{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7LEFEJ6IX75C4YXPZVLX2T7UQF","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":"f4501609caad5f4383ae48464cdf2cd0d3c526d10843700c63535d4fb37df38a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T19:16:54Z","title_canon_sha256":"17086dede3ee12f2ce4d0593d162bde12693e05716a623a225b06e108345efd6"},"schema_version":"1.0","source":{"id":"2506.10128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10128","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10128v1","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10128","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"7LEFEJ6IX75C","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"7LEFEJ6IX75C4YXP","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"7LEFEJ6I","created_at":"2026-07-05T11:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:bd8073097d764f5bfe573fbe78d537a36b9454a278ece86bbc814172f3b3c149","target":"graph","created_at":"2026-07-05T11:20:17Z","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/2506.10128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasoning or code generation. However, extending this success to visual perception in vision-language models (VLMs) has been impeded by the scarcity of vision-centric tasks that are simultaneously challenging and unambiguously verifiable. To this end, we introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of hu","authors_text":"Chao Feng, Chung-Ching Lin, Furong Huang, Kevin Lin, Lijuan Wang, Linjie Li, Ming Li, Xiaoyu Liu, Xiyao Wang, Yongyuan Liang, Yuhang Zhou, Zhengyuan Yang, Ziyi Zang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T19:16:54Z","title":"ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10128","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":"sha256:8ce9b0b0fdf723a3caec78be17632f64279ddcd13107b6211aec2c068e8da1d5","target":"record","created_at":"2026-07-05T11:20:17Z","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":"f4501609caad5f4383ae48464cdf2cd0d3c526d10843700c63535d4fb37df38a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T19:16:54Z","title_canon_sha256":"17086dede3ee12f2ce4d0593d162bde12693e05716a623a225b06e108345efd6"},"schema_version":"1.0","source":{"id":"2506.10128","kind":"arxiv","version":1}},"canonical_sha256":"fac85227c8bffa2e62efcd577d4ff4816e7908174bbddcfc633ba9a80233f7d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fac85227c8bffa2e62efcd577d4ff4816e7908174bbddcfc633ba9a80233f7d3","first_computed_at":"2026-07-05T11:20:17.025809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:17.025809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8qB9VcR39uotjDV+9i1SIEYLovwPzr3G7lNFXJhYLoDdhFwEZBOpQLOZCf91ukoqmSjc9IUssoAX3aYL9dvXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:17.026304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce9b0b0fdf723a3caec78be17632f64279ddcd13107b6211aec2c068e8da1d5","sha256:bd8073097d764f5bfe573fbe78d537a36b9454a278ece86bbc814172f3b3c149"],"state_sha256":"c38b5fd29bd5610ea7ffb3951b1a2290a12955fd1e8be8c428f93130635b643a"}