{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UFBKPF6XFEPQINB63LWJ5IRR5K","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":"a348348b526da90074adc7eccc01f574bba6f25a5f2f985c5901f65fa86224fa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-13T04:16:50Z","title_canon_sha256":"84409ece73f84f313df38b72739e4b826009084b433b3a9ab1af8057f1bdeeb0"},"schema_version":"1.0","source":{"id":"2104.05930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05930","created_at":"2026-07-05T04:37:53Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05930v1","created_at":"2026-07-05T04:37:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05930","created_at":"2026-07-05T04:37:53Z"},{"alias_kind":"pith_short_12","alias_value":"UFBKPF6XFEPQ","created_at":"2026-07-05T04:37:53Z"},{"alias_kind":"pith_short_16","alias_value":"UFBKPF6XFEPQINB6","created_at":"2026-07-05T04:37:53Z"},{"alias_kind":"pith_short_8","alias_value":"UFBKPF6X","created_at":"2026-07-05T04:37:53Z"}],"graph_snapshots":[{"event_id":"sha256:295b601810e82e3c2a077ad2a59ba9cb698b82b66468a5344960c5828309dbec","target":"graph","created_at":"2026-07-05T04:37:53Z","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/2104.05930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Brenden K. Petersen, Joanne T. Kim, Mikel Landajuela","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-13T04:16:50Z","title":"Distilling Wikipedia mathematical knowledge into neural network models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05930","kind":"arxiv","version":1},"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":"sha256:965c1f38468ad90d4e384dc995ab3be3e836e9d3771094d0781c9d465b2db878","target":"record","created_at":"2026-07-05T04:37:53Z","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":"a348348b526da90074adc7eccc01f574bba6f25a5f2f985c5901f65fa86224fa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-13T04:16:50Z","title_canon_sha256":"84409ece73f84f313df38b72739e4b826009084b433b3a9ab1af8057f1bdeeb0"},"schema_version":"1.0","source":{"id":"2104.05930","kind":"arxiv","version":1}},"canonical_sha256":"a142a797d7291f04343edaec9ea231eaa76226114dd4feee100c914de7c0be5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a142a797d7291f04343edaec9ea231eaa76226114dd4feee100c914de7c0be5d","first_computed_at":"2026-07-05T04:37:53.013176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:53.013176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8qP0rS18vPruXhmfEjKJJ8L3tZOxkft7nrMID1Le4AiC5+0Eb5s0mrtBd+Aoq5ENYiKhZQspR8d9mlnfSwBLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:53.013610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:965c1f38468ad90d4e384dc995ab3be3e836e9d3771094d0781c9d465b2db878","sha256:295b601810e82e3c2a077ad2a59ba9cb698b82b66468a5344960c5828309dbec"],"state_sha256":"5e3afbd1d46a7d0980072e859bfadbbb3bb2da0e0a53bd7c3cd0e756237281ae"}