{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7KHFULI4OLENU2FSU32JCEZO54","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":"d88d464cc8475fa47bbe1b7a5a3946b315b238231fb824e7de025ec01f81cfd9","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-16T08:43:17Z","title_canon_sha256":"6c1e4bc0b999aedf3a56fd2cfd4d27d184beacf79e046117ff7c245b1265ee30"},"schema_version":"1.0","source":{"id":"2301.06309","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.06309","created_at":"2026-07-05T06:42:41Z"},{"alias_kind":"arxiv_version","alias_value":"2301.06309v2","created_at":"2026-07-05T06:42:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06309","created_at":"2026-07-05T06:42:41Z"},{"alias_kind":"pith_short_12","alias_value":"7KHFULI4OLEN","created_at":"2026-07-05T06:42:41Z"},{"alias_kind":"pith_short_16","alias_value":"7KHFULI4OLENU2FS","created_at":"2026-07-05T06:42:41Z"},{"alias_kind":"pith_short_8","alias_value":"7KHFULI4","created_at":"2026-07-05T06:42:41Z"}],"graph_snapshots":[{"event_id":"sha256:d6361a3d3ed23e9f1b8748404185c804d49ecb35acea926f4d0892bb81f8c123","target":"graph","created_at":"2026-07-05T06:42:41Z","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/2301.06309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Bo Fang, Chang Liu, Jingdong Wang, Weiping Wang, Wenhao Wu, Xiangbo Shu, Xiangyang Ji, Yuxin Song, Yu Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-16T08:43:17Z","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06309","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":"sha256:9f627575e49d5c20316d27d9ab40b0e5f8a6084fa998b03eea11318adca533fe","target":"record","created_at":"2026-07-05T06:42:41Z","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":"d88d464cc8475fa47bbe1b7a5a3946b315b238231fb824e7de025ec01f81cfd9","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-16T08:43:17Z","title_canon_sha256":"6c1e4bc0b999aedf3a56fd2cfd4d27d184beacf79e046117ff7c245b1265ee30"},"schema_version":"1.0","source":{"id":"2301.06309","kind":"arxiv","version":2}},"canonical_sha256":"fa8e5a2d1c72c8da68b2a6f491132eef203f27d744d91f8736e73770e6b9e66a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa8e5a2d1c72c8da68b2a6f491132eef203f27d744d91f8736e73770e6b9e66a","first_computed_at":"2026-07-05T06:42:41.946524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:41.946524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LT9Qu1EQHgF2lmLDf13xQ1+VSWXqABEDAYyj79AMsn6K0HS+kkhU5fhzEXfAywXAqHR/5B1F2JkQtmBqW0sgDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:41.946984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.06309","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f627575e49d5c20316d27d9ab40b0e5f8a6084fa998b03eea11318adca533fe","sha256:d6361a3d3ed23e9f1b8748404185c804d49ecb35acea926f4d0892bb81f8c123"],"state_sha256":"68e851c01adb35825868bb376b0125fecafa83901132ae8316ac29b462736a2d"}