{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NAZFRZL2IRP2D3C5UWNH2X7R65","short_pith_number":"pith:NAZFRZL2","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"},"canonical_sha256":"683258e57a445fa1ec5da59a7d5ff1f75798d4f52e5ad38c73e9d30c437e1228","source":{"kind":"arxiv","id":"2508.00311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00311","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00311v1","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00311","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"NAZFRZL2IRP2","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"NAZFRZL2IRP2D3C5","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"NAZFRZL2","created_at":"2026-07-05T11:46:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NAZFRZL2IRP2D3C5UWNH2X7R65","target":"record","payload":{"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"},"canonical_sha256":"683258e57a445fa1ec5da59a7d5ff1f75798d4f52e5ad38c73e9d30c437e1228","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"},"source_kind":"arxiv","source_id":"2508.00311","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+5Bhq50OeKGmipo4WZf+dbQcBFOvbv7S8sa7xtUCDQqzvezihYfzxgP5s6Yq31cPfrspHlHdeSOcwIMOq/6cCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:28:03.393713Z"},"content_sha256":"6fa71c13f6b555aef4722c3028c1c9570435c7503691b4850f70b52c105ed718","schema_version":"1.0","event_id":"sha256:6fa71c13f6b555aef4722c3028c1c9570435c7503691b4850f70b52c105ed718"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NAZFRZL2IRP2D3C5UWNH2X7R65","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGDWOHXoX67eeVToVmZ2Z1DdNa39Bx9juqIJbtYZu7Ba4y+kSTRuleUfqlIQGuiNJB6P5LMrQ6ro8ywecix9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:28:03.394090Z"},"content_sha256":"28a5716d4c570ee8bfd1d1c520f77177e85164753b8ef687e0378e49cc0f5996","schema_version":"1.0","event_id":"sha256:28a5716d4c570ee8bfd1d1c520f77177e85164753b8ef687e0378e49cc0f5996"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/bundle.json","state_url":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T21:28:03Z","links":{"resolver":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65","bundle":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/bundle.json","state":"https://pith.science/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NAZFRZL2IRP2D3C5UWNH2X7R65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NAZFRZL2IRP2D3C5UWNH2X7R65","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":"21343d8f3c2719490f7daa93d9ee7139f78774c583183ca44e925794c442d7fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T04:34:17Z","title_canon_sha256":"d526efbeb314bbfc614297e24203d8d751786f00d38b497476261e41065719e6"},"schema_version":"1.0","source":{"id":"2508.00311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00311","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00311v1","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00311","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"NAZFRZL2IRP2","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"NAZFRZL2IRP2D3C5","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"NAZFRZL2","created_at":"2026-07-05T11:46:53Z"}],"graph_snapshots":[{"event_id":"sha256:28a5716d4c570ee8bfd1d1c520f77177e85164753b8ef687e0378e49cc0f5996","target":"graph","created_at":"2026-07-05T11:46:53Z","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/2508.00311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jing Huang, Lei Chen, Liming Zheng, Lin Ma, Longrong Yang, Siqi Yang, Yufeng Zhong, Zhixiong Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T04:34:17Z","title":"DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00311","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":"sha256:6fa71c13f6b555aef4722c3028c1c9570435c7503691b4850f70b52c105ed718","target":"record","created_at":"2026-07-05T11:46:53Z","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":"21343d8f3c2719490f7daa93d9ee7139f78774c583183ca44e925794c442d7fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T04:34:17Z","title_canon_sha256":"d526efbeb314bbfc614297e24203d8d751786f00d38b497476261e41065719e6"},"schema_version":"1.0","source":{"id":"2508.00311","kind":"arxiv","version":1}},"canonical_sha256":"683258e57a445fa1ec5da59a7d5ff1f75798d4f52e5ad38c73e9d30c437e1228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"683258e57a445fa1ec5da59a7d5ff1f75798d4f52e5ad38c73e9d30c437e1228","first_computed_at":"2026-07-05T11:46:53.143038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:53.143038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kXpEuR1ftri8RnoDD6bbNUvQHT1AfMG6VsaFHJ0LbZAn4H0ndntys0H6OadK67c22JrYIqrc5Cu5YT0bP5YYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:53.143579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fa71c13f6b555aef4722c3028c1c9570435c7503691b4850f70b52c105ed718","sha256:28a5716d4c570ee8bfd1d1c520f77177e85164753b8ef687e0378e49cc0f5996"],"state_sha256":"8799aeb5ae0e215be3fab0702ff557878fae268d86f3664221512046a7b794b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"teOMHRIH/1xvQlps+hBpAEHrrxhvNdLW3rOcnEI5jgkfE8oQ8XSgMpNPSZBb4r2S3KskFc60N6kRm2NeHHviCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:28:03.396682Z","bundle_sha256":"9489777dc9bcc6c2d9f2967f770527d658dfcb5236093ae92272665d6578c46e"}}