{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5OOGL74WVCCLTLBCBN3K4SIDQY","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":"40b532dac5948d451386a9e7d9803b367fbf227ef69b024c07957c3e6b9a2ccf","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T05:04:49Z","title_canon_sha256":"83109f974393ed215036f2091aa1c6d41266a92b437cc068eaeab0e6197bf67f"},"schema_version":"1.0","source":{"id":"2412.02172","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02172","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02172v2","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02172","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"pith_short_12","alias_value":"5OOGL74WVCCL","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"pith_short_16","alias_value":"5OOGL74WVCCLTLBC","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"pith_short_8","alias_value":"5OOGL74W","created_at":"2026-07-05T10:33:40Z"}],"graph_snapshots":[{"event_id":"sha256:646728df9e5f47e94219e0230353ee4495fbfa208ecad3cabe3a92801b970ded","target":"graph","created_at":"2026-07-05T10:33:40Z","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/2412.02172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability of large vision-language models (LVLMs) to critique and correct their reasoning is an essential building block towards their self-improvement. However, a systematic analysis of such capabilities in LVLMs is still lacking. We propose VISCO, the first benchmark to extensively analyze the fine-grained critique and correction capabilities of LVLMs. Compared to existing work that uses a single scalar value to critique the entire reasoning [4], VISCO features dense and fine-grained critique, requiring LVLMs to evaluate the correctness of each step in the chain-of-thought and provide natu","authors_text":"Bingxuan Li, Da Yin, Kai-Wei Chang, Nanyun Peng, Pan Lu, Xueqing Wu, Yuheng Ding","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T05:04:49Z","title":"VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02172","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":"sha256:67867c76a0f23b696e239bfc64ce9664a89c576b1cd49542168b7791c2dcab66","target":"record","created_at":"2026-07-05T10:33:40Z","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":"40b532dac5948d451386a9e7d9803b367fbf227ef69b024c07957c3e6b9a2ccf","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T05:04:49Z","title_canon_sha256":"83109f974393ed215036f2091aa1c6d41266a92b437cc068eaeab0e6197bf67f"},"schema_version":"1.0","source":{"id":"2412.02172","kind":"arxiv","version":2}},"canonical_sha256":"eb9c65ff96a884b9ac220b76ae49038626a090952482551c697a6c296db1e270","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb9c65ff96a884b9ac220b76ae49038626a090952482551c697a6c296db1e270","first_computed_at":"2026-07-05T10:33:40.628407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:40.628407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jrjNLBnNP+rfCYnnCq9foVJKHIqoHEWNI4CY7uIQWEXjoWlAB7HWJ9mCnqIDGn3Zhap0ydtDZzdK4KBCBz9dCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:40.628922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02172","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67867c76a0f23b696e239bfc64ce9664a89c576b1cd49542168b7791c2dcab66","sha256:646728df9e5f47e94219e0230353ee4495fbfa208ecad3cabe3a92801b970ded"],"state_sha256":"b17135caafd390943565f27fa743e9941bdad068e7b79e27705b7586d947f519"}