{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FIW725XNTOE4TSXVCIO7EYVYKH","short_pith_number":"pith:FIW725XN","schema_version":"1.0","canonical_sha256":"2a2dfd76ed9b89c9caf5121df262b851f561b877af75b9278c476c39fdefcbc9","source":{"kind":"arxiv","id":"2309.02290","version":1},"attestation_state":"computed","paper":{"title":"ATM: Action Temporality Modeling for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhu, Junwen Chen, Yu Kong","submitted_at":"2023-09-05T14:52:38Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.02290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T14:52:38Z","cross_cats_sorted":[],"title_canon_sha256":"36af9dac81a6a7615855ca6af8d4987dd7947d81d10770fd6f742cf056348582","abstract_canon_sha256":"18739517d86038e12dd6d8abccb9b84261cd96521cef46d0e257281328a9a761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:58.342765Z","signature_b64":"toUUZzwtsV10VaBWYZ/pbjfFdAKqecvITOwI1HBuS+YoawJYHQ75Te4gOQuS8g5mx8nCLhB4E5PGU8XSzk36Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a2dfd76ed9b89c9caf5121df262b851f561b877af75b9278c476c39fdefcbc9","last_reissued_at":"2026-07-05T06:47:58.342338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:58.342338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ATM: Action Temporality Modeling for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhu, Junwen Chen, Yu Kong","submitted_at":"2023-09-05T14:52:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02290","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.02290/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.02290","created_at":"2026-07-05T06:47:58.342403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02290v1","created_at":"2026-07-05T06:47:58.342403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02290","created_at":"2026-07-05T06:47:58.342403+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIW725XNTOE4","created_at":"2026-07-05T06:47:58.342403+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIW725XNTOE4TSXV","created_at":"2026-07-05T06:47:58.342403+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIW725XN","created_at":"2026-07-05T06:47:58.342403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH","json":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH.json","graph_json":"https://pith.science/api/pith-number/FIW725XNTOE4TSXVCIO7EYVYKH/graph.json","events_json":"https://pith.science/api/pith-number/FIW725XNTOE4TSXVCIO7EYVYKH/events.json","paper":"https://pith.science/paper/FIW725XN"},"agent_actions":{"view_html":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH","download_json":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH.json","view_paper":"https://pith.science/paper/FIW725XN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02290&json=true","fetch_graph":"https://pith.science/api/pith-number/FIW725XNTOE4TSXVCIO7EYVYKH/graph.json","fetch_events":"https://pith.science/api/pith-number/FIW725XNTOE4TSXVCIO7EYVYKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH/action/storage_attestation","attest_author":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH/action/author_attestation","sign_citation":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH/action/citation_signature","submit_replication":"https://pith.science/pith/FIW725XNTOE4TSXVCIO7EYVYKH/action/replication_record"}},"created_at":"2026-07-05T06:47:58.342403+00:00","updated_at":"2026-07-05T06:47:58.342403+00:00"}