{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3CWJKC7HPK4JLMBVLKJVIQYG65","short_pith_number":"pith:3CWJKC7H","schema_version":"1.0","canonical_sha256":"d8ac950be77ab895b0355a93544306f75038152652a8c3a567c27548957e1e88","source":{"kind":"arxiv","id":"2307.12964","version":2},"attestation_state":"computed","paper":{"title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amanmeet Garg, Ashutosh Sanan, Mohamed Omar, Pichao Wang, Sarah Ibrahimi, Xiaohang Sun","submitted_at":"2023-07-24T17:43:13Z","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"},"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":"2307.12964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-24T17:43:13Z","cross_cats_sorted":[],"title_canon_sha256":"b638a8c6d13ebe5d83992970042b28067b068718fd7f9e0209666a360f3e7047","abstract_canon_sha256":"b5ff0454d021e6e8116f8c8bc985e348dd419c630720d07568e4cf2169208e0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:31.592949Z","signature_b64":"YGEm6aX76DZStxuaLSJrW59MksTJlZVl4rep6miEc+HXAN+Uhxqj/ov0Hy5Hmt56ypmUn7/zpjZB8PSeREDSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8ac950be77ab895b0355a93544306f75038152652a8c3a567c27548957e1e88","last_reissued_at":"2026-07-05T07:02:31.592515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:31.592515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amanmeet Garg, Ashutosh Sanan, Mohamed Omar, Pichao Wang, Sarah Ibrahimi, Xiaohang Sun","submitted_at":"2023-07-24T17:43:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12964","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/2307.12964/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":"2307.12964","created_at":"2026-07-05T07:02:31.592594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12964v2","created_at":"2026-07-05T07:02:31.592594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12964","created_at":"2026-07-05T07:02:31.592594+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CWJKC7HPK4J","created_at":"2026-07-05T07:02:31.592594+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CWJKC7HPK4JLMBV","created_at":"2026-07-05T07:02:31.592594+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CWJKC7H","created_at":"2026-07-05T07:02:31.592594+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/3CWJKC7HPK4JLMBVLKJVIQYG65","json":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65.json","graph_json":"https://pith.science/api/pith-number/3CWJKC7HPK4JLMBVLKJVIQYG65/graph.json","events_json":"https://pith.science/api/pith-number/3CWJKC7HPK4JLMBVLKJVIQYG65/events.json","paper":"https://pith.science/paper/3CWJKC7H"},"agent_actions":{"view_html":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65","download_json":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65.json","view_paper":"https://pith.science/paper/3CWJKC7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12964&json=true","fetch_graph":"https://pith.science/api/pith-number/3CWJKC7HPK4JLMBVLKJVIQYG65/graph.json","fetch_events":"https://pith.science/api/pith-number/3CWJKC7HPK4JLMBVLKJVIQYG65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65/action/storage_attestation","attest_author":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65/action/author_attestation","sign_citation":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65/action/citation_signature","submit_replication":"https://pith.science/pith/3CWJKC7HPK4JLMBVLKJVIQYG65/action/replication_record"}},"created_at":"2026-07-05T07:02:31.592594+00:00","updated_at":"2026-07-05T07:02:31.592594+00:00"}