{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YLW4N3XRHRI2LF4LFHSZRIRKJX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"36aed3e749fe3211b51fc12b71126dda5a757d449185c3aa1ea18c33ab96f0c4","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-25T13:41:17Z","title_canon_sha256":"23852c693cc050fa02b0f5783b710396795e32099eb049e3e0f0e1729c23e891"},"schema_version":"1.0","source":{"id":"2203.13645","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13645","created_at":"2026-07-05T04:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13645v2","created_at":"2026-07-05T04:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13645","created_at":"2026-07-05T04:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"YLW4N3XRHRI2","created_at":"2026-07-05T04:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"YLW4N3XRHRI2LF4L","created_at":"2026-07-05T04:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"YLW4N3XR","created_at":"2026-07-05T04:09:19Z"}],"graph_snapshots":[{"event_id":"sha256:a27a989a773c76f08699aa14988c8d9fca2cfdc5759cfdd6115d4836249ec82d","target":"graph","created_at":"2026-07-05T04:09:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.13645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kai Yu, Mengyue Wu, Siyu Lou, Xuenan Xu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-25T13:41:17Z","title":"Audio-text Retrieval in Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13645","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f8b02823283471880403c517128b79390b8fdcc3292a796582976e8508e46a5a","target":"record","created_at":"2026-07-05T04:09:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"36aed3e749fe3211b51fc12b71126dda5a757d449185c3aa1ea18c33ab96f0c4","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-25T13:41:17Z","title_canon_sha256":"23852c693cc050fa02b0f5783b710396795e32099eb049e3e0f0e1729c23e891"},"schema_version":"1.0","source":{"id":"2203.13645","kind":"arxiv","version":2}},"canonical_sha256":"c2edc6eef13c51a5978b29e598a22a4dca75b01dc702dd1c751866335b56b642","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2edc6eef13c51a5978b29e598a22a4dca75b01dc702dd1c751866335b56b642","first_computed_at":"2026-07-05T04:09:19.918671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:19.918671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ybw9Wdt67QJ3W9Pfx7qMjGV468uwN+toogJdG7yi+6shqlPJi7VVcOMOelgHAPj7kuVNAhKwo+lIGXLV072DAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:19.919051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.13645","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8b02823283471880403c517128b79390b8fdcc3292a796582976e8508e46a5a","sha256:a27a989a773c76f08699aa14988c8d9fca2cfdc5759cfdd6115d4836249ec82d"],"state_sha256":"ebe9ca01d8ff7492fc59ea340a5064ccb45b6431a76fb5254295ecc79205ea3f"}