{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUT76TBUNP2FUTVARHJ5PLUUR3","short_pith_number":"pith:NUT76TBU","schema_version":"1.0","canonical_sha256":"6d27ff4c346bf45a4ea089d3d7ae948ec717c85331fcd2d4602f1b33b8035c0c","source":{"kind":"arxiv","id":"2607.02956","version":1},"attestation_state":"computed","paper":{"title":"MORE: A Multilingual Document Parsing Benchmark and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Feng Zhang, Hao Feng, Haoqing Jiang, Long Xu, Shuo Huang, Tinghao Yu, Yunhao Wang, Zhenyu Huang","submitted_at":"2026-07-03T04:59:12Z","abstract_excerpt":"Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, creating an evaluation blind spot concerning model performance on other languages. While recent Vision-Language Models (VLMs) claim support for hundreds of languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introdu"},"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":"2607.02956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T04:59:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"009a2271277ddffed01228c2a81115f981df7ae4982a0a820df5396a6c88669e","abstract_canon_sha256":"10d218e2527935981158239513d7ed1159333edd029abd7442605e9bc7449752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:37.824109Z","signature_b64":"NOxboj/kW3OhAyDwgbA6Fx98I4dXfW/uedYaP1odSfXYPeUuBLBUNz3WspN6DpKjQoKhBlQ594WfOaVNx4X0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d27ff4c346bf45a4ea089d3d7ae948ec717c85331fcd2d4602f1b33b8035c0c","last_reissued_at":"2026-07-07T01:16:37.823663Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:37.823663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MORE: A Multilingual Document Parsing Benchmark and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Binghong Wu, Feng Zhang, Hao Feng, Haoqing Jiang, Long Xu, Shuo Huang, Tinghao Yu, Yunhao Wang, Zhenyu Huang","submitted_at":"2026-07-03T04:59:12Z","abstract_excerpt":"Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, creating an evaluation blind spot concerning model performance on other languages. While recent Vision-Language Models (VLMs) claim support for hundreds of languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introdu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02956","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/2607.02956/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":"2607.02956","created_at":"2026-07-07T01:16:37.823730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02956v1","created_at":"2026-07-07T01:16:37.823730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02956","created_at":"2026-07-07T01:16:37.823730+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUT76TBUNP2F","created_at":"2026-07-07T01:16:37.823730+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUT76TBUNP2FUTVA","created_at":"2026-07-07T01:16:37.823730+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUT76TBU","created_at":"2026-07-07T01:16:37.823730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3","json":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3.json","graph_json":"https://pith.science/api/pith-number/NUT76TBUNP2FUTVARHJ5PLUUR3/graph.json","events_json":"https://pith.science/api/pith-number/NUT76TBUNP2FUTVARHJ5PLUUR3/events.json","paper":"https://pith.science/paper/NUT76TBU"},"agent_actions":{"view_html":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3","download_json":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3.json","view_paper":"https://pith.science/paper/NUT76TBU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02956&json=true","fetch_graph":"https://pith.science/api/pith-number/NUT76TBUNP2FUTVARHJ5PLUUR3/graph.json","fetch_events":"https://pith.science/api/pith-number/NUT76TBUNP2FUTVARHJ5PLUUR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3/action/storage_attestation","attest_author":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3/action/author_attestation","sign_citation":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3/action/citation_signature","submit_replication":"https://pith.science/pith/NUT76TBUNP2FUTVARHJ5PLUUR3/action/replication_record"}},"created_at":"2026-07-07T01:16:37.823730+00:00","updated_at":"2026-07-07T01:16:37.823730+00:00"}