{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:PMDVAXXNKPQX7PDOHH6IIHATHT","short_pith_number":"pith:PMDVAXXN","schema_version":"1.0","canonical_sha256":"7b07505eed53e17fbc6e39fc841c133ccaec3d30bce5a003637660952d4d3f11","source":{"kind":"arxiv","id":"1609.04938","version":2},"attestation_state":"computed","paper":{"title":"Image-to-Markup Generation with Coarse-to-Fine Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Alexander M. Rush, Anssi Kanervisto, Jeffrey Ling, Yuntian Deng","submitted_at":"2016-09-16T08:14:50Z","abstract_excerpt":"We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism. Our method is evaluated in the context of image-to-LaTeX generation, and we introduce a new dataset of real-world rendered mathematical expressions paired with LaTeX markup. We show that unlike neural OCR techniques using CTC-based models, attention-based approaches can tackle this non-standard OCR task. Our approach outperforms classical mathematical OCR systems by a large margin on in-domain rendered data, and, with pretraining, also performs well on "},"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":"1609.04938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-16T08:14:50Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"462119f497f95685a2857ce42595737dcd1a14255328866cc523c780328bb2b9","abstract_canon_sha256":"1892ff969f7fc538eb07c2acf7018e9dace6a201b192557d217e7060058c22b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:23.819082Z","signature_b64":"ndoYIMdDcFJ0Gjkp3Xm/gLfYNkWdEIW3BRxP2Cy74Gd/G3Y9O+dAH7M2o3FEC+IP0fyXjYnqy+H3PDcRwcdlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b07505eed53e17fbc6e39fc841c133ccaec3d30bce5a003637660952d4d3f11","last_reissued_at":"2026-05-18T00:42:23.818526Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:23.818526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image-to-Markup Generation with Coarse-to-Fine Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Alexander M. Rush, Anssi Kanervisto, Jeffrey Ling, Yuntian Deng","submitted_at":"2016-09-16T08:14:50Z","abstract_excerpt":"We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism. Our method is evaluated in the context of image-to-LaTeX generation, and we introduce a new dataset of real-world rendered mathematical expressions paired with LaTeX markup. We show that unlike neural OCR techniques using CTC-based models, attention-based approaches can tackle this non-standard OCR task. Our approach outperforms classical mathematical OCR systems by a large margin on in-domain rendered data, and, with pretraining, also performs well on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.04938","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1609.04938","created_at":"2026-05-18T00:42:23.818611+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.04938v2","created_at":"2026-05-18T00:42:23.818611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.04938","created_at":"2026-05-18T00:42:23.818611+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMDVAXXNKPQX","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMDVAXXNKPQX7PDO","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMDVAXXN","created_at":"2026-05-18T12:30:39.010887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2308.13418","citing_title":"Nougat: Neural Optical Understanding for Academic Documents","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10341","citing_title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT","json":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT.json","graph_json":"https://pith.science/api/pith-number/PMDVAXXNKPQX7PDOHH6IIHATHT/graph.json","events_json":"https://pith.science/api/pith-number/PMDVAXXNKPQX7PDOHH6IIHATHT/events.json","paper":"https://pith.science/paper/PMDVAXXN"},"agent_actions":{"view_html":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT","download_json":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT.json","view_paper":"https://pith.science/paper/PMDVAXXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.04938&json=true","fetch_graph":"https://pith.science/api/pith-number/PMDVAXXNKPQX7PDOHH6IIHATHT/graph.json","fetch_events":"https://pith.science/api/pith-number/PMDVAXXNKPQX7PDOHH6IIHATHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT/action/storage_attestation","attest_author":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT/action/author_attestation","sign_citation":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT/action/citation_signature","submit_replication":"https://pith.science/pith/PMDVAXXNKPQX7PDOHH6IIHATHT/action/replication_record"}},"created_at":"2026-05-18T00:42:23.818611+00:00","updated_at":"2026-05-18T00:42:23.818611+00:00"}