{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FIW725XNTOE4TSXVCIO7EYVYKH","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":"18739517d86038e12dd6d8abccb9b84261cd96521cef46d0e257281328a9a761","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T14:52:38Z","title_canon_sha256":"36af9dac81a6a7615855ca6af8d4987dd7947d81d10770fd6f742cf056348582"},"schema_version":"1.0","source":{"id":"2309.02290","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02290","created_at":"2026-07-05T06:47:58Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02290v1","created_at":"2026-07-05T06:47:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02290","created_at":"2026-07-05T06:47:58Z"},{"alias_kind":"pith_short_12","alias_value":"FIW725XNTOE4","created_at":"2026-07-05T06:47:58Z"},{"alias_kind":"pith_short_16","alias_value":"FIW725XNTOE4TSXV","created_at":"2026-07-05T06:47:58Z"},{"alias_kind":"pith_short_8","alias_value":"FIW725XN","created_at":"2026-07-05T06:47:58Z"}],"graph_snapshots":[{"event_id":"sha256:746d55b596d5f119adfc8904e5d8e8b478bcfe4fc925dfe97c18ba2adb8f370e","target":"graph","created_at":"2026-07-05T06:47:58Z","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/2309.02290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress in video question answering (VideoQA), existing methods fall short of questions that require causal/temporal reasoning across frames. This can be attributed to imprecise motion representations. We introduce Action Temporality Modeling (ATM) for temporality reasoning via three-fold uniqueness: (1) rethinking the optical flow and realizing that optical flow is effective in capturing the long horizon temporality reasoning; (2) training the visual-text embedding by contrastive learning in an action-centric manner, leading to better action representations in both vision","authors_text":"Jie Zhu, Junwen Chen, Yu Kong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T14:52:38Z","title":"ATM: Action Temporality Modeling for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02290","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:c00f21d407000dce2f9f77543241c638caa47a3e4835f17ebd0b9b96dd759097","target":"record","created_at":"2026-07-05T06:47:58Z","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":"18739517d86038e12dd6d8abccb9b84261cd96521cef46d0e257281328a9a761","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T14:52:38Z","title_canon_sha256":"36af9dac81a6a7615855ca6af8d4987dd7947d81d10770fd6f742cf056348582"},"schema_version":"1.0","source":{"id":"2309.02290","kind":"arxiv","version":1}},"canonical_sha256":"2a2dfd76ed9b89c9caf5121df262b851f561b877af75b9278c476c39fdefcbc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a2dfd76ed9b89c9caf5121df262b851f561b877af75b9278c476c39fdefcbc9","first_computed_at":"2026-07-05T06:47:58.342338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:58.342338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toUUZzwtsV10VaBWYZ/pbjfFdAKqecvITOwI1HBuS+YoawJYHQ75Te4gOQuS8g5mx8nCLhB4E5PGU8XSzk36Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:58.342765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02290","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c00f21d407000dce2f9f77543241c638caa47a3e4835f17ebd0b9b96dd759097","sha256:746d55b596d5f119adfc8904e5d8e8b478bcfe4fc925dfe97c18ba2adb8f370e"],"state_sha256":"761eeaeab0ee3e95518dbe0f1f14d1d13f64515b516ac7dbe3012133478dc86f"}