{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GEFEK44WL5RBCSQAG4QQSTQOC7","short_pith_number":"pith:GEFEK44W","schema_version":"1.0","canonical_sha256":"310a4573965f62114a003721094e0e17c7846578cb7e1c00681d2e58c026c839","source":{"kind":"arxiv","id":"2505.12766","version":1},"attestation_state":"computed","paper":{"title":"Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Dacheng Tao, Haibin He, Jing Zhang, Juhua Liu, Maoyuan Ye, Xiantao Cai","submitted_at":"2025-05-19T06:45:18Z","abstract_excerpt":"Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple visual question answering, visual-text parsing, etc. However, the extent to which LMMs can deal with complex logical reasoning problems based on OCR cues is relatively unexplored. To this end, we introduce the Reasoning-OCR benchmark, which challenges LMMs to solve complex reasoning problems based on the cues that can be extracted from rich visual-text. Rea"},"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":"2505.12766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T06:45:18Z","cross_cats_sorted":[],"title_canon_sha256":"05fc47736e12d880cdaf5c4fd3ede39f6cb9cb3c39c06804dddfd5d9574f2a62","abstract_canon_sha256":"dbf9e06de211eb659aaeccae4369707deab098d3b7f44e584e28aeb1161f340b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:09.333513Z","signature_b64":"B/loCKI8PMl4b/Baz8Y3zIEsi/fbqdkT8KUvYP3rkqB0c6RAI4M/zzmXO3JNpQAID6aDs5z86sou73x2+SFADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"310a4573965f62114a003721094e0e17c7846578cb7e1c00681d2e58c026c839","last_reissued_at":"2026-07-05T11:05:09.332996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:09.332996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Dacheng Tao, Haibin He, Jing Zhang, Juhua Liu, Maoyuan Ye, Xiantao Cai","submitted_at":"2025-05-19T06:45:18Z","abstract_excerpt":"Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple visual question answering, visual-text parsing, etc. However, the extent to which LMMs can deal with complex logical reasoning problems based on OCR cues is relatively unexplored. To this end, we introduce the Reasoning-OCR benchmark, which challenges LMMs to solve complex reasoning problems based on the cues that can be extracted from rich visual-text. Rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12766","kind":"arxiv","version":1},"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/2505.12766/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":"2505.12766","created_at":"2026-07-05T11:05:09.333064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12766v1","created_at":"2026-07-05T11:05:09.333064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12766","created_at":"2026-07-05T11:05:09.333064+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEFEK44WL5RB","created_at":"2026-07-05T11:05:09.333064+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEFEK44WL5RBCSQA","created_at":"2026-07-05T11:05:09.333064+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEFEK44W","created_at":"2026-07-05T11:05:09.333064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12978","citing_title":"GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7","json":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7.json","graph_json":"https://pith.science/api/pith-number/GEFEK44WL5RBCSQAG4QQSTQOC7/graph.json","events_json":"https://pith.science/api/pith-number/GEFEK44WL5RBCSQAG4QQSTQOC7/events.json","paper":"https://pith.science/paper/GEFEK44W"},"agent_actions":{"view_html":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7","download_json":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7.json","view_paper":"https://pith.science/paper/GEFEK44W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12766&json=true","fetch_graph":"https://pith.science/api/pith-number/GEFEK44WL5RBCSQAG4QQSTQOC7/graph.json","fetch_events":"https://pith.science/api/pith-number/GEFEK44WL5RBCSQAG4QQSTQOC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7/action/storage_attestation","attest_author":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7/action/author_attestation","sign_citation":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7/action/citation_signature","submit_replication":"https://pith.science/pith/GEFEK44WL5RBCSQAG4QQSTQOC7/action/replication_record"}},"created_at":"2026-07-05T11:05:09.333064+00:00","updated_at":"2026-07-05T11:05:09.333064+00:00"}