{"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/clotho","name":"Clotho","full_name":"Clotho","description_markdown":"**Clotho** is an audio captioning dataset, consisting of 4981 audio samples, and each audio sample has five captions (a total of 24 905 captions). Audio samples are of 15 to 30 s duration and captions are eight to 20 words long.\n\nSource: [https://zenodo.org/record/3490684](https://zenodo.org/record/3490684)\nImage Source: [https://arxiv.org/abs/1910.09387](https://arxiv.org/abs/1910.09387)","description_withheld":null,"homepage":"https://zenodo.org/record/3490684","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/clotho-an-audio-captioning-dataset","title":"Clotho: An Audio Captioning Dataset","first_author":"Konstantinos Drossos","url":null},"license":{"name":"Other (Attribution)","url":"https://zenodo.org/record/3490684"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Audio captioning","url":"/task/audio-captioning","datasets_with_task":"/datasets/task/audio-captioning"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"},{"name":"Text to Audio Retrieval","url":"/task/text-to-audio-retrieval","datasets_with_task":"/datasets/task/text-to-audio-retrieval"},{"name":"Audio to Text Retrieval","url":"/task/audio-to-text-retrieval","datasets_with_task":"/datasets/task/audio-to-text-retrieval"},{"name":"Zero-shot Text to Audio Retrieval","url":"/task/zero-shot-text-to-audio-retrieval","datasets_with_task":"/datasets/task/zero-shot-text-to-audio-retrieval"},{"name":"Zero-shot Audio Captioning","url":"/task/zero-shot-audio-captioning","datasets_with_task":"/datasets/task/zero-shot-audio-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Clotho"],"data_loaders":[{"repo":"https://github.com/labbeti/aac-datasets","url":"https://aac-datasets.readthedocs.io/en/stable/","frameworks":["pytorch"]}],"num_papers_in_archive":202,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-audio-retrieval-on-clotho","task":"Text to Audio Retrieval","dataset_variant":"Clotho","rows":12,"metrics":["R@1","R@5","R@10","mAP@10"],"first_row_in_archive_order":{"model":"PaSST-RoBERTa & Estimated Audio–Caption Correspondences","paper":"/paper/estimated-audio-caption-correspondences","metrics":{"R@1":"27.69","R@10":"70.39","R@5":"57.03","mAP@10":"40.14"},"code_links":[{"title":"optimusprimus/salsa","url":"https://github.com/optimusprimus/salsa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/audio-captioning-on-clotho","task":"Audio captioning","dataset_variant":"Clotho","rows":11,"metrics":["SPIDEr","CIDEr","SPICE","BLEU-4","METEOR","ROUGE-L","FENSE","SPIDEr-FL","Sentence-BERT"],"first_row_in_archive_order":{"model":"SLAM-AAC","paper":"/paper/slam-aac-enhancing-audio-captioning-with","metrics":{"CIDEr":"0.515","FENSE":"0.540","METEOR":"0.197","SPICE":"0.148","SPIDEr":"0.332","SPIDEr-FL":"0.330"},"code_links":[{"title":"X-LANCE/SLAM-LLM","url":"https://github.com/X-LANCE/SLAM-LLM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-audio-captioning-on-clotho","task":"Zero-shot Audio Captioning","dataset_variant":"Clotho","rows":1,"metrics":["METEOR","BLEU-4","CIDEr","ROUGE-L","SPICE","SPIDEr"],"first_row_in_archive_order":{"model":"ZerAuCap","paper":"/paper/zero-shot-audio-captioning-with-audio","metrics":{"BLEU-4":"2.9","CIDEr":"14","METEOR":"9.4","ROUGE-L":"25.4","SPICE":"5.3","SPIDEr":"9.7"},"code_links":[{"title":"explainableml/zeraucap","url":"https://github.com/explainableml/zeraucap"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","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,"shown":18,"of":18,"counts":{"papers_with_a_benchmark_row":18,"with_a_code_link":14,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":18,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":7,"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 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"},"items":[{"paper":"/paper/audio-captioning-via-generative-pair-to-pair","slug":"audio-captioning-via-generative-pair-to-pair","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","date":"2024-10-14","arxiv_id":"2410.10913","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/slam-aac-enhancing-audio-captioning-with","slug":"slam-aac-enhancing-audio-captioning-with","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","date":"2024-10-12","arxiv_id":"2410.09503","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"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":1,"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/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"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":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}}}},{"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":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"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":9,"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/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":"2026-10-05T00:36:11+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/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/the-dcase-2021-challenge-task-6-system","slug":"the-dcase-2021-challenge-task-6-system","title":"THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS","date":"2021-07-06","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-sjtu-system-for-dcase2021-challenge-task","slug":"the-sjtu-system-for-dcase2021-challenge-task","title":"THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNING","date":"2021-07-06","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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"}}}},{"paper":"/paper/the-ntt-dcase2020-challenge-task-6-system","slug":"the-ntt-dcase2020-challenge-task-6-system","title":"The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation","date":"2020-07-01","arxiv_id":"2007.00225","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/audio-captioning-using-gated-recurrent-units","slug":"audio-captioning-using-gated-recurrent-units","title":"Audio Captioning using Gated Recurrent Units","date":"2020-06-05","arxiv_id":"2006.03391","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/audio-captioning-via-generative-pair-to-pair","slug":"audio-captioning-via-generative-pair-to-pair","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","date":"2024-10-14","arxiv_id":"2410.10913","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/slam-aac-enhancing-audio-captioning-with","slug":"slam-aac-enhancing-audio-captioning-with","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","date":"2024-10-12","arxiv_id":"2410.09503","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"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":1,"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/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"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":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}}}},{"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":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"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":9,"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/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":"2026-10-05T00:36:11+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/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/the-dcase-2021-challenge-task-6-system","slug":"the-dcase-2021-challenge-task-6-system","title":"THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS","date":"2021-07-06","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-sjtu-system-for-dcase2021-challenge-task","slug":"the-sjtu-system-for-dcase2021-challenge-task","title":"THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNING","date":"2021-07-06","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+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"}}}},{"paper":"/paper/the-ntt-dcase2020-challenge-task-6-system","slug":"the-ntt-dcase2020-challenge-task-6-system","title":"The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation","date":"2020-07-01","arxiv_id":"2007.00225","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/audio-captioning-using-gated-recurrent-units","slug":"audio-captioning-using-gated-recurrent-units","title":"Audio Captioning using Gated Recurrent Units","date":"2020-06-05","arxiv_id":"2006.03391","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/dataset/clotho/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/clotho/papers/ran/1","json":"/dataset/clotho/papers/ran/1.json","rows":7}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":7,"samples_harvested":88,"samples_ran":68,"samples_constructed":6,"samples_ran_checked":51,"samples_ran_instrument_failed":17,"samples_unverified":20,"pointer_only_for_licence":37,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":7,"papers_with_a_run_with_no_instrument_failure":7,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"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)"},"since_archive_judged":{"papers":3,"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/audio-captioning-on-clotho","since_archive":"/sota/audio-captioning-on-clotho#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"c207e298e03d727055fa8e513912d0119512602fed3f4f379ffd285307916a58","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}