{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UFBKPF6XFEPQINB63LWJ5IRR5K","short_pith_number":"pith:UFBKPF6X","schema_version":"1.0","canonical_sha256":"a142a797d7291f04343edaec9ea231eaa76226114dd4feee100c914de7c0be5d","source":{"kind":"arxiv","id":"2104.05930","version":1},"attestation_state":"computed","paper":{"title":"Distilling Wikipedia mathematical knowledge into neural network models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brenden K. Petersen, Joanne T. Kim, Mikel Landajuela","submitted_at":"2021-04-13T04:16:50Z","abstract_excerpt":"Machine learning applications to symbolic mathematics are becoming increasingly popular, yet there lacks a centralized source of real-world symbolic expressions to be used as training data. In contrast, the field of natural language processing leverages resources like Wikipedia that provide enormous amounts of real-world textual data. Adopting the philosophy of \"mathematics as language,\" we bridge this gap by introducing a pipeline for distilling mathematical expressions embedded in Wikipedia into symbolic encodings to be used in downstream machine learning tasks. We demonstrate that a $\\texti"},"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":"2104.05930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-13T04:16:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84409ece73f84f313df38b72739e4b826009084b433b3a9ab1af8057f1bdeeb0","abstract_canon_sha256":"a348348b526da90074adc7eccc01f574bba6f25a5f2f985c5901f65fa86224fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:53.013610Z","signature_b64":"8qP0rS18vPruXhmfEjKJJ8L3tZOxkft7nrMID1Le4AiC5+0Eb5s0mrtBd+Aoq5ENYiKhZQspR8d9mlnfSwBLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a142a797d7291f04343edaec9ea231eaa76226114dd4feee100c914de7c0be5d","last_reissued_at":"2026-07-05T04:37:53.013176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:53.013176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Wikipedia mathematical knowledge into neural network models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brenden K. Petersen, Joanne T. Kim, Mikel Landajuela","submitted_at":"2021-04-13T04:16:50Z","abstract_excerpt":"Machine learning applications to symbolic mathematics are becoming increasingly popular, yet there lacks a centralized source of real-world symbolic expressions to be used as training data. In contrast, the field of natural language processing leverages resources like Wikipedia that provide enormous amounts of real-world textual data. Adopting the philosophy of \"mathematics as language,\" we bridge this gap by introducing a pipeline for distilling mathematical expressions embedded in Wikipedia into symbolic encodings to be used in downstream machine learning tasks. We demonstrate that a $\\texti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05930","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/2104.05930/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":"2104.05930","created_at":"2026-07-05T04:37:53.013238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05930v1","created_at":"2026-07-05T04:37:53.013238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05930","created_at":"2026-07-05T04:37:53.013238+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFBKPF6XFEPQ","created_at":"2026-07-05T04:37:53.013238+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFBKPF6XFEPQINB6","created_at":"2026-07-05T04:37:53.013238+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFBKPF6X","created_at":"2026-07-05T04:37:53.013238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11051","citing_title":"DisCo-DSO: Coupling Discrete and Continuous Optimization for Efficient Generative Design in Hybrid Spaces","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K","json":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K.json","graph_json":"https://pith.science/api/pith-number/UFBKPF6XFEPQINB63LWJ5IRR5K/graph.json","events_json":"https://pith.science/api/pith-number/UFBKPF6XFEPQINB63LWJ5IRR5K/events.json","paper":"https://pith.science/paper/UFBKPF6X"},"agent_actions":{"view_html":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K","download_json":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K.json","view_paper":"https://pith.science/paper/UFBKPF6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05930&json=true","fetch_graph":"https://pith.science/api/pith-number/UFBKPF6XFEPQINB63LWJ5IRR5K/graph.json","fetch_events":"https://pith.science/api/pith-number/UFBKPF6XFEPQINB63LWJ5IRR5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K/action/storage_attestation","attest_author":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K/action/author_attestation","sign_citation":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K/action/citation_signature","submit_replication":"https://pith.science/pith/UFBKPF6XFEPQINB63LWJ5IRR5K/action/replication_record"}},"created_at":"2026-07-05T04:37:53.013238+00:00","updated_at":"2026-07-05T04:37:53.013238+00:00"}