{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MQ5DIFWGYUETKECLQS4N57AL46","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":"ec71eabdfd454fd31f1b6a3062ad574b266672dcf0ba8f8abde4e75817fac411","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:57:26Z","title_canon_sha256":"125200e7a699e3712604ec90574186fffe9468c45b463e1c8b598446e6a788a3"},"schema_version":"1.0","source":{"id":"2506.07631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07631","created_at":"2026-07-05T11:18:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07631v1","created_at":"2026-07-05T11:18:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07631","created_at":"2026-07-05T11:18:30Z"},{"alias_kind":"pith_short_12","alias_value":"MQ5DIFWGYUET","created_at":"2026-07-05T11:18:30Z"},{"alias_kind":"pith_short_16","alias_value":"MQ5DIFWGYUETKECL","created_at":"2026-07-05T11:18:30Z"},{"alias_kind":"pith_short_8","alias_value":"MQ5DIFWG","created_at":"2026-07-05T11:18:30Z"}],"graph_snapshots":[{"event_id":"sha256:cdf4c529e3f06cefe3bc6bb46bfc6cffff608468c127e2e3883d7159547eeab8","target":"graph","created_at":"2026-07-05T11:18:30Z","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/2506.07631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (VLMs) now generate highly detailed, paragraphlength image captions, yet evaluating their factual accuracy remains challenging. Current methods often miss fine-grained errors, being designed for shorter texts or lacking datasets with verified inaccuracies. We introduce DOCCI-Critique, a benchmark with 1,400 VLM-generated paragraph captions (100 images, 14 VLMs) featuring over 10,216 sentence-level human annotations of factual correctness and explanatory rationales for errors, all within paragraph context. Building on this, we develop VNLI-Critique, a model for auto","authors_text":"Andreea Marzoca, Brian Gordon, Daniel Cohen-Or, Idan Szpektor, Xiao Wang, Yasumasa Onoe, Yonatan Bitton","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:57:26Z","title":"Unblocking Fine-Grained Evaluation of Detailed Captions: An Explaining AutoRater and Critic-and-Revise Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07631","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:dfbbaec4cc03b0d6e469aa285bc18fd14f437c44df283744ea49358c8e8aab54","target":"record","created_at":"2026-07-05T11:18:30Z","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":"ec71eabdfd454fd31f1b6a3062ad574b266672dcf0ba8f8abde4e75817fac411","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T10:57:26Z","title_canon_sha256":"125200e7a699e3712604ec90574186fffe9468c45b463e1c8b598446e6a788a3"},"schema_version":"1.0","source":{"id":"2506.07631","kind":"arxiv","version":1}},"canonical_sha256":"643a3416c6c50935104b84b8defc0be79856f1702566e75daf40e90fa95458ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"643a3416c6c50935104b84b8defc0be79856f1702566e75daf40e90fa95458ae","first_computed_at":"2026-07-05T11:18:30.598475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:30.598475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HaKNYfEqVOUD1JHApUsTIzN2BuvS5bnjeCk6vpxuNPsBOXN25ekQrfh+7sr3FH75GvS1y3rMl1O+Sn/kNtS5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:30.599149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfbbaec4cc03b0d6e469aa285bc18fd14f437c44df283744ea49358c8e8aab54","sha256:cdf4c529e3f06cefe3bc6bb46bfc6cffff608468c127e2e3883d7159547eeab8"],"state_sha256":"1413973c6c13c0b5161a642fb270113a6eeca686cdf0f21b6daa9276aa66c3ca"}