{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U7JM6A67HUDSWTMFUCBQ3C6LHF","short_pith_number":"pith:U7JM6A67","schema_version":"1.0","canonical_sha256":"a7d2cf03df3d072b4d85a0830d8bcb397760890626faa6e2f3cae9ef1fdb8432","source":{"kind":"arxiv","id":"2105.00377","version":1},"attestation_state":"computed","paper":{"title":"MathBERT: A Pre-Trained Model for Mathematical Formula Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ke Yuan, Liangcai Gao, Shuai Peng, Zhi Tang","submitted_at":"2021-05-02T02:10:31Z","abstract_excerpt":"Large-scale pre-trained models like BERT, have obtained a great success in various Natural Language Processing (NLP) tasks, while it is still a challenge to adapt them to the math-related tasks. Current pre-trained models neglect the structural features and the semantic correspondence between formula and its context. To address these issues, we propose a novel pre-trained model, namely \\textbf{MathBERT}, which is jointly trained with mathematical formulas and their corresponding contexts. In addition, in order to further capture the semantic-level structural features of formulas, a new pre-tra"},"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":"2105.00377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-02T02:10:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b63900be2a62c2a77f88fb0cbcd04e40de65630522a33b8dc278ff2748d2ea35","abstract_canon_sha256":"7bc736801755e99756c86e2b89ae9267c5c3f0ed8da85abdd679c5c6917d5d06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:53.835304Z","signature_b64":"7B6+pr/NzeggNbsJ0OU7aX4zs4XJgDIaLuudh9YBQPHiNriDBT5PqtwEeC7/dV+ZVpryQxvHBDBl9FiLzI7FCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7d2cf03df3d072b4d85a0830d8bcb397760890626faa6e2f3cae9ef1fdb8432","last_reissued_at":"2026-07-05T02:36:53.834836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:53.834836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MathBERT: A Pre-Trained Model for Mathematical Formula Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ke Yuan, Liangcai Gao, Shuai Peng, Zhi Tang","submitted_at":"2021-05-02T02:10:31Z","abstract_excerpt":"Large-scale pre-trained models like BERT, have obtained a great success in various Natural Language Processing (NLP) tasks, while it is still a challenge to adapt them to the math-related tasks. Current pre-trained models neglect the structural features and the semantic correspondence between formula and its context. To address these issues, we propose a novel pre-trained model, namely \\textbf{MathBERT}, which is jointly trained with mathematical formulas and their corresponding contexts. In addition, in order to further capture the semantic-level structural features of formulas, a new pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00377","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/2105.00377/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":"2105.00377","created_at":"2026-07-05T02:36:53.834892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.00377v1","created_at":"2026-07-05T02:36:53.834892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00377","created_at":"2026-07-05T02:36:53.834892+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7JM6A67HUDS","created_at":"2026-07-05T02:36:53.834892+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7JM6A67HUDSWTMF","created_at":"2026-07-05T02:36:53.834892+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7JM6A67","created_at":"2026-07-05T02:36:53.834892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2110.14168","citing_title":"Training Verifiers to Solve Math Word Problems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21743","citing_title":"Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19755","citing_title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13209","citing_title":"AI for Mathematics: Progress, Challenges, and Prospects","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00095","citing_title":"EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18584","citing_title":"MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF","json":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF.json","graph_json":"https://pith.science/api/pith-number/U7JM6A67HUDSWTMFUCBQ3C6LHF/graph.json","events_json":"https://pith.science/api/pith-number/U7JM6A67HUDSWTMFUCBQ3C6LHF/events.json","paper":"https://pith.science/paper/U7JM6A67"},"agent_actions":{"view_html":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF","download_json":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF.json","view_paper":"https://pith.science/paper/U7JM6A67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.00377&json=true","fetch_graph":"https://pith.science/api/pith-number/U7JM6A67HUDSWTMFUCBQ3C6LHF/graph.json","fetch_events":"https://pith.science/api/pith-number/U7JM6A67HUDSWTMFUCBQ3C6LHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF/action/storage_attestation","attest_author":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF/action/author_attestation","sign_citation":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF/action/citation_signature","submit_replication":"https://pith.science/pith/U7JM6A67HUDSWTMFUCBQ3C6LHF/action/replication_record"}},"created_at":"2026-07-05T02:36:53.834892+00:00","updated_at":"2026-07-05T02:36:53.834892+00:00"}