{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MMYTWSKOVMIC627OS5QEH5IHOF","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":"16380e591ce5fdb5d53c8ce1e198b7c21168763572e6b47d0d6cdcb82c51b269","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T12:37:03Z","title_canon_sha256":"d2133d6e386cdd3c285617728488e24480c4f2369c7ed585181ee9440e647471"},"schema_version":"1.0","source":{"id":"2605.22413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22413","created_at":"2026-05-22T01:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22413v1","created_at":"2026-05-22T01:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22413","created_at":"2026-05-22T01:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"MMYTWSKOVMIC","created_at":"2026-05-22T01:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"MMYTWSKOVMIC627O","created_at":"2026-05-22T01:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"MMYTWSKO","created_at":"2026-05-22T01:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:c95cd9519eb9f7b592190dac581a0ab25580ac4d6aee8b36d9865af2da067443","target":"graph","created_at":"2026-05-22T01:04:42Z","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/2605.22413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multimodal Large Language Models (MLLMs) have shown promising capabilities, existing benchmarks suffer from critical limitations in scale and realism, lack semantic granularity, and fail to cover diverse document types. To bridge this gap, we introduce ReceiptBench, a large-scale, human-annotated benchmark consisting of 10k diverse receipts, organizing information extraction into four hierarchical sub-tasks: (1) Basic Perception for raw text spottin","authors_text":"Jun Chen, Leilei Gan, Libin Zhan, Tiancheng Luo, Wang Dong, Yandi Wang, Yuxuan Jiang, Ziwei Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T12:37:03Z","title":"From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22413","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":"sha256:6f6f6c87347e0e5a5d388d8afd6734a2ae4b323619f9c6c0711815d28c5d7ebe","target":"record","created_at":"2026-05-22T01:04:42Z","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":"16380e591ce5fdb5d53c8ce1e198b7c21168763572e6b47d0d6cdcb82c51b269","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T12:37:03Z","title_canon_sha256":"d2133d6e386cdd3c285617728488e24480c4f2369c7ed585181ee9440e647471"},"schema_version":"1.0","source":{"id":"2605.22413","kind":"arxiv","version":1}},"canonical_sha256":"63313b494eab102f6bee976043f50771771a9dfbf2942a2ae006b1fce1f681c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63313b494eab102f6bee976043f50771771a9dfbf2942a2ae006b1fce1f681c0","first_computed_at":"2026-05-22T01:04:42.200540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:42.200540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0NOg+ZCbx+IFyqnGXPjMMAtjmFS5k1pc7GqIfs3C2BaBwHJwhNxC0dHv/UhBHWW8kRAwbxZ/jjwr5XSHxYGeBA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:42.201071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f6f6c87347e0e5a5d388d8afd6734a2ae4b323619f9c6c0711815d28c5d7ebe","sha256:c95cd9519eb9f7b592190dac581a0ab25580ac4d6aee8b36d9865af2da067443"],"state_sha256":"fc94b9cdc8fc47d09dd936b24a361bf6e56e5ce00086ca81bc772bb205baf0b3"}