{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CLHNQSQTCQ56JBXRF62NFDXSA7","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":"42bec73ed480f1c5d42322742d4985af03c0465920469c8f17ed98ff65a429f8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-20T07:43:00Z","title_canon_sha256":"cb3e35aca657396afdeb87e2bed6b06b901147b39bac5b87d010f74a447595d6"},"schema_version":"1.0","source":{"id":"2010.10095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10095","created_at":"2026-07-05T01:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10095v1","created_at":"2026-07-05T01:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10095","created_at":"2026-07-05T01:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"CLHNQSQTCQ56","created_at":"2026-07-05T01:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"CLHNQSQTCQ56JBXR","created_at":"2026-07-05T01:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"CLHNQSQT","created_at":"2026-07-05T01:44:27Z"}],"graph_snapshots":[{"event_id":"sha256:d70b0618d11d56fe3ab1d1c5c04b6245e5d00813d97b971c8252e5681907f83c","target":"graph","created_at":"2026-07-05T01:44:27Z","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/2010.10095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-grounded dialogues are very challenging due to (i) the complexity of videos which contain both spatial and temporal variations, and (ii) the complexity of user utterances which query different segments and/or different objects in videos over multiple dialogue turns. However, existing approaches to video-grounded dialogues often focus on superficial temporal-level visual cues, but neglect more fine-grained spatial signals from videos. To address this drawback, we propose Bi-directional Spatio-Temporal Learning (BiST), a vision-language neural framework for high-resolution queries in video","authors_text":"Doyen Sahoo, Hung Le, Nancy F. Chen, Steven C.H. Hoi","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-20T07:43:00Z","title":"BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10095","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:b2aabe9f49c2f52713db2b102449bbddd0fca2f60762c14b00a1919b7c2811fc","target":"record","created_at":"2026-07-05T01:44:27Z","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":"42bec73ed480f1c5d42322742d4985af03c0465920469c8f17ed98ff65a429f8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-20T07:43:00Z","title_canon_sha256":"cb3e35aca657396afdeb87e2bed6b06b901147b39bac5b87d010f74a447595d6"},"schema_version":"1.0","source":{"id":"2010.10095","kind":"arxiv","version":1}},"canonical_sha256":"12ced84a13143be486f12fb4d28ef207f79c8f0ce5d5fc71d2b567bb69c94fd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ced84a13143be486f12fb4d28ef207f79c8f0ce5d5fc71d2b567bb69c94fd9","first_computed_at":"2026-07-05T01:44:27.132546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:27.132546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sEfbMLo/CX0UaWiADdNcoPvzXsDP+CppXwHEl3FUnATLdmbpzHufPuOODCAy6mHKthLHMwveBozYXm4L8qBRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:27.132969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.10095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2aabe9f49c2f52713db2b102449bbddd0fca2f60762c14b00a1919b7c2811fc","sha256:d70b0618d11d56fe3ab1d1c5c04b6245e5d00813d97b971c8252e5681907f83c"],"state_sha256":"a45487a5285cc6d12daa3a6205fca8cc04a21c13417de67a3b588a69298f68e2"}