{"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":"/dataset/audiocaps/papers/ran/1","list_of":"/dataset/audiocaps","dataset":"AudioCaps","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_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'","samples_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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,19],"of":19,"counts":{"papers_with_a_benchmark_row":43,"with_a_code_link":36,"where_syntology_ran_a_sample":19,"not_listed_spam_title":0,"listed":43,"listed_where_code_ran":19,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":1,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/audiocaps/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/stable-audio-open","slug":"stable-audio-open","title":"Stable Audio Open","date":"2024-07-19","arxiv_id":"2407.14358","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["stability-ai/stable-audio-tools"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stable-audio-open#ran","syntology_url":"https://syntology.ai/paper/2407.14358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14358"}}}},{"paper":"/paper/enhancing-automated-audio-captioning-via","slug":"enhancing-automated-audio-captioning-via","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","date":"2024-06-19","arxiv_id":"2406.13275","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["frankenliu/LOAE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/enhancing-automated-audio-captioning-via#ran","syntology_url":"https://syntology.ai/paper/2406.13275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13275"}}}},{"paper":"/paper/2406-15487","slug":"2406-15487","title":"Improving Text-To-Audio Models with Synthetic Captions","date":"2024-06-18","arxiv_id":"2406.15487","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/2406-15487#ran","syntology_url":"https://syntology.ai/paper/2406.15487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15487"}}}},{"paper":"/paper/clapsep-leveraging-contrastive-pre-trained","slug":"clapsep-leveraging-contrastive-pre-trained","title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","date":"2024-02-27","arxiv_id":"2402.17455","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["aisaka0v0/clapsep"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clapsep-leveraging-contrastive-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2402.17455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17455"}}}},{"paper":"/paper/fast-timing-conditioned-latent-audio","slug":"fast-timing-conditioned-latent-audio","title":"Fast Timing-Conditioned Latent Audio Diffusion","date":"2024-02-07","arxiv_id":"2402.04825","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["stability-ai/stable-audio-metrics","stability-ai/stable-audio-tools"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fast-timing-conditioned-latent-audio#ran","syntology_url":"https://syntology.ai/paper/2402.04825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04825"}}}},{"paper":"/paper/audio-flamingo-a-novel-audio-language-model","slug":"audio-flamingo-a-novel-audio-language-model","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","date":"2024-02-02","arxiv_id":"2402.01831","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["NVIDIA/audio-flamingo"],"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":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/audio-flamingo-a-novel-audio-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01831"}}}},{"paper":"/paper/auffusion-leveraging-the-power-of-diffusion","slug":"auffusion-leveraging-the-power-of-diffusion","title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","date":"2024-01-02","arxiv_id":"2401.01044","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["happylittlecat2333/Auffusion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/auffusion-leveraging-the-power-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2401.01044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01044"}}}},{"paper":"/paper/zero-shot-audio-captioning-with-audio","slug":"zero-shot-audio-captioning-with-audio","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","date":"2023-11-14","arxiv_id":"2311.08396","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":17,"official":{"repos":["explainableml/zeraucap"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zero-shot-audio-captioning-with-audio#ran","syntology_url":"https://syntology.ai/paper/2311.08396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08396"}}}},{"paper":"/paper/accelerating-diffusion-based-text-to-audio","slug":"accelerating-diffusion-based-text-to-audio","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","date":"2023-09-19","arxiv_id":"2309.10740","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["Bai-YT/ConsistencyTTA"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/accelerating-diffusion-based-text-to-audio#ran","syntology_url":"https://syntology.ai/paper/2309.10740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10740"}}}},{"paper":"/paper/recap-retrieval-augmented-audio-captioning","slug":"recap-retrieval-augmented-audio-captioning","title":"RECAP: Retrieval-Augmented Audio Captioning","date":"2023-09-18","arxiv_id":"2309.09836","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["sreyan88/recap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recap-retrieval-augmented-audio-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.09836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09836"}}}},{"paper":"/paper/audioldm-2-learning-holistic-audio-generation","slug":"audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","arxiv_id":"2308.05734","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":27,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":16,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":19,"official":{"repos":["haoheliu/AudioLDM2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/audioldm-2-learning-holistic-audio-generation#ran","syntology_url":"https://syntology.ai/paper/2308.05734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.05734"}}}},{"paper":"/paper/make-an-audio-2-temporal-enhanced-text-to","slug":"make-an-audio-2-temporal-enhanced-text-to","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","date":"2023-05-29","arxiv_id":"2305.18474","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/make-an-audio-2-temporal-enhanced-text-to#ran","syntology_url":"https://syntology.ai/paper/2305.18474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18474"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":29,"samples_ran_instrument_failed":6,"samples_unverified":7,"pointer_only_for_licence":8,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/any-to-any-generation-via-composable","slug":"any-to-any-generation-via-composable","title":"Any-to-Any Generation via Composable Diffusion","date":"2023-05-19","arxiv_id":"2305.11846","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":13,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":5,"pointer_only_for_licence":1,"official":{"repos":["microsoft/i-Code"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/any-to-any-generation-via-composable#ran","syntology_url":"https://syntology.ai/paper/2305.11846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11846"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/make-an-audio-text-to-audio-generation-with","slug":"make-an-audio-text-to-audio-generation-with","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","date":"2023-01-30","arxiv_id":"2301.12661","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/make-an-audio-text-to-audio-generation-with#ran","syntology_url":"https://syntology.ai/paper/2301.12661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12661"}}}},{"paper":"/paper/audioldm-text-to-audio-generation-with-latent","slug":"audioldm-text-to-audio-generation-with-latent","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","date":"2023-01-29","arxiv_id":"2301.12503","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":21,"samples_ran":16,"samples_constructed":1,"samples_ran_checked":12,"samples_ran_instrument_failed":4,"samples_unverified":5,"pointer_only_for_licence":12,"official":{"repos":["haoheliu/AudioLDM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["named_in_paper","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/audioldm-text-to-audio-generation-with-latent#ran","syntology_url":"https://syntology.ai/paper/2301.12503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12503"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"record_sha256":"f6254b16f8caa2b16ef0a97c894a4966bfd37def9698f91e75c6f2bbc74787e3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}