{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XOKSKZUDK5E2WQUJLES6H5KQMD","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":"df59132b7dba76d37501a36a0a16895d54a15689052331b46d60544245a543f3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-22T07:40:20Z","title_canon_sha256":"ad6d9aef8b7a7ffce83c8341dd48f091f5b8c1821ff705a1b18a4796345dae80"},"schema_version":"1.0","source":{"id":"2503.17682","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17682","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17682v2","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17682","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"pith_short_12","alias_value":"XOKSKZUDK5E2","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"pith_short_16","alias_value":"XOKSKZUDK5E2WQUJ","created_at":"2026-07-05T11:07:21Z"},{"alias_kind":"pith_short_8","alias_value":"XOKSKZUD","created_at":"2026-07-05T11:07:21Z"}],"graph_snapshots":[{"event_id":"sha256:9663956ab0e6260f92651e5c13df3181177e6c28811c695bb8044adaa54b0920","target":"graph","created_at":"2026-07-05T11:07:21Z","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/2503.17682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants; however, they pose increasing safety risks. How can we ensure safety alignment of MLLMs to prevent undesired behaviors? Going further, it is critical to explore how to fine-tune MLLMs to preserve capabilities while meeting safety constraints. Fundamentally, this challenge can be formulated as a min-max optimization problem. However, existing datasets have not yet disentangled single preference signals into explicit safety constraints, hindering systematic investigation in this direction. Moreover","authors_text":"Boyuan Chen, Chi-Min Chan, Conghui Zhang, Donghai Hong, Han Zhu, Jiahao Li, Jiaming Ji, Jiayi Zhou, Juntao Dai, Kaile Wang, Rui Pan, Sirui Han, Xinyu Chen, Yaodong Yang, Yida Tang, Yike Guo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-22T07:40:20Z","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17682","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":"sha256:91ea310a8ffd8ab7376e792ce343ea3b3df734d69d1b174d9201cef6d2b5cbb1","target":"record","created_at":"2026-07-05T11:07:21Z","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":"df59132b7dba76d37501a36a0a16895d54a15689052331b46d60544245a543f3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-22T07:40:20Z","title_canon_sha256":"ad6d9aef8b7a7ffce83c8341dd48f091f5b8c1821ff705a1b18a4796345dae80"},"schema_version":"1.0","source":{"id":"2503.17682","kind":"arxiv","version":2}},"canonical_sha256":"bb952566835749ab42895925e3f55060fc802615f06a191f30bd44b29c6c9fe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb952566835749ab42895925e3f55060fc802615f06a191f30bd44b29c6c9fe2","first_computed_at":"2026-07-05T11:07:21.950383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:21.950383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZN+nockJIWHCJVG0o0s7TxBMn0+D3nXJ/hSqrBch6YZ8Cq6oL9KIDYhLmKUWS7uXg0xVz5j23pGM1/hho3/oBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:21.950938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17682","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91ea310a8ffd8ab7376e792ce343ea3b3df734d69d1b174d9201cef6d2b5cbb1","sha256:9663956ab0e6260f92651e5c13df3181177e6c28811c695bb8044adaa54b0920"],"state_sha256":"be39ca4481949470cb03bb1667e6ef1fca5e449f9cfb2d32ae174f87677f48c5"}