{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TM7S7JAL4UZXJKAX7IAQ4XLKXL","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":"0a11bd44b254024612635dd2732f92c5b6a665efe4654c0320456940537731aa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T18:04:01Z","title_canon_sha256":"1d4e6fd01262dcc13fb6ef4d0292a178749915ea64792998fe58404c8c96fb7e"},"schema_version":"1.0","source":{"id":"2408.04015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04015","created_at":"2026-07-05T08:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04015v1","created_at":"2026-07-05T08:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04015","created_at":"2026-07-05T08:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"TM7S7JAL4UZX","created_at":"2026-07-05T08:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"TM7S7JAL4UZXJKAX","created_at":"2026-07-05T08:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"TM7S7JAL","created_at":"2026-07-05T08:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:92b37ed5d46525e7ba9260cb5e50386da99b3ec3d2a90e77a1847af799f509c5","target":"graph","created_at":"2026-07-05T08:53:26Z","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/2408.04015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this project, we train a vision encoder-decoder model to generate LaTeX code from images of mathematical formulas and text. Utilizing a diverse collection of image-to-LaTeX data, we build two models: a base model with a Swin Transformer encoder and a GPT-2 decoder, trained on machine-generated images, and a fine-tuned version enhanced with Low-Rank Adaptation (LoRA) trained on handwritten formulas. We then compare the BLEU performance of our specialized model on a handwritten test set with other similar models, such as Pix2Text, TexTeller, and Sumen. Through this project, we contribute open","authors_text":"Aleksey Morshnev, Daniil Gurgurov","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T18:04:01Z","title":"Image-to-LaTeX Converter for Mathematical Formulas and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04015","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":"sha256:7dc6d6591407caf0a548418f5924304440571aa309d0e63e0c55228f1f946f6c","target":"record","created_at":"2026-07-05T08:53:26Z","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":"0a11bd44b254024612635dd2732f92c5b6a665efe4654c0320456940537731aa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T18:04:01Z","title_canon_sha256":"1d4e6fd01262dcc13fb6ef4d0292a178749915ea64792998fe58404c8c96fb7e"},"schema_version":"1.0","source":{"id":"2408.04015","kind":"arxiv","version":1}},"canonical_sha256":"9b3f2fa40be53374a817fa010e5d6abaed3f637cf943f1ada3e836dc04e556b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b3f2fa40be53374a817fa010e5d6abaed3f637cf943f1ada3e836dc04e556b5","first_computed_at":"2026-07-05T08:53:26.779340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:26.779340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v1XrLColOFJx788zclYmZrfBXAAzLUhRZbAcLzXFaVIzpK096z+yIVX2mUNSnv1OjxVeajwp24bDjka60g4HBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:26.779833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dc6d6591407caf0a548418f5924304440571aa309d0e63e0c55228f1f946f6c","sha256:92b37ed5d46525e7ba9260cb5e50386da99b3ec3d2a90e77a1847af799f509c5"],"state_sha256":"e81a4a2f7b1a0515485bc5823d2c88b292768aa3220efbbf707275d59ef171d9"}