{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J3VASWYUVPPGPJDHK5MBUFPWJI","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":"779c5acf465d8024ec5b57388606cb289f19047010a4b56cbafbbe4b615229d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T02:43:18Z","title_canon_sha256":"c6337823b2f29394759c44d0f7f9872e7db065f09a710dada995aae42a496386"},"schema_version":"1.0","source":{"id":"2106.07340","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07340","created_at":"2026-07-05T06:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07340v5","created_at":"2026-07-05T06:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07340","created_at":"2026-07-05T06:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"J3VASWYUVPPG","created_at":"2026-07-05T06:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"J3VASWYUVPPGPJDH","created_at":"2026-07-05T06:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"J3VASWYU","created_at":"2026-07-05T06:40:26Z"}],"graph_snapshots":[{"event_id":"sha256:ae135b4668ecb3fa4da8eaaf9b7c9c9f8cca12e996a177532e1b31a887d3d59d","target":"graph","created_at":"2026-07-05T06:40:26Z","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/2106.07340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since the introduction of the original BERT (i.e., BASE BERT), researchers have developed various customized BERT models with improved performance for specific domains and tasks by exploiting the benefits of transfer learning. Due to the nature of mathematical texts, which often use domain specific vocabulary along with equations and math symbols, we posit that the development of a new BERT model for mathematics would be useful for many mathematical downstream tasks. In this resource paper, we introduce our multi-institutional effort (i.e., two learning platforms and three academic institution","authors_text":"Ben Graff, Dongwon Lee, Ethan Prihar, Jia Tracy Shen, Michiharu Yamashita, Neil Heffernan, Xintao Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T02:43:18Z","title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07340","kind":"arxiv","version":5},"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":"sha256:0e73777842507752f3778343918986570f0a3d3533a51f68a0a2d69a286c7d87","target":"record","created_at":"2026-07-05T06:40:26Z","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":"779c5acf465d8024ec5b57388606cb289f19047010a4b56cbafbbe4b615229d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-02T02:43:18Z","title_canon_sha256":"c6337823b2f29394759c44d0f7f9872e7db065f09a710dada995aae42a496386"},"schema_version":"1.0","source":{"id":"2106.07340","kind":"arxiv","version":5}},"canonical_sha256":"4eea095b14abde67a46757581a15f64a04a1d241378f070218c822f881f7d480","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eea095b14abde67a46757581a15f64a04a1d241378f070218c822f881f7d480","first_computed_at":"2026-07-05T06:40:26.905697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:26.905697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tNEsmSFY8AHykBKih1O/LMiiwHh1hFFPUyxSDb3+3WqJ8dzP2nA/1jUM4xCCKtWuF69hYH3kfxsPf/r9XSYDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:26.906259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07340","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e73777842507752f3778343918986570f0a3d3533a51f68a0a2d69a286c7d87","sha256:ae135b4668ecb3fa4da8eaaf9b7c9c9f8cca12e996a177532e1b31a887d3d59d"],"state_sha256":"e052c871fc94f6af60d975d4f4f4dd4ced1860bace31b48c2b9b594ea81ebb60"}