{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W3L65D5SL5R46JSPFIMWQSW4RJ","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":"8a88eedcb0c30c158d426ac7f5e58843c106962512f2b5f449032fee808a5a45","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:50:23Z","title_canon_sha256":"e0b5cc64c00f696e1aba64d987c9e9a978cbb66a30f417952a39439591a34354"},"schema_version":"1.0","source":{"id":"2410.23266","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23266","created_at":"2026-07-05T11:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23266v2","created_at":"2026-07-05T11:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23266","created_at":"2026-07-05T11:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"W3L65D5SL5R4","created_at":"2026-07-05T11:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"W3L65D5SL5R46JSP","created_at":"2026-07-05T11:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"W3L65D5S","created_at":"2026-07-05T11:58:21Z"}],"graph_snapshots":[{"event_id":"sha256:515dd75b9aa242322a638b7091dcd957cd2fd35a7356283dd574173d0bf49925","target":"graph","created_at":"2026-07-05T11:58:21Z","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/2410.23266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing benchmarks often highlight the remarkable performance achieved by state-of-the-art Multimodal Foundation Models (MFMs) in leveraging temporal context for video understanding. However, how well do the models truly perform visual temporal reasoning? Our study of existing benchmarks shows that this capability of MFMs is likely overestimated as many questions can be solved by using a single, few, or out-of-order frames. To systematically examine current visual temporal reasoning tasks, we propose three principles with corresponding metrics: (1) Multi-Frame Gain, (2) Frame Order Sensitivit","authors_text":"Arman Cohan, Chuhan Li, Tesca FItzgerald, Yanan Zheng, Yilun Zhao, Yuxuan Ding, Ziyao Shangguan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:50:23Z","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23266","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:b65b2b1e60f09327a38b8901fcddd60961f60beac929f7fc5588bf40535b9ba3","target":"record","created_at":"2026-07-05T11:58:21Z","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":"8a88eedcb0c30c158d426ac7f5e58843c106962512f2b5f449032fee808a5a45","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:50:23Z","title_canon_sha256":"e0b5cc64c00f696e1aba64d987c9e9a978cbb66a30f417952a39439591a34354"},"schema_version":"1.0","source":{"id":"2410.23266","kind":"arxiv","version":2}},"canonical_sha256":"b6d7ee8fb25f63cf264f2a19684adc8a4d9e86fbb32d91fd6f8f5e9fce753e20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6d7ee8fb25f63cf264f2a19684adc8a4d9e86fbb32d91fd6f8f5e9fce753e20","first_computed_at":"2026-07-05T11:58:21.516136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:21.516136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9CZUmUBRADkdZq0FsrnqasCa4MwEArQo1oEkKcck1y33lyN4ekNY3FLTBfn+tm+gvSLmVIUNsRArYrCSoG+HBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:21.516634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23266","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b65b2b1e60f09327a38b8901fcddd60961f60beac929f7fc5588bf40535b9ba3","sha256:515dd75b9aa242322a638b7091dcd957cd2fd35a7356283dd574173d0bf49925"],"state_sha256":"0474821fd7a39720605fe4ece84c0472b3eebbbf0184dfff2fba853d2ae22cc3"}