{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FFV6VXOXDNKSKKCCW4F2QX6MYK","short_pith_number":"pith:FFV6VXOX","schema_version":"1.0","canonical_sha256":"296beaddd71b55252842b70ba85fccc2a8334099ed4fe49cb568d14cb1876a76","source":{"kind":"arxiv","id":"2505.17163","version":2},"attestation_state":"computed","paper":{"title":"OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dezhi Peng, Lianwen Jin, Mingxin Huang, Songxuan Lai, Yongxin Shi, Zecheng Xie","submitted_at":"2025-05-22T15:25:14Z","abstract_excerpt":"Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across various visual reasoning tasks. However, their capabilities in text-rich image reasoning tasks remain understudied due to the absence of a dedicated and systematic benchmark. To address this gap, we propose OCR-Reasoning, a novel benchmark designed to systematically assess Multimodal Large Language Models on text-rich image reasoning tasks. Specifically, OCR-Reasoning comprises 1,069 human-annotated examples spanning 6 core reasoning abilities and 18 practical reasoning tasks in text-rich vi"},"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":"2505.17163","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T15:25:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"e5ee3d37dc84e7382817b6dc249671313e9686323e34eb487c492c1c3493db51","abstract_canon_sha256":"15c06470bff01e75ae7ee21e0cc14f43d45850fcd97354819ebfd72adea1548a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:48.493385Z","signature_b64":"0idIUDvCWOBDZnuAtUEJxofbK2spIGaybiYYzccZ1GNf2CM0aHd0P/Eh8GabHEVVSYng8jnAl5rV6iM/KbQXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296beaddd71b55252842b70ba85fccc2a8334099ed4fe49cb568d14cb1876a76","last_reissued_at":"2026-05-27T01:04:48.492777Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:48.492777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dezhi Peng, Lianwen Jin, Mingxin Huang, Songxuan Lai, Yongxin Shi, Zecheng Xie","submitted_at":"2025-05-22T15:25:14Z","abstract_excerpt":"Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across various visual reasoning tasks. However, their capabilities in text-rich image reasoning tasks remain understudied due to the absence of a dedicated and systematic benchmark. To address this gap, we propose OCR-Reasoning, a novel benchmark designed to systematically assess Multimodal Large Language Models on text-rich image reasoning tasks. Specifically, OCR-Reasoning comprises 1,069 human-annotated examples spanning 6 core reasoning abilities and 18 practical reasoning tasks in text-rich vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17163","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/2505.17163/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":"2505.17163","created_at":"2026-05-27T01:04:48.492879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17163v2","created_at":"2026-05-27T01:04:48.492879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17163","created_at":"2026-05-27T01:04:48.492879+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFV6VXOXDNKS","created_at":"2026-05-27T01:04:48.492879+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFV6VXOXDNKSKKCC","created_at":"2026-05-27T01:04:48.492879+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFV6VXOX","created_at":"2026-05-27T01:04:48.492879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2506.09082","citing_title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2508.05748","citing_title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11960","citing_title":"Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24954","citing_title":"Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24954","citing_title":"Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence","ref_index":2,"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":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK","json":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK.json","graph_json":"https://pith.science/api/pith-number/FFV6VXOXDNKSKKCCW4F2QX6MYK/graph.json","events_json":"https://pith.science/api/pith-number/FFV6VXOXDNKSKKCCW4F2QX6MYK/events.json","paper":"https://pith.science/paper/FFV6VXOX"},"agent_actions":{"view_html":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK","download_json":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK.json","view_paper":"https://pith.science/paper/FFV6VXOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17163&json=true","fetch_graph":"https://pith.science/api/pith-number/FFV6VXOXDNKSKKCCW4F2QX6MYK/graph.json","fetch_events":"https://pith.science/api/pith-number/FFV6VXOXDNKSKKCCW4F2QX6MYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK/action/storage_attestation","attest_author":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK/action/author_attestation","sign_citation":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK/action/citation_signature","submit_replication":"https://pith.science/pith/FFV6VXOXDNKSKKCCW4F2QX6MYK/action/replication_record"}},"created_at":"2026-05-27T01:04:48.492879+00:00","updated_at":"2026-05-27T01:04:48.492879+00:00"}