": 0, "drum": false, "notes": 203, "role": "chords" }, { "program": 24, "drum": false, "notes": 286, "role": "chords" }, { "program": 32, "drum": false, "notes": 28, "role": "bass" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 6.9 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "36b7ad8008573dda9347840008d1935a0c9ad5dfcc8c7da492571e96c7dc5dc5", "mp3": "02dcc75ce55bec3d20323d50c9d68b42065613e675e16a68431a754a554c3fc6", "wav": "eee8cb230e7e459ea8651fa97b1c1a943aa6313d3dae0f11c827c2f9361e7cc1" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-3_music2music.wav", "source_wav_sha256": "eee8cb230e7e459ea8651fa97b1c1a943aa6313d3dae0f11c827c2f9361e7cc1", "source_mp3_sha256": "f43356d6c092508a02b96b634cadf18d2a5a5666ed16f11dc3c7c092e999a4ce", "source_audio_duration": 77.740408, "last_note_end_seconds": 28.45235317204824, "trim_end_seconds": 29.95235317204824, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-4", "window": "Track01657.npz:25", "model": "music2music", "name": "Music2Music-PT", "midi": "assets/song-4_music2music.mid", "mp3": "assets/song-4_music2music.mp3", "wav": "assets/song-4_music2music.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/music2music/song-4/result.json", "source_midi_sha256": "0b31494f88ec5b8cd0668adfac0d74f4d5924b02a10157a871f02319394321c8", "seed": 20260924, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 19.125, "prefix_seconds": 16, "duration": 80, "audio_duration": 55.797551, "notes": 616, "peak": 0.2635011076927185, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 382, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 27, "reached_requested_boundary": false }, "metrics": { "rbde": 10.660628211777185, "rhythm_jsd": 0.5635645415623898, "chroma_jsd": 0.5257242353742029, "role_structure_error": 0.7796843502751747, "tsse": 0.7024641720837265 }, "diagnostics": { "notes": 616, "sounding_bars": 19.125, "empty_bar_rate": 0.375, "role_assignments": [ { "program": 0, "drum": false, "notes": 358, "role": "chords" }, { "program": 24, "drum": false, "notes": 212, "role": "chords" }, { "program": 32, "drum": false, "notes": 46, "role": "bass" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 19.1 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "bea7f910ab1130d70d91ead1b708bd42018f23e934c75a6e4daf75f3cae5f085", "mp3": "633adcc6f2e06776be6be9a9a4d76490b9438b3724b2e6e8be9b78f3ea7d8c4c", "wav": "ed7b2c47f143aef282718531063c3215c8efcc2676641dcfb3a2a330952de5e3" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-4_music2music.wav", "source_wav_sha256": "ed7b2c47f143aef282718531063c3215c8efcc2676641dcfb3a2a330952de5e3", "source_mp3_sha256": "6394fa917042d56f5c35cf1216d33be02d0185f50427ff9a1a355db44fa42fc3", "source_audio_duration": 81.528163, "last_note_end_seconds": 54.25, "trim_end_seconds": 55.75, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-5", "window": "Track01527.npz:112", "model": "music2music", "name": "Music2Music-PT", "midi": "assets/song-5_music2music.mid", "mp3": "assets/song-5_music2music.mp3", "wav": "assets/song-5_music2music.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/music2music/song-5/result.json", "source_midi_sha256": "ed9f3c571ce89ecc5438fc16c68256445b4bbccb022597c61f5e4e7b0624095b", "seed": 20260925, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 9, "prefix_seconds": 11.99923150692855, "duration": 59.996157534642755, "audio_duration": 27.036735, "notes": 417, "peak": 0.36702871322631836, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 11.899229024943311, "generation": { "prefix_tokens": 937, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 17, "reached_requested_boundary": false }, "metrics": { "rbde": 7.33287131639229, "rhythm_jsd": 0.34376207907528916, "chroma_jsd": 0.7806652873017116, "role_structure_error": 0.69995029025211, "tsse": 0.6695463524496241 }, "diagnostics": { "notes": 417, "sounding_bars": 9, "empty_bar_rate": 0.71875, "role_assignments": [ { "program": 0, "drum": false, "notes": 109, "role": "chords" }, { "program": 24, "drum": false, "notes": 258, "role": "chords" }, { "program": 32, "drum": false, "notes": 50, "role": "bass" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 9.0 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "32bc87b8f18df9a31bcc8ebfa9797a95852e803fa314ecf5cb9598d5c183f123", "mp3": "92bae0aa841807b163e04818ef66d5373b31574c9546fdaf1446351cf9958daa", "wav": "654d8bd0d423ed807d4e097329759a91277da46d12cd33e4fc68f690326b895d" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-5_music2music.wav", "source_wav_sha256": "654d8bd0d423ed807d4e097329759a91277da46d12cd33e4fc68f690326b895d", "source_mp3_sha256": "2cb0ff47bfc037bd2d2710a7dbbb17d85cf00a46bb8da99098c9d7c816b99593", "source_audio_duration": 61.54449, "last_note_end_seconds": 25.498366952223172, "trim_end_seconds": 26.998366952223172, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-1", "window": "Track01646.npz:73", "model": "text2midi", "name": "Text2midi", "midi": "assets/song-1_text2midi.mid", "mp3": "assets/song-1_text2midi.mp3", "wav": "assets/song-1_text2midi.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/text2midi/song-1/result.json", "source_midi_sha256": "3ddd4717f9fd82260a0c7279704fb3bedda02405ff4bec58e9a27303594704c0", "seed": 20260921, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 0.625, "prefix_seconds": 16, "duration": 80, "audio_duration": 18.782041, "notes": 29, "peak": 0.20436261594295502, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 1922, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 9, "reached_requested_boundary": false, "encoder_cache_parity": true }, "metrics": { "rbde": 5.392548699029837, "rhythm_jsd": 0.3287778539068692, "chroma_jsd": 0.9726068661916691, "role_structure_error": 0.4375531169559423, "tsse": 0.27680058084572695 }, "diagnostics": { "notes": 29, "sounding_bars": 0.625, "empty_bar_rate": 0.96875, "role_assignments": [ { "program": 0, "drum": false, "notes": 18, "role": "chords" }, { "program": 0, "drum": true, "notes": 8, "role": "drums" }, { "program": 24, "drum": false, "notes": 3, "role": "accompaniment" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 0.6 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "6940667bb0af4770612c4fc7f03f6c55f39020f7636216a03f8272f3bc7a5e12", "mp3": "5e392ca30595e682a20ba1194977a3a20f4b0a11bf61b7809c6ccd63716b082e", "wav": "45be07c3f75d1391cfab744a092abf449a7327258a15cec21075d9b4cc32fd4a" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-1_text2midi.wav", "source_wav_sha256": "45be07c3f75d1391cfab744a092abf449a7327258a15cec21075d9b4cc32fd4a", "source_mp3_sha256": "8ad90ce0bb1f8984987f1da429c504a298bb376b1070f51dc2289fb17caf7143", "source_audio_duration": 81.528163, "last_note_end_seconds": 17.25, "trim_end_seconds": 18.75, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-2", "window": "Track01631.npz:32", "model": "text2midi", "name": "Text2midi", "midi": "assets/song-2_text2midi.mid", "mp3": "assets/song-2_text2midi.mp3", "wav": "assets/song-2_text2midi.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/short_prefix_fallback/models/text2midi/song-2/result.json", "source_midi_sha256": "a179207640ac78fb2d4c8653c065274bf7d6c9850e967db31edadd283da9cd68", "seed": 20260921, "model_input_bars": 4, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 3, "prefix_seconds": 18.916159559985374, "duration": 94.58079779992687, "audio_duration": 27.559184, "notes": 177, "peak": 0.33230891823768616, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 18.816145124716552, "generation": { "prefix_tokens": 1291, "encoded_prefix_bars_before_boundary_crop": 4, "total_tokens": 2048, "total_bar_tokens": 7, "reached_requested_boundary": false, "encoder_cache_parity": true }, "metrics": { "rbde": 8.161759649443576, "rhythm_jsd": 0.427465783307923, "chroma_jsd": 0.9655993673539488, "role_structure_error": 0.5429765129400629, "tsse": 0.43210588308927045 }, "diagnostics": { "notes": 177, "sounding_bars": 3, "empty_bar_rate": 0.90625, "role_assignments": [ { "program": 0, "drum": false, "notes": 22, "role": "accompaniment" }, { "program": 32, "drum": false, "notes": 16, "role": "bass" }, { "program": 0, "drum": true, "notes": 70, "role": "drums" }, { "program": 24, "drum": false, "notes": 69, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 3.0 / 32 bars. Reached the 2,048-token context limit in this run. Uses the last 4 GT context bars to fit the model context limit.", "hashes": { "mid": "05ce453467263fe720eab5f260c26f87b77e562ae3e9bb5fa64054009a6d447c", "mp3": "22ea545028b841617c279943861970fa5f5199df2c0e9f70830d4f84e913f6fb", "wav": "d11fdf8ed03398e9a990379929325433da61d8ad51c205bb6bbcb7777729d4fd" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-2_text2midi.wav", "source_wav_sha256": "d11fdf8ed03398e9a990379929325433da61d8ad51c205bb6bbcb7777729d4fd", "source_mp3_sha256": "bfd7aa69d501c4693610c8211b8ab16bc8ecd689b720dc20d8a0c56dd8ae4157", "source_audio_duration": 96.130612, "last_note_end_seconds": 26.00971939497989, "trim_end_seconds": 27.50971939497989, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-3", "window": "Track01672.npz:16", "model": "text2midi", "name": "Text2midi", "midi": "assets/song-3_text2midi.mid", "mp3": "assets/song-3_text2midi.mp3", "wav": "assets/song-3_text2midi.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/text2midi/song-3/result.json", "source_midi_sha256": "de9c0ce2ba701a0a80b906d1c6865270e34e14dcea48dc1e07d779527b233ac7", "seed": 20260923, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 2, "prefix_seconds": 15.238080359925418, "duration": 76.1904017996271, "audio_duration": 20.58449, "notes": 54, "peak": 0.40005943179130554, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.138072562358277, "generation": { "prefix_tokens": 1808, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 10, "reached_requested_boundary": false, "encoder_cache_parity": true }, "metrics": { "rbde": 8.427380411580021, "rhythm_jsd": 0.5295715114053553, "chroma_jsd": 0.9858739380198752, "role_structure_error": 0.5418941898322744, "tsse": 0.35425248549225014 }, "diagnostics": { "notes": 54, "sounding_bars": 2, "empty_bar_rate": 0.9375, "role_assignments": [ { "program": 0, "drum": false, "notes": 28, "role": "accompaniment" }, { "program": 32, "drum": false, "notes": 6, "role": "bass" }, { "program": 24, "drum": false, "notes": 4, "role": "chords" }, { "program": 0, "drum": true, "notes": 13, "role": "drums" }, { "program": 49, "drum": false, "notes": 3, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 2.0 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "0e98f535cfd6d7bd9c04eb6f44b540650e8b33d8563fdd8730266b20555e6db0", "mp3": "51ad2946679216cf4f62c4b932753e60eb627c0278cb1de6bbeb359ca1077352", "wav": "e2a1b8fdc0c5009a31ef9aa356df7fe450d47ca62cda74f6ea2152a2c2418e3c" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-3_text2midi.wav", "source_wav_sha256": "e2a1b8fdc0c5009a31ef9aa356df7fe450d47ca62cda74f6ea2152a2c2418e3c", "source_mp3_sha256": "b693f78dbafdbe318b8d995b542da39fbe83e5fa0997b03a8b86317fdc1c721d", "source_audio_duration": 77.740408, "last_note_end_seconds": 19.04760044990677, "trim_end_seconds": 20.54760044990677, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } }, { "song_id": "song-4", "window": "Track01657.npz:25", "model": "text2midi", "name": "Text2midi", "midi": "assets/song-4_text2midi.mid", "mp3": "assets/song-4_text2midi.mp3", "wav": "assets/song-4_text2midi.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/text2midi/song-4/result.json", "source_midi_sha256": "a83966ad8b3f06db9eaf7261d1b4620d1fde34b055ecc80844d9e4078f9f09ca", "seed": 20260924, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 6.125, "prefix_seconds": 16, "duration": 80, "audio_duration": 29.492245, "notes": 251, "peak": 0.34614115953445435, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 15.9, "generation": { "prefix_tokens": 944, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 14, "reached_requested_boundary": false, "encoder_cache_parity": true }, "metrics": { "rbde": 11.160206555757128, "rhythm_jsd": 0.5755733251000547, "chroma_jsd": 0.8927629105766118, "role_structure_error": 0.40540651708145936, "tsse": 0.5678505971862275 }, "diagnostics": { "notes": 251, "sounding_bars": 5.9375, "empty_bar_rate": 0.8125, "role_assignments": [ { "program": 0, "drum": false, "notes": 127, "role": "chords" }, { "program": 32, "drum": false, "notes": 20, "role": "bass" }, { "program": 0, "drum": true, "notes": 92, "role": "drums" }, { "program": 24, "drum": false, "notes": 2, "role": "chords" }, { "program": 48, "drum": false, "notes": 10, "role": "other" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 6.0 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "f1af37dbab5a700edcc4d883ea3bbea3167e515c0ac3034bde84ad695766d5ba", "mp3": "457a0fd5bdef5f56de324ca2372be96e0f8892ece3a7aed1e9fb2031f094b8f4", "wav": "0b73891d2063eeeb4fe641d6a3f46b83430e6fb1993b2f03e55d95bccfbeadea" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-4_text2midi.wav", "source_wav_sha256": "0b73891d2063eeeb4fe641d6a3f46b83430e6fb1993b2f03e55d95bccfbeadea", "source_mp3_sha256": "c3599f7e2836b01098130dc249e4c99c352f0ea7c962f86dac606d08300a3936", "source_audio_duration": 81.528163, "last_note_end_seconds": 27.958333333333332, "trim_end_seconds": 29.458333333333332, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false, "grid_last_note_end_seconds": 28.25, "endpoint_source": "Last note-off in the exported MIDI" }, "playback_sounding_bars": 5.979166666666666 }, { "song_id": "song-5", "window": "Track01527.npz:112", "model": "text2midi", "name": "Text2midi", "midi": "assets/song-5_text2midi.mid", "mp3": "assets/song-5_text2midi.mp3", "wav": "assets/song-5_text2midi.wav", "source_result": "/data/HDD1/tjut-yinhanqing/repo/experiments/cross_model/baseline_listening_20260921/models/text2midi/song-5/result.json", "source_midi_sha256": "9340de358c3445a24db294cebf51aee988d2a0452eb3351ef17324998e9f2c67", "seed": 20260925, "model_input_bars": 8, "display_prefix_bars": 8, "requested_bars": 32, "sounding_bars": 1.125, "prefix_seconds": 11.99923150692855, "duration": 59.996157534642755, "audio_duration": 15.229388, "notes": 40, "peak": 0.36702871322631836, "prefix_notes_identical": true, "prefix_audio_identical": true, "prefix_audio_checked_seconds": 11.899229024943311, "generation": { "prefix_tokens": 1879, "encoded_prefix_bars_before_boundary_crop": 8, "total_tokens": 2048, "total_bar_tokens": 9, "reached_requested_boundary": false, "encoder_cache_parity": true }, "metrics": { "rbde": 5.375425071042135, "rhythm_jsd": 0.27611276124806505, "chroma_jsd": 0.9826885203254145, "role_structure_error": 0.4986239658092249, "tsse": 0.3995068326902232 }, "diagnostics": { "notes": 40, "sounding_bars": 1.125, "empty_bar_rate": 0.9375, "role_assignments": [ { "program": 0, "drum": false, "notes": 8, "role": "chords" }, { "program": 32, "drum": false, "notes": 3, "role": "bass" }, { "program": 0, "drum": true, "notes": 6, "role": "drums" }, { "program": 24, "drum": false, "notes": 23, "role": "chords" } ], "role_mapping": "grid_onset_v2" }, "notation_timing": null, "listening_note": "Native output: 1.1 / 32 bars. Reached the 2,048-token context limit in this run.", "hashes": { "mid": "e73a7be26cf3208f058b8787cc4f5433fe91f9198508a5c89bf281f6f49f6be0", "mp3": "5312936ed0e53750ce0bb0c73e01303b33b9fd292fe5e96195ca3a44392f561f", "wav": "c833cd0b9e75fc4fb1151e247a2d06f08acb2bd73887cfdb2fc45fba4a916a22" }, "audio_assembly": "Reuse the hashed lossless GT prefix through handoff minus 0.1 seconds; the boundary and continuation are synthesized from the combined MIDI.", "audio_edit": { "source_wav": "demo/baseline-20260921/assets/song-5_text2midi.wav", "source_wav_sha256": "c833cd0b9e75fc4fb1151e247a2d06f08acb2bd73887cfdb2fc45fba4a916a22", "source_mp3_sha256": "f395dcb3951e9dafbb148aafcca451948524009c71f0071c4bba04234543fa66", "source_audio_duration": 61.54449, "last_note_end_seconds": 13.686623437590377, "trim_end_seconds": 15.186623437590377, "release_tail_seconds": 1.5, "silent_padding": false, "bitrate_kbps": 192, "midi_notes_changed": false } } ], "pending": [], "human_listening_review": false }