{"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/text-to-audio-retrieval","name":"Text to Audio Retrieval","slug":"text-to-audio-retrieval","description_markdown":null,"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":20,"papers_with_code":13,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":5,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","slug":"text-to-audio-retrieval-on-clotho","dataset":"Clotho","dataset_url":"/dataset/clotho","rows_in_archive":12,"metrics":["R@1","R@5","R@10","mAP@10"],"first_row_in_archive_order":{"model":"PaSST-RoBERTa & Estimated Audio–Caption Correspondences","paper_title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","paper_url":"/paper/estimated-audio-caption-correspondences","paper_date":"2024-08-21","arxiv_id":"2408.11641","code_links":[{"title":"optimusprimus/salsa","url":"https://github.com/optimusprimus/salsa"}],"syntology":null}},{"leaderboard":"/sota/text-to-audio-retrieval-on-audiocaps","slug":"text-to-audio-retrieval-on-audiocaps","dataset":"AudioCaps","dataset_url":"/dataset/audiocaps","rows_in_archive":11,"metrics":["R@1","R@5","R@10"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","paper_url":"/paper/internvideo2-scaling-video-foundation-models","paper_date":"2024-03-22","arxiv_id":"2403.15377","code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}],"syntology":null}},{"leaderboard":"/sota/text-to-audio-retrieval-on-sounddescs","slug":"text-to-audio-retrieval-on-sounddescs","dataset":"SoundDescs","dataset_url":"/dataset/sounddescs","rows_in_archive":4,"metrics":["R@1","R@10"],"first_row_in_archive_order":{"model":"CE","paper_title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","paper_url":"/paper/audio-retrieval-with-natural-language-queries-1","paper_date":"2021-12-17","arxiv_id":"2112.09418","code_links":[{"title":"akoepke/audio-retrieval-benchmark","url":"https://github.com/akoepke/audio-retrieval-benchmark"}],"syntology":null}},{"leaderboard":"/sota/text-to-audio-retrieval-on-localized","slug":"text-to-audio-retrieval-on-localized","dataset":"Localized Narratives","dataset_url":"/dataset/localized-narratives","rows_in_archive":1,"metrics":["Text-to-audio R@1","Text-to-audio R@10","Text-to-audio R@5"],"first_row_in_archive_order":{"model":"OPT","paper_title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","paper_url":"/paper/opt-omni-perception-pre-trainer-for-cross","paper_date":"2021-07-01","arxiv_id":"2107.00249","code_links":[{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/mm/opt"},{"title":"2023-MindSpore-1/ms-code-161","url":"https://github.com/2023-MindSpore-1/ms-code-161"}],"syntology":null}}],"datasets":[{"url":"/dataset/audiocaps","name":"AudioCaps","full_name":"","num_papers_in_archive":279},{"url":"/dataset/clotho","name":"Clotho","full_name":"Clotho","num_papers_in_archive":202},{"url":"/dataset/localized-narratives","name":"Localized Narratives","full_name":"","num_papers_in_archive":63},{"url":"/dataset/wavcaps","name":"WavCaps","full_name":"","num_papers_in_archive":41},{"url":"/dataset/sounddescs","name":"SoundDescs","full_name":"","num_papers_in_archive":8}],"subtasks":[{"url":"/task/audio-moment-retrieval","name":"audio moment retrieval"}],"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":1,"rows_per_page":100,"shown":20,"of":20,"of_with_code":13,"tagged_in_all":20,"counts":{"archive_papers_tagged":20,"with_a_code_link":13,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":20,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":6,"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/m2d2-exploring-general-purpose-audio-language","slug":"m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/opt-omni-perception-pre-trainer-for-cross","slug":"opt-omni-perception-pre-trainer-for-cross","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","date":"2021-07-01","arxiv_id":"2107.00249","repositories_listed":2,"syntology":null},{"url":"/paper/evaluation-of-pretrained-language-models-on","slug":"evaluation-of-pretrained-language-models-on","title":"Evaluation of pretrained language models on music understanding","date":"2024-09-17","arxiv_id":"2409.11449","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"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: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluation-of-pretrained-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2409.11449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11449"}},"official":{"repos":["YannisBilly/Evaluation-of-pretrained-language-models-on-music-understanding"],"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/estimated-audio-caption-correspondences","slug":"estimated-audio-caption-correspondences","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","date":"2024-08-21","arxiv_id":"2408.11641","repositories_listed":1,"syntology":null},{"url":"/paper/the-song-describer-dataset-a-corpus-of-audio","slug":"the-song-describer-dataset-a-corpus-of-audio","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","date":"2023-11-16","arxiv_id":"2311.10057","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-song-describer-dataset-a-corpus-of-audio#ran","syntology_url":"https://syntology.ai/paper/2311.10057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10057"}},"official":{"repos":["mulab-mir/song-describer-dataset"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/advancing-natural-language-based-audio","slug":"advancing-natural-language-based-audio","title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","date":"2023-08-08","arxiv_id":"2308.04258","repositories_listed":1,"syntology":null},{"url":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-retrieval-with-querybank","slug":"cross-modal-retrieval-with-querybank","title":"Cross Modal Retrieval with Querybank Normalisation","date":"2021-12-23","arxiv_id":"2112.12777","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cross-modal-retrieval-with-querybank#ran","syntology_url":"https://syntology.ai/paper/2112.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12777"}},"official":{"repos":["ioanacroi/qb-norm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/audio-retrieval-with-natural-language-queries-1","slug":"audio-retrieval-with-natural-language-queries-1","title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","date":"2021-12-17","arxiv_id":"2112.09418","repositories_listed":1,"syntology":null},{"url":"/paper/audio-retrieval-with-natural-language-queries","slug":"audio-retrieval-with-natural-language-queries","title":"Audio Retrieval with Natural Language Queries","date":"2021-05-05","arxiv_id":"2105.02192","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/audio-retrieval-with-natural-language-queries#ran","syntology_url":"https://syntology.ai/paper/2105.02192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02192"}},"official":{"repos":["oncescuandreea/audio-retrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":null,"slug":"do-audio-language-models-understand","title":"Do Audio-Language Models Understand Linguistic Variations?","date":"2024-10-21","arxiv_id":"2410.16505","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-language-of-sound-search-examining-user","title":"The language of sound search: Examining User Queries in Audio Search Engines","date":"2024-10-10","arxiv_id":"2410.08324","repositories_listed":0,"syntology":null},{"url":null,"slug":"dissecting-temporal-understanding-in-text-to","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","date":"2024-09-01","arxiv_id":"2409.00851","repositories_listed":0,"syntology":null},{"url":null,"slug":"wikimute-a-web-sourced-dataset-of-semantic","title":"WikiMuTe: A web-sourced dataset of semantic descriptions for music audio","date":"2023-12-14","arxiv_id":"2312.09207","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-leakage-in-cross-modal-retrieval","title":"Data leakage in cross-modal retrieval training: A case study","date":"2023-02-23","arxiv_id":"2302.12258","repositories_listed":0,"syntology":null},{"url":"/paper/improving-audio-language-learning-with-mixgen","slug":"improving-audio-language-learning-with-mixgen","title":"Exploring Train and Test-Time Augmentations for Audio-Language Learning","date":"2022-10-31","arxiv_id":"2210.17143","repositories_listed":0,"syntology":null},{"url":null,"slug":"matching-text-and-audio-embeddings-exploring","title":"Matching Text and Audio Embeddings: Exploring Transfer-learning Strategies for Language-based Audio Retrieval","date":"2022-10-06","arxiv_id":"2210.02833","repositories_listed":0,"syntology":null}],"syntology_records":6,"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":4,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","since_archive":"/sota/text-to-audio-retrieval-on-clotho#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/text-to-audio-retrieval-on-audiocaps","since_archive":"/sota/text-to-audio-retrieval-on-audiocaps#since-judged","papers_judged":3,"placed":0}]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/text-to-audio-retrieval/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":"ran","page":1,"of":1,"url":"/task/text-to-audio-retrieval/papers/ran/1","json":"/task/text-to-audio-retrieval/papers/ran/1.json","rows":6}],"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":"e583ee3bf042a903e5a9dfba9d822b96e117338316cbe804f496a0c752c05845","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}