{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4O35KQMFPA3BYGLGEDZQZZ7DND","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":"9b4d08740e608c1227682699dfd5584dadf097a8a4001e944aca673aaaf1ba3d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:28:16Z","title_canon_sha256":"c19612b1332b091b80562dfca4414390efaf1ac857eaf2efd33d38cd7261d90f"},"schema_version":"1.0","source":{"id":"2404.01258","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01258","created_at":"2026-07-05T08:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01258v2","created_at":"2026-07-05T08:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01258","created_at":"2026-07-05T08:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"4O35KQMFPA3B","created_at":"2026-07-05T08:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"4O35KQMFPA3BYGLG","created_at":"2026-07-05T08:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"4O35KQMF","created_at":"2026-07-05T08:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:7984172211b025dfd2a2e40339635fe65791bedf222b9de794f530c6e176df63","target":"graph","created_at":"2026-07-05T08:03:30Z","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/2404.01258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference modeling techniques, such as direct preference optimization (DPO), has shown effective in enhancing the generalization abilities of large language model (LLM). However, in tasks involving video instruction-following, providing informative feedback, especially for detecting hallucinations in generated responses, remains a significant challenge. Previous studies have explored using large large multimodal models (LMMs) as reward models to guide preference modeling, but their ability to accurately assess the factuality of generated responses compared to corresponding videos has not been","authors_text":"Alexander Hauptmann, Chunyuan Li, Di Fu, Keyang Xu, Liangke Gui, Ruohong Zhang, Yihao Feng, Yiming Yang, Yonatan Bisk, Yuanhan Zhang, Zhiqing Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:28:16Z","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01258","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":"sha256:2e24ab354e89ec14d92917bf2b26865cacf1b289544bdca57884340aec68ab91","target":"record","created_at":"2026-07-05T08:03:30Z","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":"9b4d08740e608c1227682699dfd5584dadf097a8a4001e944aca673aaaf1ba3d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:28:16Z","title_canon_sha256":"c19612b1332b091b80562dfca4414390efaf1ac857eaf2efd33d38cd7261d90f"},"schema_version":"1.0","source":{"id":"2404.01258","kind":"arxiv","version":2}},"canonical_sha256":"e3b7d5418578361c196620f30ce7e368cc2c6eae0f8a592d6295951831d0f4fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3b7d5418578361c196620f30ce7e368cc2c6eae0f8a592d6295951831d0f4fe","first_computed_at":"2026-07-05T08:03:30.723718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:30.723718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tYZxD9tkK+4jnNKV7vCrAPM6tTfzD7GwAirZYgS8KZk1Ms9vRYcPPCNN9y/9KnEC7J1UQWYedbiJmTdt4rkQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:30.724361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01258","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e24ab354e89ec14d92917bf2b26865cacf1b289544bdca57884340aec68ab91","sha256:7984172211b025dfd2a2e40339635fe65791bedf222b9de794f530c6e176df63"],"state_sha256":"d6d718a7af3c530793a043e2ceb57313492d7e1838990b7d83b9848dad2dac7c"}