{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:662334EJVTIP6ADUFVTTIGGQDA","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":"40ffafdddee4c3df398ad14809121e836d4ad8a0d086855a15c82b56d245c6fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-12T06:51:32Z","title_canon_sha256":"203ab1f0152b26a017f30e0319489766dad9575688ed7d2f9b00cf63cf2ec070"},"schema_version":"1.0","source":{"id":"2207.05342","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.05342","created_at":"2026-07-05T04:42:20Z"},{"alias_kind":"arxiv_version","alias_value":"2207.05342v3","created_at":"2026-07-05T04:42:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05342","created_at":"2026-07-05T04:42:20Z"},{"alias_kind":"pith_short_12","alias_value":"662334EJVTIP","created_at":"2026-07-05T04:42:20Z"},{"alias_kind":"pith_short_16","alias_value":"662334EJVTIP6ADU","created_at":"2026-07-05T04:42:20Z"},{"alias_kind":"pith_short_8","alias_value":"662334EJ","created_at":"2026-07-05T04:42:20Z"}],"graph_snapshots":[{"event_id":"sha256:9578424f86cb99aae3dfc6e631b2f39e33e44e5b7ab547e1f97a15349b25c5d4","target":"graph","created_at":"2026-07-05T04:42:20Z","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/2207.05342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT's uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal reasoning; and 2) it exploits disentangled video and text Transformers for relevance comparison between the video and text to perform QA, instead of entangled cross-modal Transformer for answer classification. Vision-text communication is done by additional cross-modal interaction modules. With more ","authors_text":"Junbin Xiao, Pan Zhou, Shuicheng Yan, Tat-Seng Chua","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-12T06:51:32Z","title":"Video Graph Transformer for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05342","kind":"arxiv","version":3},"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":"sha256:59ba25ac28417d78f6709946b069e7e3809d8e551691809494c4a8aad530d3a3","target":"record","created_at":"2026-07-05T04:42:20Z","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":"40ffafdddee4c3df398ad14809121e836d4ad8a0d086855a15c82b56d245c6fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-12T06:51:32Z","title_canon_sha256":"203ab1f0152b26a017f30e0319489766dad9575688ed7d2f9b00cf63cf2ec070"},"schema_version":"1.0","source":{"id":"2207.05342","kind":"arxiv","version":3}},"canonical_sha256":"f7b5bdf089acd0ff00742d673418d01821bec8aad753b9fd4678429e4015d63f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7b5bdf089acd0ff00742d673418d01821bec8aad753b9fd4678429e4015d63f","first_computed_at":"2026-07-05T04:42:20.495163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:20.495163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ju6jfBptP7jwPeD6vQXOOuEK+n9aqhyCfXWygKIfDbRQFrSbOILth7yBKY9o3qzSkFCAVIT68Kr4i7vMQMdYCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:20.495661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.05342","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59ba25ac28417d78f6709946b069e7e3809d8e551691809494c4a8aad530d3a3","sha256:9578424f86cb99aae3dfc6e631b2f39e33e44e5b7ab547e1f97a15349b25c5d4"],"state_sha256":"37773f55ba8e2a26ea601ce340618ea3e6ccfb23bd63b0ef75c72f754740811d"}