{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H43HPSP6B6YQP32GQ43ZGP2JQN","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":"93e7ae963b1cfd826fafcea4a7600aff7cd9f49cbc2e2d4c19520cdc8d76e81f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T03:08:02Z","title_canon_sha256":"69ceae8cbbd9c773125083aaf59b701fbf4c14b04aeda9cc15d43770e3d57285"},"schema_version":"1.0","source":{"id":"2509.00676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00676","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00676v1","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00676","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"H43HPSP6B6YQ","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"H43HPSP6B6YQP32G","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"H43HPSP6","created_at":"2026-07-05T12:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:248fcd6c18a9e3f79a9c7313711f92a35c5b96468962b27628e40528338954e8","target":"graph","created_at":"2026-07-05T12:02:20Z","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/2509.00676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses, is so entrenched that critics are rarely considered for direct policy use. In this work, we challenge this convention. We propose to reorganize preference-labeled critic datasets into verifiable training signals and perform reinforcement learning directly on a base generative model, producing LLaVA-Critic-R1, a multimodal critic trained to optimize preference","authors_text":"Bo Liu, Chunyuan Li, Furong Huang, Jianwei Yang, Kai Zhang, Tianyi Xiong, Xiyao Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T03:08:02Z","title":"LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00676","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":"sha256:3a69edb26f4ee0846015134cd47f02cf7b0ad44e95037b5ce905c55bc1372be8","target":"record","created_at":"2026-07-05T12:02:20Z","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":"93e7ae963b1cfd826fafcea4a7600aff7cd9f49cbc2e2d4c19520cdc8d76e81f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T03:08:02Z","title_canon_sha256":"69ceae8cbbd9c773125083aaf59b701fbf4c14b04aeda9cc15d43770e3d57285"},"schema_version":"1.0","source":{"id":"2509.00676","kind":"arxiv","version":1}},"canonical_sha256":"3f3677c9fe0fb107ef468737933f4983548d62e988f337d46b267e923acfccf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f3677c9fe0fb107ef468737933f4983548d62e988f337d46b267e923acfccf8","first_computed_at":"2026-07-05T12:02:20.885715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:20.885715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/HayfdLoCiHM0doABpmDcyNZaArWbV7OLYPmCH5eSQF/5V4qCEWbYV17t4ReCO0HM1IQ0/ugI9wpQZ6HoqdTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:20.886151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a69edb26f4ee0846015134cd47f02cf7b0ad44e95037b5ce905c55bc1372be8","sha256:248fcd6c18a9e3f79a9c7313711f92a35c5b96468962b27628e40528338954e8"],"state_sha256":"0029b7ca43bfafc387b6aebc1771bc1ed446066c003e8110aa445089e53d1d97"}