{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/audio-source-separation","name":"Audio Source Separation","slug":"audio-source-separation","description_markdown":"**Audio Source Separation** is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals).\r\n\r\n\r\n<span class=\"description-source\">Source: [Model selection for deep audio source separation via clustering analysis ](https://arxiv.org/abs/1910.12626)</span>","categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":112,"papers_with_code":54,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":15,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-source-separation-on-audioset","slug":"audio-source-separation-on-audioset","dataset":"AudioSet","dataset_url":"/dataset/audioset","rows_in_archive":2,"metrics":["SDR","SAR","SIR"],"first_row_in_archive_order":{"model":"ST-SED-SEP","paper_title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","paper_url":"/paper/zero-shot-audio-source-separation-through","paper_date":"2021-12-15","arxiv_id":"2112.07891","code_links":[{"title":"RetroCirce/Zero_Shot_Audio_Source_Separation","url":"https://github.com/RetroCirce/Zero_Shot_Audio_Source_Separation"}],"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zero-shot-audio-source-separation-through#ran","syntology_url":"https://syntology.ai/paper/2112.07891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07891"}},"official":{"repos":["RetroCirce/Zero_Shot_Audio_Source_Separation"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/audio-source-separation-on-music-multi-source","slug":"audio-source-separation-on-music-multi-source","dataset":"MUSIC (multi-source)","dataset_url":null,"rows_in_archive":1,"metrics":["SAR","SIR"],"first_row_in_archive_order":{"model":"Co-Separation","paper_title":"Co-Separating Sounds of Visual Objects","paper_url":"/paper/co-separating-sounds-of-visual-objects","paper_date":"2019-04-16","arxiv_id":"1904.07750","code_links":[{"title":"rhgao/co-separation","url":"https://github.com/rhgao/co-separation"},{"title":"manhnguyen1998/co_separation_encoder_decoder","url":"https://github.com/manhnguyen1998/co_separation_encoder_decoder"},{"title":"YashNita/Co-Separating-Sound-Object-","url":"https://github.com/YashNita/Co-Separating-Sound-Object-"}],"syntology":null}}],"datasets":[{"url":"/dataset/audioset","name":"AudioSet","full_name":"","num_papers_in_archive":744},{"url":"/dataset/wsj0-2mix-1","name":"WSJ0-2mix","full_name":"","num_papers_in_archive":159},{"url":"/dataset/librimix","name":"LibriMix","full_name":"","num_papers_in_archive":122},{"url":"/dataset/wham","name":"WHAM!","full_name":"WSJ0 Hipster Ambient Mixtures","num_papers_in_archive":114},{"url":"/dataset/musdb18","name":"MUSDB18","full_name":"","num_papers_in_archive":106},{"url":"/dataset/whamr","name":"WHAMR!","full_name":"WHAM! with synthetic reverberated sources","num_papers_in_archive":57},{"url":"/dataset/deep-noise-suppression-2020","name":"DNS Challenge","full_name":"Deep Noise Suppression Challenge","num_papers_in_archive":48},{"url":"/dataset/avspeech","name":"AVSpeech","full_name":"","num_papers_in_archive":42},{"url":"/dataset/fuss","name":"FUSS","full_name":"Free Universal Sound Separation","num_papers_in_archive":16},{"url":"/dataset/sms-wsj","name":"SMS-WSJ","full_name":"Spatialized Multi-Speaker Wall Street Journal","num_papers_in_archive":14},{"url":"/dataset/openmic-2018","name":"OpenMIC-2018","full_name":null,"num_papers_in_archive":8},{"url":"/dataset/medleyvox","name":"MedleyVox","full_name":"","num_papers_in_archive":2},{"url":"/dataset/jacappella","name":"jaCappella","full_name":"","num_papers_in_archive":1},{"url":"/dataset/kinect-wsj","name":"Kinect-WSJ","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cadenza-woodwind","name":"Cadenza Woodwind","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/directional-hearing","name":"Directional Hearing"},{"url":"/task/single-label-target-sound-extraction","name":"Single-Label Target Sound Extraction"},{"url":"/task/target-sound-extraction","name":"Target Sound Extraction"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":112,"of_with_code":54,"tagged_in_all":112,"counts":{"archive_papers_tagged":112,"with_a_code_link":54,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":112,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":15,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":15,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/wave-u-net-a-multi-scale-neural-network-for","slug":"wave-u-net-a-multi-scale-neural-network-for","title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","date":"2018-06-08","arxiv_id":"1806.03185","repositories_listed":10,"syntology":{"n":19,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/wave-u-net-a-multi-scale-neural-network-for#ran","syntology_url":"https://syntology.ai/paper/1806.03185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.03185"}},"official":{"repos":["f90/Wave-U-Net"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-scale-multi-band-densenets-for-audio","slug":"multi-scale-multi-band-densenets-for-audio","title":"Multi-scale Multi-band DenseNets for Audio Source Separation","date":"2017-06-29","arxiv_id":"1706.09588","repositories_listed":5,"syntology":null},{"url":"/paper/sudo-rm-rf-efficient-networks-for-universal","slug":"sudo-rm-rf-efficient-networks-for-universal","title":"Sudo rm -rf: Efficient Networks for Universal Audio Source Separation","date":"2020-07-14","arxiv_id":"2007.06833","repositories_listed":4,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sudo-rm-rf-efficient-networks-for-universal#ran","syntology_url":"https://syntology.ai/paper/2007.06833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06833"}},"official":{"repos":["etzinis/sudo_rm_rf"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-cocktail-fork-problem-three-stem-audio","slug":"the-cocktail-fork-problem-three-stem-audio","title":"The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks","date":"2021-10-19","arxiv_id":"2110.09958","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-cocktail-fork-problem-three-stem-audio#ran","syntology_url":"https://syntology.ai/paper/2110.09958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09958"}},"official":null}},{"url":"/paper/compute-and-memory-efficient-universal-sound","slug":"compute-and-memory-efficient-universal-sound","title":"Compute and memory efficient universal sound source separation","date":"2021-03-03","arxiv_id":"2103.02644","repositories_listed":3,"syntology":null},{"url":"/paper/co-separating-sounds-of-visual-objects","slug":"co-separating-sounds-of-visual-objects","title":"Co-Separating Sounds of Visual Objects","date":"2019-04-16","arxiv_id":"1904.07750","repositories_listed":3,"syntology":null},{"url":"/paper/improved-speech-enhancement-with-the-wave-u","slug":"improved-speech-enhancement-with-the-wave-u","title":"Improved Speech Enhancement with the Wave-U-Net","date":"2018-11-27","arxiv_id":"1811.11307","repositories_listed":3,"syntology":null},{"url":"/paper/adversarial-semi-supervised-audio-source","slug":"adversarial-semi-supervised-audio-source","title":"Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction","date":"2017-10-31","arxiv_id":"1711.00048","repositories_listed":3,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/adversarial-semi-supervised-audio-source#ran","syntology_url":"https://syntology.ai/paper/1711.00048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00048"}},"official":{"repos":["f90/AdversarialAudioSeparation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/unsupervised-audio-source-separation-using-1","slug":"unsupervised-audio-source-separation-using-1","title":"Unsupervised Music Source Separation Using Differentiable Parametric Source Models","date":"2022-01-24","arxiv_id":"2201.09592","repositories_listed":2,"syntology":null},{"url":"/paper/directional-sparse-filtering-using-weighted","slug":"directional-sparse-filtering-using-weighted","title":"Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures","date":"2021-01-30","arxiv_id":"2102.00196","repositories_listed":2,"syntology":null},{"url":"/paper/conditioned-u-net-introducing-a-control","slug":"conditioned-u-net-introducing-a-control","title":"Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations","date":"2019-07-02","arxiv_id":"1907.01277","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conditioned-u-net-introducing-a-control#ran","syntology_url":"https://syntology.ai/paper/1907.01277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01277"}},"official":{"repos":["gabolsgabs/cunet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-separate-object-sounds-by","slug":"learning-to-separate-object-sounds-by","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","date":"2018-04-05","arxiv_id":"1804.01665","repositories_listed":2,"syntology":null},{"url":"/paper/towards-reliable-objective-evaluation-metrics","slug":"towards-reliable-objective-evaluation-metrics","title":"Towards Reliable Objective Evaluation Metrics for Generative Singing Voice Separation Models","date":"2025-07-15","arxiv_id":"2507.11427","repositories_listed":1,"syntology":null},{"url":"/paper/training-free-multi-step-audio-source","slug":"training-free-multi-step-audio-source","title":"Training-Free Multi-Step Audio Source Separation","date":"2025-05-26","arxiv_id":"2505.19534","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-llm-and-text-queried-separation","slug":"leveraging-llm-and-text-queried-separation","title":"Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection","date":"2024-11-02","arxiv_id":"2411.01174","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-text-queried-sound-event-detection","slug":"exploring-text-queried-sound-event-detection","title":"Exploring Text-Queried Sound Event Detection with Audio Source Separation","date":"2024-09-20","arxiv_id":"2409.13292","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-text-queried-sound-event-detection#ran","syntology_url":"https://syntology.ai/paper/2409.13292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13292"}},"official":{"repos":["apple-yinhan/tq-sed"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-composable-representations-for","slug":"unsupervised-composable-representations-for","title":"Unsupervised Composable Representations for Audio","date":"2024-08-19","arxiv_id":"2408.09792","repositories_listed":1,"syntology":null},{"url":"/paper/facing-the-music-tackling-singing-voice","slug":"facing-the-music-tackling-singing-voice","title":"Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation","date":"2024-08-07","arxiv_id":"2408.03588","repositories_listed":1,"syntology":null},{"url":"/paper/remastering-divide-and-remaster-a-cinematic","slug":"remastering-divide-and-remaster-a-cinematic","title":"Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support","date":"2024-07-09","arxiv_id":"2407.07275","repositories_listed":1,"syntology":null},{"url":"/paper/a-stem-agnostic-single-decoder-system-for","slug":"a-stem-agnostic-single-decoder-system-for","title":"A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems","date":"2024-06-26","arxiv_id":"2406.18747","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-stem-agnostic-single-decoder-system-for#ran","syntology_url":"https://syntology.ai/paper/2406.18747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18747"}},"official":{"repos":["kwatcharasupat/query-bandit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spectral-mapping-of-singing-voices-u-net","slug":"spectral-mapping-of-singing-voices-u-net","title":"Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation","date":"2024-05-30","arxiv_id":"2405.20059","repositories_listed":1,"syntology":null},{"url":"/paper/a-generalized-bandsplit-neural-network-for","slug":"a-generalized-bandsplit-neural-network-for","title":"A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation","date":"2023-09-05","arxiv_id":"2309.02539","repositories_listed":1,"syntology":null},{"url":"/paper/separate-anything-you-describe","slug":"separate-anything-you-describe","title":"Separate Anything You Describe","date":"2023-08-09","arxiv_id":"2308.05037","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/separate-anything-you-describe#ran","syntology_url":"https://syntology.ai/paper/2308.05037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05037"}},"official":{"repos":["audio-agi/audiosep"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-audio-visual-dynamics-using-scene","slug":"learning-audio-visual-dynamics-using-scene","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","date":"2022-10-29","arxiv_id":"2210.16472","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-audio-visual-dynamics-using-scene#ran","syntology_url":"https://syntology.ai/paper/2210.16472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16472"}},"official":null}},{"url":"/paper/deep-audio-waveform-prior","slug":"deep-audio-waveform-prior","title":"Deep Audio Waveform Prior","date":"2022-07-21","arxiv_id":"2207.10441","repositories_listed":1,"syntology":null},{"url":"/paper/separate-what-you-describe-language-queried","slug":"separate-what-you-describe-language-queried","title":"Separate What You Describe: Language-Queried Audio Source Separation","date":"2022-03-28","arxiv_id":"2203.15147","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/separate-what-you-describe-language-queried#ran","syntology_url":"https://syntology.ai/paper/2203.15147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15147"}},"official":{"repos":["liuxubo717/lass"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-audio-source-separation-through","slug":"zero-shot-audio-source-separation-through","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","date":"2021-12-15","arxiv_id":"2112.07891","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zero-shot-audio-source-separation-through#ran","syntology_url":"https://syntology.ai/paper/2112.07891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07891"}},"official":{"repos":["RetroCirce/Zero_Shot_Audio_Source_Separation"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hybrid-neural-networks-for-on-device","slug":"hybrid-neural-networks-for-on-device","title":"Hybrid Neural Networks for On-device Directional Hearing","date":"2021-12-11","arxiv_id":"2112.05893","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-with-jukebox-for-music","slug":"transfer-learning-with-jukebox-for-music","title":"Transfer Learning with Jukebox for Music Source Separation","date":"2021-11-28","arxiv_id":"2111.14200","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-source-separation-by-steering","slug":"unsupervised-source-separation-by-steering","title":"Unsupervised Source Separation By Steering Pretrained Music Models","date":"2021-10-25","arxiv_id":"2110.13071","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-source-separation-via-bayesian","slug":"unsupervised-source-separation-via-bayesian","title":"Unsupervised Source Separation via Bayesian Inference in the Latent Domain","date":"2021-10-11","arxiv_id":"2110.05313","repositories_listed":1,"syntology":null},{"url":"/paper/visual-scene-graphs-for-audio-source","slug":"visual-scene-graphs-for-audio-source","title":"Visual Scene Graphs for Audio Source Separation","date":"2021-09-24","arxiv_id":"2109.11955","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-scene-graphs-for-audio-source#ran","syntology_url":"https://syntology.ai/paper/2109.11955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11955"}},"official":{"repos":["merlresearch/AVSGS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-audio-source-separation","slug":"multi-task-audio-source-separation","title":"Multi-Task Audio Source Separation","date":"2021-07-14","arxiv_id":"2107.06467","repositories_listed":1,"syntology":null},{"url":"/paper/densely-connected-multi-dilated-convolutional","slug":"densely-connected-multi-dilated-convolutional","title":"Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction Tasks","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/parallel-and-flexible-sampling-from","slug":"parallel-and-flexible-sampling-from","title":"Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics","date":"2021-05-17","arxiv_id":"2105.08164","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parallel-and-flexible-sampling-from#ran","syntology_url":"https://syntology.ai/paper/2105.08164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08164"}},"official":{"repos":["vivjay30/pnf-sampling"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sampling-frequency-independent-audio-source","slug":"sampling-frequency-independent-audio-source","title":"Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method","date":"2021-05-10","arxiv_id":"2105.04079","repositories_listed":1,"syntology":null},{"url":"/paper/differentiable-model-compression-via-pseudo","slug":"differentiable-model-compression-via-pseudo","title":"Differentiable Model Compression via Pseudo Quantization Noise","date":"2021-04-20","arxiv_id":"2104.09987","repositories_listed":1,"syntology":null},{"url":"/paper/music-source-separation-conditioned-on-3d","slug":"music-source-separation-conditioned-on-3d","title":"Music source separation conditioned on 3D point clouds","date":"2021-02-03","arxiv_id":"2102.02028","repositories_listed":1,"syntology":null},{"url":"/paper/densely-connected-multidilated-convolutional","slug":"densely-connected-multidilated-convolutional","title":"Densely connected multidilated convolutional networks for dense prediction tasks","date":"2020-11-21","arxiv_id":"2011.11844","repositories_listed":1,"syntology":null},{"url":"/paper/unified-gradient-reweighting-for-model","slug":"unified-gradient-reweighting-for-model","title":"Unified Gradient Reweighting for Model Biasing with Applications to Source Separation","date":"2020-10-25","arxiv_id":"2010.13228","repositories_listed":1,"syntology":null},{"url":"/paper/the-cone-of-silence-speech-separation-by","slug":"the-cone-of-silence-speech-separation-by","title":"The Cone of Silence: Speech Separation by Localization","date":"2020-10-12","arxiv_id":"2010.06007","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-cone-of-silence-speech-separation-by#ran","syntology_url":"https://syntology.ai/paper/2010.06007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06007"}},"official":{"repos":["vivjay30/Cone-of-Silence"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/autoclip-adaptive-gradient-clipping-for","slug":"autoclip-adaptive-gradient-clipping-for","title":"AutoClip: Adaptive Gradient Clipping for Source Separation Networks","date":"2020-07-25","arxiv_id":"2007.14469","repositories_listed":1,"syntology":null},{"url":"/paper/otoworld-towards-learning-to-separate-by","slug":"otoworld-towards-learning-to-separate-by","title":"OtoWorld: Towards Learning to Separate by Learning to Move","date":"2020-07-12","arxiv_id":"2007.06123","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/otoworld-towards-learning-to-separate-by#ran","syntology_url":"https://syntology.ai/paper/2007.06123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06123"}},"official":{"repos":["pseeth/otoworld"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-audio-source-separation-using","slug":"unsupervised-audio-source-separation-using","title":"Unsupervised Audio Source Separation using Generative Priors","date":"2020-05-28","arxiv_id":"2005.13769","repositories_listed":1,"syntology":null},{"url":"/paper/time-domain-audio-source-separation-based-on","slug":"time-domain-audio-source-separation-based-on","title":"Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet Transform","date":"2020-01-28","arxiv_id":"2001.10190","repositories_listed":1,"syntology":null},{"url":"/paper/j-net-randomly-weighted-u-net-for-audio","slug":"j-net-randomly-weighted-u-net-for-audio","title":"J-Net: Randomly weighted U-Net for audio source separation","date":"2019-11-29","arxiv_id":"1911.12926","repositories_listed":1,"syntology":null},{"url":"/paper/retrieving-signals-in-the-frequency-domain","slug":"retrieving-signals-in-the-frequency-domain","title":"Retrieving Signals in the Frequency Domain with Deep Complex Extractors","date":"2019-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tf-attention-net-an-end-to-end-neural-network","slug":"tf-attention-net-an-end-to-end-neural-network","title":"Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation","date":"2019-09-12","arxiv_id":"1909.05746","repositories_listed":1,"syntology":null},{"url":"/paper/a-provably-correct-and-robust-algorithm-for","slug":"a-provably-correct-and-robust-algorithm-for","title":"A Provably Correct and Robust Algorithm for Convolutive Nonnegative Matrix Factorization","date":"2019-06-17","arxiv_id":"1906.06899","repositories_listed":1,"syntology":null},{"url":"/paper/training-generative-adversarial-networks-from","slug":"training-generative-adversarial-networks-from","title":"Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators","date":"2019-05-29","arxiv_id":"1905.12660","repositories_listed":1,"syntology":null},{"url":"/paper/weak-label-supervision-for-monaural-source","slug":"weak-label-supervision-for-monaural-source","title":"Audio Source Separation Using Variational Autoencoders and Weak Class Supervision","date":"2018-10-31","arxiv_id":"1810.13104","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-gaussian-process-audio-source","slug":"sparse-gaussian-process-audio-source","title":"Sparse Gaussian Process Audio Source Separation Using Spectrum Priors in the Time-Domain","date":"2018-10-30","arxiv_id":"1810.12679","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-scene-analysis-with-self","slug":"audio-visual-scene-analysis-with-self","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","date":"2018-04-10","arxiv_id":"1804.03641","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-challenges-for-neural","slug":"generalization-challenges-for-neural","title":"Generalization Challenges for Neural Architectures in Audio Source Separation","date":"2018-03-23","arxiv_id":"1803.08629","repositories_listed":1,"syntology":null},{"url":null,"slug":"dgmo-training-free-audio-source-separation","title":"DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization","date":"2025-06-03","arxiv_id":"2506.02858","repositories_listed":0,"syntology":null},{"url":null,"slug":"zerosep-separate-anything-in-audio-with-zero","title":"ZeroSep: Separate Anything in Audio with Zero Training","date":"2025-05-29","arxiv_id":"2505.23625","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-queried-audio-source-separation-via","title":"Text-Queried Audio Source Separation via Hierarchical Modeling","date":"2025-05-27","arxiv_id":"2505.21025","repositories_listed":0,"syntology":null},{"url":null,"slug":"score-distillation-sampling-for-audio-source","title":"Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond","date":"2025-05-07","arxiv_id":"2505.04621","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-identification-of-samples-in-hip","title":"Automatic Identification of Samples in Hip-Hop Music via Multi-Loss Training and an Artificial Dataset","date":"2025-02-10","arxiv_id":"2502.06364","repositories_listed":0,"syntology":null},{"url":null,"slug":"study-of-the-performance-of-ceemdan-in","title":"Study of the Performance of CEEMDAN in Underdetermined Speech Separation","date":"2024-11-18","arxiv_id":"2411.11312","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-aware-unified-source-separation","title":"Task-Aware Unified Source Separation","date":"2024-10-31","arxiv_id":"2410.23987","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-grouping-network-for-audio-source","title":"Semantic Grouping Network for Audio Source Separation","date":"2024-07-04","arxiv_id":"2407.03736","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-improvement-of-language-queried","title":"Performance Improvement of Language-Queried Audio Source Separation Based on Caption Augmentation From Large Language Models for DCASE Challenge 2024 Task 9","date":"2024-06-17","arxiv_id":"2406.11248","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-algorithmic-delay-implementation-of","title":"Low algorithmic delay implementation of convolutional beamformer for online joint source separation and dereverberation","date":"2024-06-14","arxiv_id":"2406.09821","repositories_listed":0,"syntology":null},{"url":null,"slug":"gull-a-generative-multifunctional-audio-codec","title":"Gull: A Generative Multifunctional Audio Codec","date":"2024-04-07","arxiv_id":"2404.04947","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-dynamical-variational-autoencoders","title":"Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation","date":"2023-12-07","arxiv_id":"2312.04167","repositories_listed":0,"syntology":null},{"url":null,"slug":"gass-generalizing-audio-source-separation","title":"GASS: Generalizing Audio Source Separation with Large-scale Data","date":"2023-09-29","arxiv_id":"2310.00140","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-audio-visual-source","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","date":"2023-03-28","arxiv_id":"2303.16342","repositories_listed":0,"syntology":null},{"url":"/paper/separate-and-diffuse-using-a-pretrained","slug":"separate-and-diffuse-using-a-pretrained","title":"Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation","date":"2023-01-25","arxiv_id":"2301.10752","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-the-cocktail-fork-problem-for","title":"Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks","date":"2022-12-14","arxiv_id":"2212.07327","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperbolic-audio-source-separation","title":"Hyperbolic Audio Source Separation","date":"2022-12-09","arxiv_id":"2212.05008","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-dictionary-search-integrating","title":"Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation","date":"2022-11-28","arxiv_id":"2211.15524","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchic-temporal-convolutional-network","slug":"hierarchic-temporal-convolutional-network","title":"Hierarchic Temporal Convolutional Network With Cross-Domain Encoder for Music Source Separation","date":"2022-06-30","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sampling-frequency-independent-dialogue","title":"Sampling Frequency Independent Dialogue Separation","date":"2022-06-05","arxiv_id":"2206.02124","repositories_listed":0,"syntology":null},{"url":"/paper/sepit-approaching-a-single-channel-speech","slug":"sepit-approaching-a-single-channel-speech","title":"SepIt: Approaching a Single Channel Speech Separation Bound","date":"2022-05-24","arxiv_id":"2205.11801","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-loss-functions-and-evaluation-metrics-for","title":"On loss functions and evaluation metrics for music source separation","date":"2022-02-16","arxiv_id":"2202.07968","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-digital-signal-processing","title":"Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds","date":"2022-02-01","arxiv_id":"2202.00200","repositories_listed":0,"syntology":null},{"url":null,"slug":"fish-sounds-towards-the-evaluation-of-marine","title":"Fish sounds: towards the evaluation of marine acoustic biodiversity through data-driven audio source separation","date":"2022-01-13","arxiv_id":"2201.05013","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-beat-tracking-in-musical","title":"Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning","date":"2022-01-05","arxiv_id":"2201.01771","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-audio-source-separation-through-1","title":"Zero-shot Audio Source Separation through Query-based Learningfrom Weakly-labeled Data","date":"2021-12-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reduction-of-subjective-listening-effort-for","title":"Reduction of Subjective Listening Effort for TV Broadcast Signals with Recurrent Neural Networks","date":"2021-11-02","arxiv_id":"2111.01914","repositories_listed":0,"syntology":null},{"url":null,"slug":"move2hear-active-audio-visual-source","title":"Move2Hear: Active Audio-Visual Source Separation","date":"2021-05-15","arxiv_id":"2105.07142","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-analysis-informed-content","title":"MULTIMODAL ANALYSIS: Informed content estimation and audio source separation","date":"2021-04-27","arxiv_id":"2104.13276","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-audio-visual-sound-source","title":"Weakly-supervised Audio-visual Sound Source Detection and Separation","date":"2021-03-25","arxiv_id":"2104.02606","repositories_listed":0,"syntology":null},{"url":null,"slug":"problems-using-deep-generative-models-for","title":"Problems using deep generative models for probabilistic audio source separation","date":"2020-11-03","arxiv_id":"2011.01761","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-transfer-learning-in-music-source","title":"A Study of Transfer Learning in Music Source Separation","date":"2020-10-23","arxiv_id":"2010.12650","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-listening-to-10-people-simultaneously","title":"Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm","date":"2020-10-22","arxiv_id":"2010.11871","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-accuracy-estimation-of-deep-learning","title":"Fast accuracy estimation of deep learning based multi-class musical source separation","date":"2020-10-19","arxiv_id":"2010.09453","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-on-audio-source","title":"Adversarial attacks on audio source separation","date":"2020-10-07","arxiv_id":"2010.03164","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-and-automatic-segmentation-of","title":"Structure and Automatic Segmentation of Dhrupad Vocal Bandish Audio","date":"2020-08-03","arxiv_id":"2008.00756","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-audio-source-separation-and","title":"Cooperative Audio Source Separation and Enhancement Using Distributed Microphone Arrays and Wearable Devices","date":"2019-12-10","arxiv_id":"1912.05038","repositories_listed":0,"syntology":null},{"url":null,"slug":"wildmix-dataset-and-spectro-temporal","title":"WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation","date":"2019-11-21","arxiv_id":"1911.09783","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-universal-sound-separation-using","title":"Improving Universal Sound Separation Using Sound Classification","date":"2019-11-18","arxiv_id":"1911.07951","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-strength-in-weakness-learning-to","title":"Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision","date":"2019-11-06","arxiv_id":"1911.02182","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-selection-for-deep-audio-source","title":"Model selection for deep audio source separation via clustering analysis","date":"2019-10-23","arxiv_id":"1910.12626","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-signals-with-deep-complex","title":"Retrieving Signals with Deep Complex Extractors","date":"2019-09-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interleaved-multitask-learning-for-audio","title":"Interleaved Multitask Learning for Audio Source Separation with Independent Databases","date":"2019-08-14","arxiv_id":"1908.05182","repositories_listed":0,"syntology":null},{"url":null,"slug":"blind-audio-source-separation-with-minimum","title":"Blind Audio Source Separation with Minimum-Volume Beta-Divergence NMF","date":"2019-07-04","arxiv_id":"1907.02404","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-separable-nonnegative-matrix","title":"Generalized Separable Nonnegative Matrix Factorization","date":"2019-05-30","arxiv_id":"1905.12995","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-source-separation-via-multi-scale","title":"Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets","date":"2019-04-08","arxiv_id":"1904.04161","repositories_listed":0,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":15,"papers_where_code_ran_first_page":"/task/audio-source-separation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/audio-source-separation/papers/2","json":"/task/audio-source-separation/papers/2.json","rows":12},{"order":"ran","page":1,"of":1,"url":"/task/audio-source-separation/papers/ran/1","json":"/task/audio-source-separation/papers/ran/1.json","rows":15}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"140b7a2fbe11eb92dffe6f3d8cd6b5f579d541535fa13296ebff5d7517b3c1b6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}