{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RM6RWWBRYT4SBP5YFFQ2FEFSWU","short_pith_number":"pith:RM6RWWBR","schema_version":"1.0","canonical_sha256":"8b3d1b5831c4f920bfb82961a290b2b53b4143ee39ac35cbbb3d33032604b13e","source":{"kind":"arxiv","id":"2409.06639","version":3},"attestation_state":"computed","paper":{"title":"TeXBLEU: Automatic Metric for Evaluate LaTeX Format","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyeok-jae Lee, Hyongon Ryu, Kyudan Jung, Nam-Joon Kim, Seung-jun Lee, Sieun Hyeon","submitted_at":"2024-09-10T16:54:32Z","abstract_excerpt":"LaTeX is suitable for creating specially formatted documents in science, technology, mathematics, and computer science. Although the use of mathematical expressions in LaTeX format along with language models is increasing, there are no proper evaluation matrices to evaluate them. In this study, we propose TeXBLEU, a metric for evaluating mathematical expressions in the LaTeX format built on the n-gram-based BLEU metric widely used in translation tasks. The proposed TeXBLEU consists of a predefined tokenizer trained on the arXiv paper dataset and a fine-tuned embedding model with positional 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":"2409.06639","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T16:54:32Z","cross_cats_sorted":[],"title_canon_sha256":"33db253f490127bb2a585fa8fd710ce84242aa78ec0d815c1d0738f2dec45cef","abstract_canon_sha256":"b8b80eba36dd4fb1091dae0a3c107d044c72c1c5bff09bce96eaec4fec5066a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:28.397592Z","signature_b64":"tq5BtkxcOBmdxTP6ZAxb5PSl6S/lBVEqdDf7ALx95R+vuCRV00lAgap2bG8yNilUdTUbDW+nBkiieQRsXl6wBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3d1b5831c4f920bfb82961a290b2b53b4143ee39ac35cbbb3d33032604b13e","last_reissued_at":"2026-07-05T09:06:28.397198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:28.397198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TeXBLEU: Automatic Metric for Evaluate LaTeX Format","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyeok-jae Lee, Hyongon Ryu, Kyudan Jung, Nam-Joon Kim, Seung-jun Lee, Sieun Hyeon","submitted_at":"2024-09-10T16:54:32Z","abstract_excerpt":"LaTeX is suitable for creating specially formatted documents in science, technology, mathematics, and computer science. Although the use of mathematical expressions in LaTeX format along with language models is increasing, there are no proper evaluation matrices to evaluate them. In this study, we propose TeXBLEU, a metric for evaluating mathematical expressions in the LaTeX format built on the n-gram-based BLEU metric widely used in translation tasks. The proposed TeXBLEU consists of a predefined tokenizer trained on the arXiv paper dataset and a fine-tuned embedding model with positional enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06639","kind":"arxiv","version":3},"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/2409.06639/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":"2409.06639","created_at":"2026-07-05T09:06:28.397258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06639v3","created_at":"2026-07-05T09:06:28.397258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06639","created_at":"2026-07-05T09:06:28.397258+00:00"},{"alias_kind":"pith_short_12","alias_value":"RM6RWWBRYT4S","created_at":"2026-07-05T09:06:28.397258+00:00"},{"alias_kind":"pith_short_16","alias_value":"RM6RWWBRYT4SBP5Y","created_at":"2026-07-05T09:06:28.397258+00:00"},{"alias_kind":"pith_short_8","alias_value":"RM6RWWBR","created_at":"2026-07-05T09:06:28.397258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11086","citing_title":"Intelligibility of Text-to-Speech Systems for Mathematical Expressions","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU","json":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU.json","graph_json":"https://pith.science/api/pith-number/RM6RWWBRYT4SBP5YFFQ2FEFSWU/graph.json","events_json":"https://pith.science/api/pith-number/RM6RWWBRYT4SBP5YFFQ2FEFSWU/events.json","paper":"https://pith.science/paper/RM6RWWBR"},"agent_actions":{"view_html":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU","download_json":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU.json","view_paper":"https://pith.science/paper/RM6RWWBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06639&json=true","fetch_graph":"https://pith.science/api/pith-number/RM6RWWBRYT4SBP5YFFQ2FEFSWU/graph.json","fetch_events":"https://pith.science/api/pith-number/RM6RWWBRYT4SBP5YFFQ2FEFSWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU/action/storage_attestation","attest_author":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU/action/author_attestation","sign_citation":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU/action/citation_signature","submit_replication":"https://pith.science/pith/RM6RWWBRYT4SBP5YFFQ2FEFSWU/action/replication_record"}},"created_at":"2026-07-05T09:06:28.397258+00:00","updated_at":"2026-07-05T09:06:28.397258+00:00"}