{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AFWRNCUWPFLOABIJIV46PCW2PV","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":"8da9c408844116d6fb5ab29be49f9b1e05be9eb123eaaa0f2869994b4a94027d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-13T15:44:02Z","title_canon_sha256":"e12777a36cd3a8ff00d38005462bec5c0d026ef11809c2b9c5064260459bdb27"},"schema_version":"1.0","source":{"id":"2604.11632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11632","created_at":"2026-05-26T02:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11632v2","created_at":"2026-05-26T02:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11632","created_at":"2026-05-26T02:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"AFWRNCUWPFLO","created_at":"2026-05-26T02:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"AFWRNCUWPFLOABIJ","created_at":"2026-05-26T02:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"AFWRNCUW","created_at":"2026-05-26T02:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:15f0750de236fe785c16f23dfd02c02a26e39abb162a8199077b29623ea06bb0","target":"graph","created_at":"2026-05-26T02:05:09Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across nine representative VLMs, we find that high overall CURATORQA accuracy can mask sharp drops on hard evidence linking and style-to-period inference; long-form appreciation remains far from expert references; and authenticity-oriented diagnostic discrimination stays near chance, underscoring the difficulty of connoisseur-level reasoning for current models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That alignment of Wikidata objects with authoritative Palace Museum catalog pages and expert ratings provides reliable, unbiased ground truth for defensible reinterpretation and authenticity discrimination tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CArtBench shows VLMs achieve high scores on easy recognition but drop sharply on evidence linking, style inference, long-form appreciation, and authenticity discrimination for Chinese art."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Vision-language models post high overall scores on Chinese art questions yet drop sharply on evidence linking, expert-style appreciation, and authenticity discrimination."}],"snapshot_sha256":"31818fdd737ccbab93bf4d159525226aeb1e00682e446a19039096f978d987cb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce CARTBENCH, a museum-grounded benchmark for evaluating vision-language models (VLMs) on Chinese artworks beyond short-form recognition and QA. CARTBENCH comprises four subtasks: CURATORQA for evidence-grounded recognition and reasoning, CATALOGCAPTION for structured four-section expert-style appreciation, REINTERPRET for defensible reinterpretation with expert ratings, and CONNOISSEURPAIRS for diagnostic authenticity discrimination under visually similar confounds. CARTBENCH is built by aligning image-bearing Palace Museum objects from Wikidata with authoritative catalog pages, spa","authors_text":"Hidetaka Kamigaito, Hongyao Li, Taro Watanabe, Xuan Zhou, Xuefeng Wei, Yusuke Sakai, Zhi Qu, Zhixuan Wang","cross_cats":[],"headline":"Vision-language models post high overall scores on Chinese art questions yet drop sharply on evidence linking, expert-style appreciation, and authenticity discrimination.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-13T15:44:02Z","title":"CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11632","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T15:17:24.530599Z","id":"dc9f2b65-79cc-4dd2-b49d-160fbc85f504","model_set":{"reader":"grok-4.3"},"one_line_summary":"CArtBench shows VLMs achieve high scores on easy recognition but drop sharply on evidence linking, style inference, long-form appreciation, and authenticity discrimination for Chinese art.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Vision-language models post high overall scores on Chinese art questions yet drop sharply on evidence linking, expert-style appreciation, and authenticity discrimination.","strongest_claim":"Across nine representative VLMs, we find that high overall CURATORQA accuracy can mask sharp drops on hard evidence linking and style-to-period inference; long-form appreciation remains far from expert references; and authenticity-oriented diagnostic discrimination stays near chance, underscoring the difficulty of connoisseur-level reasoning for current models.","weakest_assumption":"That alignment of Wikidata objects with authoritative Palace Museum catalog pages and expert ratings provides reliable, unbiased ground truth for defensible reinterpretation and authenticity discrimination tasks."}},"verdict_id":"dc9f2b65-79cc-4dd2-b49d-160fbc85f504"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2a1734a3c66a12babce6ca1c76c878c499b29e363f75e4de0f3df4303ff3e8d9","target":"record","created_at":"2026-05-26T02:05:09Z","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":"8da9c408844116d6fb5ab29be49f9b1e05be9eb123eaaa0f2869994b4a94027d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-13T15:44:02Z","title_canon_sha256":"e12777a36cd3a8ff00d38005462bec5c0d026ef11809c2b9c5064260459bdb27"},"schema_version":"1.0","source":{"id":"2604.11632","kind":"arxiv","version":2}},"canonical_sha256":"016d168a967956e005094579e78ada7d63bc186b7f647094b1a2a2b687fcddc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"016d168a967956e005094579e78ada7d63bc186b7f647094b1a2a2b687fcddc2","first_computed_at":"2026-05-26T02:05:09.334005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:09.334005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6J35pa3IjQX+SraUXD8OBdxr7X91axXE94HrYp2KKEpGbYE/qUjUpcUYzax+9j83F/Upn6VDAKh1V2FYvONFCg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:09.334870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a1734a3c66a12babce6ca1c76c878c499b29e363f75e4de0f3df4303ff3e8d9","sha256:15f0750de236fe785c16f23dfd02c02a26e39abb162a8199077b29623ea06bb0"],"state_sha256":"25eaedf20a3e61d2b9d16a7594dbfb2a4c4eb4fbe70bd5eb5f9989d857eb1130"}