{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6G23K53Z5KXQOXPFJ2DXDQXY5U","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":"4b8afa50fabdd8c96b49e8085a83fedde72dedfd4a53df85e9e312f4ecbd381c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T17:36:50Z","title_canon_sha256":"8510a3811601decc89964b7dffe9eb860c4ef269217d4ab4e11c6439768f8908"},"schema_version":"1.0","source":{"id":"2402.16769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16769","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16769v1","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16769","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_12","alias_value":"6G23K53Z5KXQ","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_16","alias_value":"6G23K53Z5KXQOXPF","created_at":"2026-07-05T07:49:26Z"},{"alias_kind":"pith_short_8","alias_value":"6G23K53Z","created_at":"2026-07-05T07:49:26Z"}],"graph_snapshots":[{"event_id":"sha256:d2cfb46d8a8c165ea2a94388ed34e37d91795aeeffd75e1f816a0172a386c40a","target":"graph","created_at":"2026-07-05T07:49:26Z","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/2402.16769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representations for videos and texts. However, they face challenges in capturing fine-grained semantic concepts. In this work, we propose the UNIFY framework, which learns lexicon representations to capture fine-grained semantics and combines the strengths of latent and lexicon representations for video-text retrieval. Specifically, we map videos and texts into a pre-defined lexicon space, where each dimension corresponds to a sem","authors_text":"Bing Li, Chenliang Li, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Qinghao Ye, Weiming Hu, Yaya Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T17:36:50Z","title":"Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16769","kind":"arxiv","version":1},"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":"sha256:25f2c01853cf5a7a809d971368b3316e9cbc0d2cc6fbe7599a72c86a93eeda63","target":"record","created_at":"2026-07-05T07:49:26Z","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":"4b8afa50fabdd8c96b49e8085a83fedde72dedfd4a53df85e9e312f4ecbd381c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T17:36:50Z","title_canon_sha256":"8510a3811601decc89964b7dffe9eb860c4ef269217d4ab4e11c6439768f8908"},"schema_version":"1.0","source":{"id":"2402.16769","kind":"arxiv","version":1}},"canonical_sha256":"f1b5b57779eaaf075de54e8771c2f8ed3330dc8fb931619d9e5837bd1dcd48d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1b5b57779eaaf075de54e8771c2f8ed3330dc8fb931619d9e5837bd1dcd48d8","first_computed_at":"2026-07-05T07:49:26.121472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:26.121472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iWo6P9LN/2dLWsb2z/7oSPw79/93Z0z8DD1CjfxW3jA2eMegHKT6qTxS4EdbXY77/KVagwCSFgoYaZkmWFuOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:26.121965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25f2c01853cf5a7a809d971368b3316e9cbc0d2cc6fbe7599a72c86a93eeda63","sha256:d2cfb46d8a8c165ea2a94388ed34e37d91795aeeffd75e1f816a0172a386c40a"],"state_sha256":"5cebb830f942d0f8cf7f1d83747e03438cef223cf051d28f6dd177f8c0444a67"}