{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CSFTUU4P57IQNIKF6YQSK7MXE4","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":"e52e33490688e57ffbeb4e6540a5173eb42bf77548a8d4f3826ffd89859fcd37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T12:52:32Z","title_canon_sha256":"5c88ab278f38074b61e3af4b49446bab865e75f3213d0a40b630544f09549e89"},"schema_version":"1.0","source":{"id":"2407.11677","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11677","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11677v2","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11677","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"CSFTUU4P57IQ","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"pith_short_16","alias_value":"CSFTUU4P57IQNIKF","created_at":"2026-07-05T08:47:54Z"},{"alias_kind":"pith_short_8","alias_value":"CSFTUU4P","created_at":"2026-07-05T08:47:54Z"}],"graph_snapshots":[{"event_id":"sha256:83071e0901439497884b36cb83bda80fa871542336ddfff88597c1abcb19f417","target":"graph","created_at":"2026-07-05T08:47:54Z","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/2407.11677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or apply global and local alignment techniques to promote alignment precision. However, these methods often fail to fully explore the spatio-temporal relationships among vision tokens within video and across different video-text pairs. In this paper, we propose a novel Spatio-Temporal Graph Transformer module to uniformly learn spatial and temporal contexts for v","authors_text":"Chun Yang, Hongfa Wang, Shi-Xue Zhang, Tianjin Zhang, Weibo Gu, Wei Liu, Xiaobin Zhu, Xu-Cheng Yin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T12:52:32Z","title":"Video-Language Alignment via Spatio-Temporal Graph Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11677","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:b4e6bb5c66ee0f8342290b2e3b9c54c0511137a60a082820cc69423473c3837e","target":"record","created_at":"2026-07-05T08:47:54Z","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":"e52e33490688e57ffbeb4e6540a5173eb42bf77548a8d4f3826ffd89859fcd37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T12:52:32Z","title_canon_sha256":"5c88ab278f38074b61e3af4b49446bab865e75f3213d0a40b630544f09549e89"},"schema_version":"1.0","source":{"id":"2407.11677","kind":"arxiv","version":2}},"canonical_sha256":"148b3a538fefd106a145f621257d9727133eb11f8584b41ffa60d5654f64fc7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"148b3a538fefd106a145f621257d9727133eb11f8584b41ffa60d5654f64fc7d","first_computed_at":"2026-07-05T08:47:54.851656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:54.851656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9wwWbjgWF7sAFb581PfwJ1hEKtXvTyWiDi/TodMsQWUbIuraVD0slzpiiJ5Yej8ZBd+OQ8dHVnC15bNEF7/DAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:54.852079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11677","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4e6bb5c66ee0f8342290b2e3b9c54c0511137a60a082820cc69423473c3837e","sha256:83071e0901439497884b36cb83bda80fa871542336ddfff88597c1abcb19f417"],"state_sha256":"c56b92ba31c6cbd58cd76828b393c7d54e90c027a5aca40b3c8a86cb70fbbca7"}