{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3FN3RB6VYYSH3BNJBVFRJ2MIY","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":"7e3b252f10aa523d3db37c14322e0debf8e86309a0fdbf26efe7a2893dbbf98f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:59:58Z","title_canon_sha256":"1a0b55aac4a84872fd1349d2c1c9070324ab3cf3e438e3931daaaa79565183b2"},"schema_version":"1.0","source":{"id":"2410.02763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02763","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02763v1","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02763","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"N3FN3RB6VYYS","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"N3FN3RB6VYYSH3BN","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"N3FN3RB6","created_at":"2026-07-05T09:15:24Z"}],"graph_snapshots":[{"event_id":"sha256:556572e1581c41933a2d814b2bdf1a2b059ae418bee196b29283081fcdd54026","target":"graph","created_at":"2026-07-05T09:15:24Z","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/2410.02763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been growing sentiment recently that modern large multimodal models (LMMs) have addressed most of the key challenges related to short video comprehension. As a result, both academia and industry are gradually shifting their attention towards the more complex challenges posed by understanding long-form videos. However, is this really the case? Our studies indicate that LMMs still lack many fundamental reasoning capabilities even when dealing with short videos. We introduce Vinoground, a temporal counterfactual LMM evaluation benchmark encompassing 1000 short and natural video-caption ","authors_text":"Jianrui Zhang, Mu Cai, Yong Jae Lee","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:59:58Z","title":"Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02763","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":"sha256:630e238ef87a8a7de72daf0010e509c45b86a7e5285a81a1daa17b828ceec8f0","target":"record","created_at":"2026-07-05T09:15:24Z","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":"7e3b252f10aa523d3db37c14322e0debf8e86309a0fdbf26efe7a2893dbbf98f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:59:58Z","title_canon_sha256":"1a0b55aac4a84872fd1349d2c1c9070324ab3cf3e438e3931daaaa79565183b2"},"schema_version":"1.0","source":{"id":"2410.02763","kind":"arxiv","version":1}},"canonical_sha256":"6ecaddc43eae3123ec2d486a58a74c4633442ccf9a9e2bade329de634b045169","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ecaddc43eae3123ec2d486a58a74c4633442ccf9a9e2bade329de634b045169","first_computed_at":"2026-07-05T09:15:24.832550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:24.832550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bz9UuS9mb9uLwDZnpJdkoyMKqufFV72jTtbzcWRFRuP4vxfZwROj+XhuHM8jCCAZrxVPTqwXawC0oq72EUQoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:24.832987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:630e238ef87a8a7de72daf0010e509c45b86a7e5285a81a1daa17b828ceec8f0","sha256:556572e1581c41933a2d814b2bdf1a2b059ae418bee196b29283081fcdd54026"],"state_sha256":"01d68eb701c945e3996a5a275a27e3b635eb24589a186e9203dca86e70fd4ee0"}