{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LBWMFWGM556BE5ZL635YJCVJDW","short_pith_number":"pith:LBWMFWGM","schema_version":"1.0","canonical_sha256":"586cc2d8ccef7c12772bf6fb848aa91d8326e364f991930cbba46ef38d3eac3e","source":{"kind":"arxiv","id":"1908.11415","version":2},"attestation_state":"computed","paper":{"title":"Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jyh-Charn Liu, Zelun Wang","submitted_at":"2019-08-29T18:33:21Z","abstract_excerpt":"In this paper we propose a deep neural network model with an encoder-decoder architecture that translates images of math formulas into their LaTeX markup sequences. The encoder is a convolutional neural network (CNN) that transforms images into a group of feature maps. To better capture the spatial relationships of math symbols, the feature maps are augmented with 2D positional encoding before being unfolded into a vector. The decoder is a stacked bidirectional long short-term memory (LSTM) model integrated with the soft attention mechanism, which works as a language model to translate the enc"},"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":"1908.11415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-29T18:33:21Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"cbff1309550ef2667512d543668f73297c59c6b4756cd4316f0fd624c7496240","abstract_canon_sha256":"99d423ebfc857ef9ddbb56f7ddababf85669f2063d8fa4b8a90b859582fc8075"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:17.539213Z","signature_b64":"OUVoak9CEZJMAhEqsNpVC0+ai+4wb0Rk9xg1elN0+Dp49L3vDQL1g597OHK8l+dG7Y7vzq7oI2gW6K8YYfo/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586cc2d8ccef7c12772bf6fb848aa91d8326e364f991930cbba46ef38d3eac3e","last_reissued_at":"2026-07-05T00:03:17.538746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:17.538746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jyh-Charn Liu, Zelun Wang","submitted_at":"2019-08-29T18:33:21Z","abstract_excerpt":"In this paper we propose a deep neural network model with an encoder-decoder architecture that translates images of math formulas into their LaTeX markup sequences. The encoder is a convolutional neural network (CNN) that transforms images into a group of feature maps. To better capture the spatial relationships of math symbols, the feature maps are augmented with 2D positional encoding before being unfolded into a vector. The decoder is a stacked bidirectional long short-term memory (LSTM) model integrated with the soft attention mechanism, which works as a language model to translate the enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11415","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.11415/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":"1908.11415","created_at":"2026-07-05T00:03:17.538806+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.11415v2","created_at":"2026-07-05T00:03:17.538806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11415","created_at":"2026-07-05T00:03:17.538806+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBWMFWGM556B","created_at":"2026-07-05T00:03:17.538806+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBWMFWGM556BE5ZL","created_at":"2026-07-05T00:03:17.538806+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBWMFWGM","created_at":"2026-07-05T00:03:17.538806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.13418","citing_title":"Nougat: Neural Optical Understanding for Academic Documents","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW","json":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW.json","graph_json":"https://pith.science/api/pith-number/LBWMFWGM556BE5ZL635YJCVJDW/graph.json","events_json":"https://pith.science/api/pith-number/LBWMFWGM556BE5ZL635YJCVJDW/events.json","paper":"https://pith.science/paper/LBWMFWGM"},"agent_actions":{"view_html":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW","download_json":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW.json","view_paper":"https://pith.science/paper/LBWMFWGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.11415&json=true","fetch_graph":"https://pith.science/api/pith-number/LBWMFWGM556BE5ZL635YJCVJDW/graph.json","fetch_events":"https://pith.science/api/pith-number/LBWMFWGM556BE5ZL635YJCVJDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW/action/storage_attestation","attest_author":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW/action/author_attestation","sign_citation":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW/action/citation_signature","submit_replication":"https://pith.science/pith/LBWMFWGM556BE5ZL635YJCVJDW/action/replication_record"}},"created_at":"2026-07-05T00:03:17.538806+00:00","updated_at":"2026-07-05T00:03:17.538806+00:00"}