{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7KHFULI4OLENU2FSU32JCEZO54","short_pith_number":"pith:7KHFULI4","schema_version":"1.0","canonical_sha256":"fa8e5a2d1c72c8da68b2a6f491132eef203f27d744d91f8736e73770e6b9e66a","source":{"kind":"arxiv","id":"2301.06309","version":2},"attestation_state":"computed","paper":{"title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Fang, Chang Liu, Jingdong Wang, Weiping Wang, Wenhao Wu, Xiangbo Shu, Xiangyang Ji, Yuxin Song, Yu Zhou","submitted_at":"2023-01-16T08:43:17Z","abstract_excerpt":"With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities in specific granularities for semantic correspondence. Unfortunately, the intrinsic uncertainties of optimal entity combinations in appropriate granularities for cross-modal queries are understudied, which is especially critical for modalities with hierarchical "},"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":"2301.06309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-16T08:43:17Z","cross_cats_sorted":[],"title_canon_sha256":"6c1e4bc0b999aedf3a56fd2cfd4d27d184beacf79e046117ff7c245b1265ee30","abstract_canon_sha256":"d88d464cc8475fa47bbe1b7a5a3946b315b238231fb824e7de025ec01f81cfd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:41.946984Z","signature_b64":"LT9Qu1EQHgF2lmLDf13xQ1+VSWXqABEDAYyj79AMsn6K0HS+kkhU5fhzEXfAywXAqHR/5B1F2JkQtmBqW0sgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa8e5a2d1c72c8da68b2a6f491132eef203f27d744d91f8736e73770e6b9e66a","last_reissued_at":"2026-07-05T06:42:41.946524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:41.946524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Fang, Chang Liu, Jingdong Wang, Weiping Wang, Wenhao Wu, Xiangbo Shu, Xiangyang Ji, Yuxin Song, Yu Zhou","submitted_at":"2023-01-16T08:43:17Z","abstract_excerpt":"With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities in specific granularities for semantic correspondence. Unfortunately, the intrinsic uncertainties of optimal entity combinations in appropriate granularities for cross-modal queries are understudied, which is especially critical for modalities with hierarchical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06309","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/2301.06309/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":"2301.06309","created_at":"2026-07-05T06:42:41.946578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06309v2","created_at":"2026-07-05T06:42:41.946578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06309","created_at":"2026-07-05T06:42:41.946578+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KHFULI4OLEN","created_at":"2026-07-05T06:42:41.946578+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KHFULI4OLENU2FS","created_at":"2026-07-05T06:42:41.946578+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KHFULI4","created_at":"2026-07-05T06:42:41.946578+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/7KHFULI4OLENU2FSU32JCEZO54","json":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54.json","graph_json":"https://pith.science/api/pith-number/7KHFULI4OLENU2FSU32JCEZO54/graph.json","events_json":"https://pith.science/api/pith-number/7KHFULI4OLENU2FSU32JCEZO54/events.json","paper":"https://pith.science/paper/7KHFULI4"},"agent_actions":{"view_html":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54","download_json":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54.json","view_paper":"https://pith.science/paper/7KHFULI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06309&json=true","fetch_graph":"https://pith.science/api/pith-number/7KHFULI4OLENU2FSU32JCEZO54/graph.json","fetch_events":"https://pith.science/api/pith-number/7KHFULI4OLENU2FSU32JCEZO54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54/action/storage_attestation","attest_author":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54/action/author_attestation","sign_citation":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54/action/citation_signature","submit_replication":"https://pith.science/pith/7KHFULI4OLENU2FSU32JCEZO54/action/replication_record"}},"created_at":"2026-07-05T06:42:41.946578+00:00","updated_at":"2026-07-05T06:42:41.946578+00:00"}