{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GK4W4FMOGNWHKSAM2ADXDYQZKE","short_pith_number":"pith:GK4W4FMO","schema_version":"1.0","canonical_sha256":"32b96e158e336c75480cd00771e21951246a1d513a6b16a20e92489e541483dd","source":{"kind":"arxiv","id":"2603.04205","version":2},"attestation_state":"computed","paper":{"title":"Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changda Zhou, Cheng Cui, Jing Tang, Tingquan Gao, Xueqing Wang, Yi Liu, Ziyue Gao","submitted_at":"2026-03-04T15:49:06Z","abstract_excerpt":"While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world remains largely unknown due to the lack of controlled yet realistic evaluations. We introduce Real5-OmniDocBench, the first benchmark that performs a full-scale, one-to-one physical reconstruction of the entire OmniDocBench v1.5 (1,355 images) across five critical real-world scenarios: Scanning, Warping, Screen-Photography, Illumination, and Skew. Unlike prior benchmark that either lack digital correspondence or employ partial s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.04205","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-04T15:49:06Z","cross_cats_sorted":[],"title_canon_sha256":"ff617ff98ad04655587d392c87d28ff5562b2415fb08d499bae1cea2b66e0852","abstract_canon_sha256":"a7d5cd7d1d2c87a9808d37dcf9aca82a0876260105c711ff860c480440d99eb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:59.098803Z","signature_b64":"QPnZVoeAyVCPLKslvhQO7ooYFrkqKCDJtqAgVcyEU2ZP+hwbztTi4EiHQWq/4orWG8ZeeoUxOzA5USHTQAbcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32b96e158e336c75480cd00771e21951246a1d513a6b16a20e92489e541483dd","last_reissued_at":"2026-06-23T02:13:59.098214Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:59.098214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changda Zhou, Cheng Cui, Jing Tang, Tingquan Gao, Xueqing Wang, Yi Liu, Ziyue Gao","submitted_at":"2026-03-04T15:49:06Z","abstract_excerpt":"While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world remains largely unknown due to the lack of controlled yet realistic evaluations. We introduce Real5-OmniDocBench, the first benchmark that performs a full-scale, one-to-one physical reconstruction of the entire OmniDocBench v1.5 (1,355 images) across five critical real-world scenarios: Scanning, Warping, Screen-Photography, Illumination, and Skew. Unlike prior benchmark that either lack digital correspondence or employ partial s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04205","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.04205/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.04205","created_at":"2026-06-23T02:13:59.098288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.04205v2","created_at":"2026-06-23T02:13:59.098288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04205","created_at":"2026-06-23T02:13:59.098288+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK4W4FMOGNWH","created_at":"2026-06-23T02:13:59.098288+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK4W4FMOGNWHKSAM","created_at":"2026-06-23T02:13:59.098288+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK4W4FMO","created_at":"2026-06-23T02:13:59.098288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2601.21957","citing_title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02692","citing_title":"Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03903","citing_title":"CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07492","citing_title":"How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE","json":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE.json","graph_json":"https://pith.science/api/pith-number/GK4W4FMOGNWHKSAM2ADXDYQZKE/graph.json","events_json":"https://pith.science/api/pith-number/GK4W4FMOGNWHKSAM2ADXDYQZKE/events.json","paper":"https://pith.science/paper/GK4W4FMO"},"agent_actions":{"view_html":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE","download_json":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE.json","view_paper":"https://pith.science/paper/GK4W4FMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.04205&json=true","fetch_graph":"https://pith.science/api/pith-number/GK4W4FMOGNWHKSAM2ADXDYQZKE/graph.json","fetch_events":"https://pith.science/api/pith-number/GK4W4FMOGNWHKSAM2ADXDYQZKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE/action/storage_attestation","attest_author":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE/action/author_attestation","sign_citation":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE/action/citation_signature","submit_replication":"https://pith.science/pith/GK4W4FMOGNWHKSAM2ADXDYQZKE/action/replication_record"}},"created_at":"2026-06-23T02:13:59.098288+00:00","updated_at":"2026-06-23T02:13:59.098288+00:00"}