{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z7DEXKUITVTFXVTSV6MLZTI5UQ","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":"960ac8354e60e7973ac5afe2e62812038bb20cb10fc2ede2623e6844751b359e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T18:43:07Z","title_canon_sha256":"bfa081163df982766a38977d163749c09ddf95dc2c2cfe229bdfd8294cee8953"},"schema_version":"1.0","source":{"id":"2311.12919","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12919","created_at":"2026-07-05T07:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12919v2","created_at":"2026-07-05T07:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12919","created_at":"2026-07-05T07:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"Z7DEXKUITVTF","created_at":"2026-07-05T07:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"Z7DEXKUITVTFXVTS","created_at":"2026-07-05T07:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"Z7DEXKUI","created_at":"2026-07-05T07:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:9d3aaa2fc1a0d7dbd5db1f357e9cc6b98a7ea8ce851b6b79d2af4cfad8beaea3","target":"graph","created_at":"2026-07-05T07:19:24Z","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/2311.12919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding videos is an important research topic for multimodal learning. Leveraging large-scale datasets of web-crawled video-text pairs as weak supervision has become a pre-training paradigm for learning joint representations and showcased remarkable potential in video understanding tasks. However, videos can be multi-event and multi-grained, while these video-text pairs usually contain only broad-level video captions. This raises a question: with such weak supervision, can video representation in video-language models gain the ability to distinguish even factual discrepancies in textual ","authors_text":"Gengyuan Zhang, Jindong Gu, Jinhe Bi, Volker Tresp, Yanyu Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T18:43:07Z","title":"SPOT! Revisiting Video-Language Models for Event Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12919","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:ea3611991ffc120e22fec3c6b894a579aa66f9eeac8665437a04e869d0774667","target":"record","created_at":"2026-07-05T07:19:24Z","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":"960ac8354e60e7973ac5afe2e62812038bb20cb10fc2ede2623e6844751b359e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T18:43:07Z","title_canon_sha256":"bfa081163df982766a38977d163749c09ddf95dc2c2cfe229bdfd8294cee8953"},"schema_version":"1.0","source":{"id":"2311.12919","kind":"arxiv","version":2}},"canonical_sha256":"cfc64baa889d665bd672af98bccd1da405a1fe6d6f770bc2deb79db7416897fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfc64baa889d665bd672af98bccd1da405a1fe6d6f770bc2deb79db7416897fe","first_computed_at":"2026-07-05T07:19:24.162518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:24.162518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gRIoFm7HjwuZAYo+AQdybDKAlyW3pCNMzcXlWbga7clYpeFBpis+3GU9q0m47WKtUMjrYv95D7suFXf2Qb3yDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:24.163548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.12919","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea3611991ffc120e22fec3c6b894a579aa66f9eeac8665437a04e869d0774667","sha256:9d3aaa2fc1a0d7dbd5db1f357e9cc6b98a7ea8ce851b6b79d2af4cfad8beaea3"],"state_sha256":"3b4f32160f89d461f38c951358d0fbfecfdbcc789523ceee14f24c2a3c9af184"}