{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MKK64FZNUHAIXP2HKHUY5IL4AA","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":"5df022035fb9fe5572afaf1be2a2f5b1aa2c84bd0d5a6ece958d0e92ec48a310","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-01T11:36:08Z","title_canon_sha256":"9f7008b703560b6d1a8470ff8870be2cd83def1d1f0e93543fd2176eaa583ac1"},"schema_version":"1.0","source":{"id":"2312.00849","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00849","created_at":"2026-07-05T07:53:32Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00849v2","created_at":"2026-07-05T07:53:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00849","created_at":"2026-07-05T07:53:32Z"},{"alias_kind":"pith_short_12","alias_value":"MKK64FZNUHAI","created_at":"2026-07-05T07:53:32Z"},{"alias_kind":"pith_short_16","alias_value":"MKK64FZNUHAIXP2H","created_at":"2026-07-05T07:53:32Z"},{"alias_kind":"pith_short_8","alias_value":"MKK64FZN","created_at":"2026-07-05T07:53:32Z"}],"graph_snapshots":[{"event_id":"sha256:c7f3cdd1b9f468e7238ad7f04785104ee460fb7d9140d6e401f34ecdba41954b","target":"graph","created_at":"2026-07-05T07:53:32Z","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/2312.00849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction. However, existing MLLMs prevalently suffer from serious hallucination problems, generating text that is not factually grounded in associated images. The problem makes existing MLLMs untrustworthy and thus impractical in real-world (especially high-stakes) applications. To address the challenge, we present RLHF-V, which enhances MLLM trustworthiness via behavior alignment from fine-grained correctional human feedback. Specifically, RLHF-V collects ","authors_text":"Ganqu Cui, Hai-Tao Zheng, Haoye Zhang, Jinyi Hu, Maosong Sun, Taiwen He, Tat-Seng Chua, Tianyu Yu, Yifeng Han, Yuan Yao, Zhiyuan Liu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-01T11:36:08Z","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00849","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:aa19e96fab8e93b8397a81d56a92cae08aa98d94244dca1016c121dbfaefdba6","target":"record","created_at":"2026-07-05T07:53:32Z","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":"5df022035fb9fe5572afaf1be2a2f5b1aa2c84bd0d5a6ece958d0e92ec48a310","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-01T11:36:08Z","title_canon_sha256":"9f7008b703560b6d1a8470ff8870be2cd83def1d1f0e93543fd2176eaa583ac1"},"schema_version":"1.0","source":{"id":"2312.00849","kind":"arxiv","version":2}},"canonical_sha256":"6295ee172da1c08bbf4751e98ea17c0016c228aab6502d9753dd37a60e898f6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6295ee172da1c08bbf4751e98ea17c0016c228aab6502d9753dd37a60e898f6d","first_computed_at":"2026-07-05T07:53:32.249759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:32.249759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PwTA/MIcFzcoHetuQmfyHs+ec3I9qnet7NEjm1/v6lu7LRt64oCXW/Z7ZevEtg2hoHNS2vCdjxoLZO074kbaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:32.250185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00849","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa19e96fab8e93b8397a81d56a92cae08aa98d94244dca1016c121dbfaefdba6","sha256:c7f3cdd1b9f468e7238ad7f04785104ee460fb7d9140d6e401f34ecdba41954b"],"state_sha256":"cfaa03b20d16c92d58ec9f8deb0eab957c82b69eb3990bd4418f4fced530441e"}