{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YLW4N3XRHRI2LF4LFHSZRIRKJX","short_pith_number":"pith:YLW4N3XR","schema_version":"1.0","canonical_sha256":"c2edc6eef13c51a5978b29e598a22a4dca75b01dc702dd1c751866335b56b642","source":{"kind":"arxiv","id":"2203.13645","version":2},"attestation_state":"computed","paper":{"title":"Audio-text Retrieval in Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Yu, Mengyue Wu, Siyu Lou, Xuenan Xu","submitted_at":"2022-03-25T13:41:17Z","abstract_excerpt":"Audio-text retrieval based on natural language descriptions is a challenging task. It involves learning cross-modality alignments between long sequences under inadequate data conditions. In this work, we investigate several audio features as well as sequence aggregation methods for better audio-text alignment. Moreover, through a qualitative analysis we observe that semantic mapping is more important than temporal relations in contextual retrieval. Using pre-trained audio features and a descriptor-based aggregation method, we build our contextual audio-text retrieval system. Specifically, we u"},"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":"2203.13645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-25T13:41:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"23852c693cc050fa02b0f5783b710396795e32099eb049e3e0f0e1729c23e891","abstract_canon_sha256":"36aed3e749fe3211b51fc12b71126dda5a757d449185c3aa1ea18c33ab96f0c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:19.919051Z","signature_b64":"Ybw9Wdt67QJ3W9Pfx7qMjGV468uwN+toogJdG7yi+6shqlPJi7VVcOMOelgHAPj7kuVNAhKwo+lIGXLV072DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2edc6eef13c51a5978b29e598a22a4dca75b01dc702dd1c751866335b56b642","last_reissued_at":"2026-07-05T04:09:19.918671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:19.918671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-text Retrieval in Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Yu, Mengyue Wu, Siyu Lou, Xuenan Xu","submitted_at":"2022-03-25T13:41:17Z","abstract_excerpt":"Audio-text retrieval based on natural language descriptions is a challenging task. It involves learning cross-modality alignments between long sequences under inadequate data conditions. In this work, we investigate several audio features as well as sequence aggregation methods for better audio-text alignment. Moreover, through a qualitative analysis we observe that semantic mapping is more important than temporal relations in contextual retrieval. Using pre-trained audio features and a descriptor-based aggregation method, we build our contextual audio-text retrieval system. Specifically, we u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13645","kind":"arxiv","version":2},"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/2203.13645/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":"2203.13645","created_at":"2026-07-05T04:09:19.918728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13645v2","created_at":"2026-07-05T04:09:19.918728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13645","created_at":"2026-07-05T04:09:19.918728+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLW4N3XRHRI2","created_at":"2026-07-05T04:09:19.918728+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLW4N3XRHRI2LF4L","created_at":"2026-07-05T04:09:19.918728+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLW4N3XR","created_at":"2026-07-05T04:09:19.918728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX","json":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX.json","graph_json":"https://pith.science/api/pith-number/YLW4N3XRHRI2LF4LFHSZRIRKJX/graph.json","events_json":"https://pith.science/api/pith-number/YLW4N3XRHRI2LF4LFHSZRIRKJX/events.json","paper":"https://pith.science/paper/YLW4N3XR"},"agent_actions":{"view_html":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX","download_json":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX.json","view_paper":"https://pith.science/paper/YLW4N3XR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13645&json=true","fetch_graph":"https://pith.science/api/pith-number/YLW4N3XRHRI2LF4LFHSZRIRKJX/graph.json","fetch_events":"https://pith.science/api/pith-number/YLW4N3XRHRI2LF4LFHSZRIRKJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX/action/storage_attestation","attest_author":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX/action/author_attestation","sign_citation":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX/action/citation_signature","submit_replication":"https://pith.science/pith/YLW4N3XRHRI2LF4LFHSZRIRKJX/action/replication_record"}},"created_at":"2026-07-05T04:09:19.918728+00:00","updated_at":"2026-07-05T04:09:19.918728+00:00"}