{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NAZFRZL2IRP2D3C5UWNH2X7R65","short_pith_number":"pith:NAZFRZL2","schema_version":"1.0","canonical_sha256":"683258e57a445fa1ec5da59a7d5ff1f75798d4f52e5ad38c73e9d30c437e1228","source":{"kind":"arxiv","id":"2508.00311","version":1},"attestation_state":"computed","paper":{"title":"DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Huang, Lei Chen, Liming Zheng, Lin Ma, Longrong Yang, Siqi Yang, Yufeng Zhong, Zhixiong Zeng","submitted_at":"2025-08-01T04:34:17Z","abstract_excerpt":"Optical Character Recognition (OCR) for mathematical formula is essential for the intelligent analysis of scientific literature. However, both task-specific and general vision-language models often struggle to handle the structural diversity, complexity, and real-world variability inherent in mathematical content. In this work, we present DocTron-Formula, a unified framework built upon general vision-language models, thereby eliminating the need for specialized architectures. Furthermore, we introduce CSFormula, a large-scale and challenging dataset that encompasses multidisciplinary and struc"},"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":"2508.00311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T04:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"d526efbeb314bbfc614297e24203d8d751786f00d38b497476261e41065719e6","abstract_canon_sha256":"21343d8f3c2719490f7daa93d9ee7139f78774c583183ca44e925794c442d7fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:53.143579Z","signature_b64":"kXpEuR1ftri8RnoDD6bbNUvQHT1AfMG6VsaFHJ0LbZAn4H0ndntys0H6OadK67c22JrYIqrc5Cu5YT0bP5YYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"683258e57a445fa1ec5da59a7d5ff1f75798d4f52e5ad38c73e9d30c437e1228","last_reissued_at":"2026-07-05T11:46:53.143038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:53.143038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Huang, Lei Chen, Liming Zheng, Lin Ma, Longrong Yang, Siqi Yang, Yufeng Zhong, Zhixiong Zeng","submitted_at":"2025-08-01T04:34:17Z","abstract_excerpt":"Optical Character Recognition (OCR) for mathematical formula is essential for the intelligent analysis of scientific literature. However, both task-specific and general vision-language models often struggle to handle the structural diversity, complexity, and real-world variability inherent in mathematical content. In this work, we present DocTron-Formula, a unified framework built upon general vision-language models, thereby eliminating the need for specialized architectures. Furthermore, we introduce CSFormula, a large-scale and challenging dataset that encompasses multidisciplinary and struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00311","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/2508.00311/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":"2508.00311","created_at":"2026-07-05T11:46:53.143094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00311v1","created_at":"2026-07-05T11:46:53.143094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00311","created_at":"2026-07-05T11:46:53.143094+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAZFRZL2IRP2","created_at":"2026-07-05T11:46:53.143094+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAZFRZL2IRP2D3C5","created_at":"2026-07-05T11:46:53.143094+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAZFRZL2","created_at":"2026-07-05T11:46:53.143094+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/NAZFRZL2IRP2D3C5UWNH2X7R65","json":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65.json","graph_json":"https://pith.science/api/pith-number/NAZFRZL2IRP2D3C5UWNH2X7R65/graph.json","events_json":"https://pith.science/api/pith-number/NAZFRZL2IRP2D3C5UWNH2X7R65/events.json","paper":"https://pith.science/paper/NAZFRZL2"},"agent_actions":{"view_html":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65","download_json":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65.json","view_paper":"https://pith.science/paper/NAZFRZL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00311&json=true","fetch_graph":"https://pith.science/api/pith-number/NAZFRZL2IRP2D3C5UWNH2X7R65/graph.json","fetch_events":"https://pith.science/api/pith-number/NAZFRZL2IRP2D3C5UWNH2X7R65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/action/storage_attestation","attest_author":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/action/author_attestation","sign_citation":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/action/citation_signature","submit_replication":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/action/replication_record"}},"created_at":"2026-07-05T11:46:53.143094+00:00","updated_at":"2026-07-05T11:46:53.143094+00:00"}