{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FFV6VXOXDNKSKKCCW4F2QX6MYK","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":"15c06470bff01e75ae7ee21e0cc14f43d45850fcd97354819ebfd72adea1548a","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T15:25:14Z","title_canon_sha256":"e5ee3d37dc84e7382817b6dc249671313e9686323e34eb487c492c1c3493db51"},"schema_version":"1.0","source":{"id":"2505.17163","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17163","created_at":"2026-05-27T01:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17163v2","created_at":"2026-05-27T01:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17163","created_at":"2026-05-27T01:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"FFV6VXOXDNKS","created_at":"2026-05-27T01:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"FFV6VXOXDNKSKKCC","created_at":"2026-05-27T01:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"FFV6VXOX","created_at":"2026-05-27T01:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:181c84c166851a4b172a7e5d76bb0f6ecf6d0588ec1b499c6a79fa727f266c65","target":"graph","created_at":"2026-05-27T01:04:48Z","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/2505.17163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dezhi Peng, Lianwen Jin, Mingxin Huang, Songxuan Lai, Yongxin Shi, Zecheng Xie","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T15:25:14Z","title":"OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17163","kind":"arxiv","version":2},"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:c706e9fb787de50a13dc13bf9ef6ab0812308ec89c764dd28bc3710751369417","target":"record","created_at":"2026-05-27T01:04:48Z","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":"15c06470bff01e75ae7ee21e0cc14f43d45850fcd97354819ebfd72adea1548a","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T15:25:14Z","title_canon_sha256":"e5ee3d37dc84e7382817b6dc249671313e9686323e34eb487c492c1c3493db51"},"schema_version":"1.0","source":{"id":"2505.17163","kind":"arxiv","version":2}},"canonical_sha256":"296beaddd71b55252842b70ba85fccc2a8334099ed4fe49cb568d14cb1876a76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"296beaddd71b55252842b70ba85fccc2a8334099ed4fe49cb568d14cb1876a76","first_computed_at":"2026-05-27T01:04:48.492777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:48.492777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0idIUDvCWOBDZnuAtUEJxofbK2spIGaybiYYzccZ1GNf2CM0aHd0P/Eh8GabHEVVSYng8jnAl5rV6iM/KbQXAQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:48.493385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17163","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c706e9fb787de50a13dc13bf9ef6ab0812308ec89c764dd28bc3710751369417","sha256:181c84c166851a4b172a7e5d76bb0f6ecf6d0588ec1b499c6a79fa727f266c65"],"state_sha256":"65426326a4a4cb0099e397f61e0da07129d87fbc892923e2fdc794ee4ed7f7cc"}