{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:URLZYK6LTH4FMIXOWZ346PZSUX","short_pith_number":"pith:URLZYK6L","schema_version":"1.0","canonical_sha256":"a4579c2bcb99f85622eeb677cf3f32a5c325fcd9c811e1d988d9791334eabc8a","source":{"kind":"arxiv","id":"2209.09967","version":3},"attestation_state":"computed","paper":{"title":"Language-based Audio Retrieval Task in DCASE 2022 Challenge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Huang Xie, Samuel Lipping, Tuomas Virtanen","submitted_at":"2022-09-20T19:51:53Z","abstract_excerpt":"Language-based audio retrieval is a task, where natural language textual captions are used as queries to retrieve audio signals from a dataset. It has been first introduced into DCASE 2022 Challenge as Subtask 6B of task 6, which aims at developing computational systems to model relationships between audio signals and free-form textual descriptions. Compared with audio captioning (Subtask 6A), which is about generating audio captions for audio signals, language-based audio retrieval (Subtask 6B) focuses on ranking audio signals according to their relevance to natural language textual captions."},"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":"2209.09967","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-20T19:51:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8ec81aa56260a90bf5415efe9ae37a0ee8597ddf01a85c7f98faecb3fb835fb6","abstract_canon_sha256":"5f6bedca97ebf1fd0886661cb3dc51307b6138abdd28d6be90a81b117de9b385"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:06.386500Z","signature_b64":"8/0PKV6ZGI1Z9wnbT43IUF6hr7CSYNTX1kyp4UFFJWa+3jYdt3kDCmuh6bUXoV/IwuKaoiwntQFzq+agFOG3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4579c2bcb99f85622eeb677cf3f32a5c325fcd9c811e1d988d9791334eabc8a","last_reissued_at":"2026-07-05T05:03:06.386041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:06.386041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-based Audio Retrieval Task in DCASE 2022 Challenge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Huang Xie, Samuel Lipping, Tuomas Virtanen","submitted_at":"2022-09-20T19:51:53Z","abstract_excerpt":"Language-based audio retrieval is a task, where natural language textual captions are used as queries to retrieve audio signals from a dataset. It has been first introduced into DCASE 2022 Challenge as Subtask 6B of task 6, which aims at developing computational systems to model relationships between audio signals and free-form textual descriptions. Compared with audio captioning (Subtask 6A), which is about generating audio captions for audio signals, language-based audio retrieval (Subtask 6B) focuses on ranking audio signals according to their relevance to natural language textual captions."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09967","kind":"arxiv","version":3},"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/2209.09967/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":"2209.09967","created_at":"2026-07-05T05:03:06.386097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09967v3","created_at":"2026-07-05T05:03:06.386097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09967","created_at":"2026-07-05T05:03:06.386097+00:00"},{"alias_kind":"pith_short_12","alias_value":"URLZYK6LTH4F","created_at":"2026-07-05T05:03:06.386097+00:00"},{"alias_kind":"pith_short_16","alias_value":"URLZYK6LTH4FMIXO","created_at":"2026-07-05T05:03:06.386097+00:00"},{"alias_kind":"pith_short_8","alias_value":"URLZYK6L","created_at":"2026-07-05T05:03:06.386097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20914","citing_title":"Language-based Audio Retrieval with Co-Attention Networks","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX","json":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX.json","graph_json":"https://pith.science/api/pith-number/URLZYK6LTH4FMIXOWZ346PZSUX/graph.json","events_json":"https://pith.science/api/pith-number/URLZYK6LTH4FMIXOWZ346PZSUX/events.json","paper":"https://pith.science/paper/URLZYK6L"},"agent_actions":{"view_html":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX","download_json":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX.json","view_paper":"https://pith.science/paper/URLZYK6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09967&json=true","fetch_graph":"https://pith.science/api/pith-number/URLZYK6LTH4FMIXOWZ346PZSUX/graph.json","fetch_events":"https://pith.science/api/pith-number/URLZYK6LTH4FMIXOWZ346PZSUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX/action/storage_attestation","attest_author":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX/action/author_attestation","sign_citation":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX/action/citation_signature","submit_replication":"https://pith.science/pith/URLZYK6LTH4FMIXOWZ346PZSUX/action/replication_record"}},"created_at":"2026-07-05T05:03:06.386097+00:00","updated_at":"2026-07-05T05:03:06.386097+00:00"}