{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UCLFYFY4X2223SLOOD45YDQWWB","short_pith_number":"pith:UCLFYFY4","schema_version":"1.0","canonical_sha256":"a0965c171cbeb5adc96e70f9dc0e16b04e01b86bf7ffa41ccbd001140a5298c4","source":{"kind":"arxiv","id":"1910.09387","version":1},"attestation_state":"computed","paper":{"title":"Clotho: An Audio Captioning Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Konstantinos Drossos, Samuel Lipping, Tuomas Virtanen","submitted_at":"2019-10-21T14:06:01Z","abstract_excerpt":"Audio captioning is the novel task of general audio content description using free text. It is an intermodal translation task (not speech-to-text), where a system accepts as an input an audio signal and outputs the textual description (i.e. the caption) of that signal. In this paper we present Clotho, a dataset for audio captioning consisting of 4981 audio samples of 15 to 30 seconds duration and 24 905 captions of eight to 20 words length, and a baseline method to provide initial results. Clotho is built with focus on audio content and caption diversity, and the splits of the data are not ham"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1910.09387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-10-21T14:06:01Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"b908fe943a591590cb266691ffa9992b1dd4cb005beb504296d4d73a04a9257a","abstract_canon_sha256":"4155f69be65532d014c86d74825f59d0f124cb2e6a1a0567d33bef5993303b73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:33.281547Z","signature_b64":"CL9DUXJopomMB7LvPwhYmIEIY3kG7ndZnhpDf/a1jWqQvPGr/oCOoo2BCcvjjJ6YQuMht/E0AhIalQPdpOx6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0965c171cbeb5adc96e70f9dc0e16b04e01b86bf7ffa41ccbd001140a5298c4","last_reissued_at":"2026-07-05T00:13:33.281136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:33.281136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clotho: An Audio Captioning Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Konstantinos Drossos, Samuel Lipping, Tuomas Virtanen","submitted_at":"2019-10-21T14:06:01Z","abstract_excerpt":"Audio captioning is the novel task of general audio content description using free text. It is an intermodal translation task (not speech-to-text), where a system accepts as an input an audio signal and outputs the textual description (i.e. the caption) of that signal. In this paper we present Clotho, a dataset for audio captioning consisting of 4981 audio samples of 15 to 30 seconds duration and 24 905 captions of eight to 20 words length, and a baseline method to provide initial results. Clotho is built with focus on audio content and caption diversity, and the splits of the data are not ham"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09387","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.09387/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1910.09387","created_at":"2026-07-05T00:13:33.281197+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.09387v1","created_at":"2026-07-05T00:13:33.281197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09387","created_at":"2026-07-05T00:13:33.281197+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCLFYFY4X222","created_at":"2026-07-05T00:13:33.281197+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCLFYFY4X2223SLO","created_at":"2026-07-05T00:13:33.281197+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCLFYFY4","created_at":"2026-07-05T00:13:33.281197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02739","citing_title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16678","citing_title":"UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB","json":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB.json","graph_json":"https://pith.science/api/pith-number/UCLFYFY4X2223SLOOD45YDQWWB/graph.json","events_json":"https://pith.science/api/pith-number/UCLFYFY4X2223SLOOD45YDQWWB/events.json","paper":"https://pith.science/paper/UCLFYFY4"},"agent_actions":{"view_html":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB","download_json":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB.json","view_paper":"https://pith.science/paper/UCLFYFY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.09387&json=true","fetch_graph":"https://pith.science/api/pith-number/UCLFYFY4X2223SLOOD45YDQWWB/graph.json","fetch_events":"https://pith.science/api/pith-number/UCLFYFY4X2223SLOOD45YDQWWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB/action/storage_attestation","attest_author":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB/action/author_attestation","sign_citation":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB/action/citation_signature","submit_replication":"https://pith.science/pith/UCLFYFY4X2223SLOOD45YDQWWB/action/replication_record"}},"created_at":"2026-07-05T00:13:33.281197+00:00","updated_at":"2026-07-05T00:13:33.281197+00:00"}