{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:75CUJ5YIO2FUBSWVUIU4QIJZMZ","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":"4656e2eb38516b8e7c7ad7c01f284a052040cb97bca335dd59b2780f39c717f4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T18:35:30Z","title_canon_sha256":"a5d9d0d7144cc433c578def094afc64ba5f03b7ba162994d73580d1ad2c32e45"},"schema_version":"1.0","source":{"id":"2606.01393","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01393","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01393v1","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01393","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"75CUJ5YIO2FU","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"75CUJ5YIO2FUBSWV","created_at":"2026-06-02T02:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"75CUJ5YI","created_at":"2026-06-02T02:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:f820cc4aebe08069918974911770b30f25041edeadf812061537878fc0a405af","target":"graph","created_at":"2026-06-02T02:04:32Z","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/2606.01393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OCR) and document parsing benchmarks are increasingly limited in coverage and difficulty: many focus on common document genres or uniformly sampled pages where modern parsers already perform strongly, while offering limited annotation for expert-domain structures such as chemical formula, music notation, complex tables, and cross-page layouts. We introduce Dr. DocBench, a difficulty-aware benchmark for expert-level doc","authors_text":"Alex Pentland, Bangya Liu, Haris Riaz, Henry Zhang, Jesse Thomason, Jinhe Bi, Konwoo Kim, Longtian Ye, Michael Lingzhi Li, Minghao Liu, Minglai Yang, Pengyuan Li, Qunshu Lin, Rogerio Feris, Tom Tang, Xiaolong Luo, Xinyan Velocity Yu, Xinyu Guo, Xuan Zhang, Yilun Du, Yunfei Zhao, Yunze Xiao, Zexue He, Zhenting Qi, Zihan Wang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T18:35:30Z","title":"Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01393","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":"sha256:68c09c1b9e98fed1dd5968a8e5079cab9a88dfc20e89de4fad96dad7bcf84c40","target":"record","created_at":"2026-06-02T02:04:32Z","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":"4656e2eb38516b8e7c7ad7c01f284a052040cb97bca335dd59b2780f39c717f4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T18:35:30Z","title_canon_sha256":"a5d9d0d7144cc433c578def094afc64ba5f03b7ba162994d73580d1ad2c32e45"},"schema_version":"1.0","source":{"id":"2606.01393","kind":"arxiv","version":1}},"canonical_sha256":"ff4544f708768b40cad5a229c821396651af885b65d8eaa70b83a911083f6154","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff4544f708768b40cad5a229c821396651af885b65d8eaa70b83a911083f6154","first_computed_at":"2026-06-02T02:04:32.182946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:32.182946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WFSunsM8CiK/vqVFuxH4GZEpVFKro6juWYRLnRC6lGo4z+jk2JixDqzoFsNQ/p+gpMKNprn0exuNDrc/oTP6DA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:32.183377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01393","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68c09c1b9e98fed1dd5968a8e5079cab9a88dfc20e89de4fad96dad7bcf84c40","sha256:f820cc4aebe08069918974911770b30f25041edeadf812061537878fc0a405af"],"state_sha256":"3bff0e55f4250bb632462863844932fd90141a69a217fe4aa41b8de73d59eb2a"}