{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3CWJKC7HPK4JLMBVLKJVIQYG65","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":"b5ff0454d021e6e8116f8c8bc985e348dd419c630720d07568e4cf2169208e0f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:43:13Z","title_canon_sha256":"b638a8c6d13ebe5d83992970042b28067b068718fd7f9e0209666a360f3e7047"},"schema_version":"1.0","source":{"id":"2307.12964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12964","created_at":"2026-07-05T07:02:31Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12964v2","created_at":"2026-07-05T07:02:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12964","created_at":"2026-07-05T07:02:31Z"},{"alias_kind":"pith_short_12","alias_value":"3CWJKC7HPK4J","created_at":"2026-07-05T07:02:31Z"},{"alias_kind":"pith_short_16","alias_value":"3CWJKC7HPK4JLMBV","created_at":"2026-07-05T07:02:31Z"},{"alias_kind":"pith_short_8","alias_value":"3CWJKC7H","created_at":"2026-07-05T07:02:31Z"}],"graph_snapshots":[{"event_id":"sha256:cf5f95929622c034715a3f71f41854cacb34edff7756f8f4487d6c29b3b170f6","target":"graph","created_at":"2026-07-05T07:02:31Z","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/2307.12964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video retrieval systems have recently made significant progress by utilizing pre-trained models trained on large-scale image-text pairs. However, most of the latest methods primarily focus on the video modality while disregarding the audio signal for this task. Nevertheless, a recent advancement by ECLIPSE has improved long-range text-to-video retrieval by developing an audiovisual video representation. Nonetheless, the objective of the text-to-video retrieval task is to capture the complementary audio and video information that is pertinent to the text query rather than simply achievi","authors_text":"Amanmeet Garg, Ashutosh Sanan, Mohamed Omar, Pichao Wang, Sarah Ibrahimi, Xiaohang Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:43:13Z","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12964","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":"sha256:73730be29d9465ceeffc1895c114d2fda34a16701306abb59e33721faff7e1c7","target":"record","created_at":"2026-07-05T07:02:31Z","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":"b5ff0454d021e6e8116f8c8bc985e348dd419c630720d07568e4cf2169208e0f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:43:13Z","title_canon_sha256":"b638a8c6d13ebe5d83992970042b28067b068718fd7f9e0209666a360f3e7047"},"schema_version":"1.0","source":{"id":"2307.12964","kind":"arxiv","version":2}},"canonical_sha256":"d8ac950be77ab895b0355a93544306f75038152652a8c3a567c27548957e1e88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8ac950be77ab895b0355a93544306f75038152652a8c3a567c27548957e1e88","first_computed_at":"2026-07-05T07:02:31.592515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:31.592515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YGEm6aX76DZStxuaLSJrW59MksTJlZVl4rep6miEc+HXAN+Uhxqj/ov0Hy5Hmt56ypmUn7/zpjZB8PSeREDSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:31.592949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73730be29d9465ceeffc1895c114d2fda34a16701306abb59e33721faff7e1c7","sha256:cf5f95929622c034715a3f71f41854cacb34edff7756f8f4487d6c29b3b170f6"],"state_sha256":"70087bd076ae10f1730bde7e50e99a6b2525a8b6cfcfc74fdfed8bf2b47dfbd0"}