{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OJYDWZTC6QUCGKV4M743A72BKN","short_pith_number":"pith:OJYDWZTC","schema_version":"1.0","canonical_sha256":"72703b6662f428232abc67f9b07f415350584e7b744cc13eb10885fdce4aee97","source":{"kind":"arxiv","id":"1711.04574","version":2},"attestation_state":"computed","paper":{"title":"Learning Explanatory Rules from Noisy Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.LO"],"primary_cat":"cs.NE","authors_text":"Edward Grefenstette, Richard Evans","submitted_at":"2017-11-13T13:30:39Z","abstract_excerpt":"Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model, yielding a nearly ubiquitous overfitting problem. Although mitigated by a variety of model regularisation methods, the common cure is to seek large amounts of training data---which is not necessarily easily obtained---that sufficiently approximates the data distribution of the domain we wish to test on. In contrast, logic programming methods such as Inductiv"},"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":"1711.04574","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-11-13T13:30:39Z","cross_cats_sorted":["math.LO"],"title_canon_sha256":"bef6af4d6072f69b759eddcecfe0ddd94c54df366987fc7dea1cebc91c6ebc69","abstract_canon_sha256":"c016705bd22b058d9acdc917df9e93f4dc516f19d6eeecd4375582b3b1e563ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:07.370065Z","signature_b64":"+vV39guHjBSLnlkLopEXE6yPTaFTebdhOhbk6tWGUlsMy495BoBVeEsd5juaYFHsxUvSPpIqiyRcI8vYv7QlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72703b6662f428232abc67f9b07f415350584e7b744cc13eb10885fdce4aee97","last_reissued_at":"2026-05-18T00:25:07.369648Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:07.369648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Explanatory Rules from Noisy Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.LO"],"primary_cat":"cs.NE","authors_text":"Edward Grefenstette, Richard Evans","submitted_at":"2017-11-13T13:30:39Z","abstract_excerpt":"Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model, yielding a nearly ubiquitous overfitting problem. Although mitigated by a variety of model regularisation methods, the common cure is to seek large amounts of training data---which is not necessarily easily obtained---that sufficiently approximates the data distribution of the domain we wish to test on. In contrast, logic programming methods such as Inductiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04574","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.04574","created_at":"2026-05-18T00:25:07.369707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04574v2","created_at":"2026-05-18T00:25:07.369707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04574","created_at":"2026-05-18T00:25:07.369707+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJYDWZTC6QUC","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJYDWZTC6QUCGKV4","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJYDWZTC","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22875","citing_title":"RMA: an Agentic System for Research-Level Mathematical Problems","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN","json":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN.json","graph_json":"https://pith.science/api/pith-number/OJYDWZTC6QUCGKV4M743A72BKN/graph.json","events_json":"https://pith.science/api/pith-number/OJYDWZTC6QUCGKV4M743A72BKN/events.json","paper":"https://pith.science/paper/OJYDWZTC"},"agent_actions":{"view_html":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN","download_json":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN.json","view_paper":"https://pith.science/paper/OJYDWZTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04574&json=true","fetch_graph":"https://pith.science/api/pith-number/OJYDWZTC6QUCGKV4M743A72BKN/graph.json","fetch_events":"https://pith.science/api/pith-number/OJYDWZTC6QUCGKV4M743A72BKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN/action/storage_attestation","attest_author":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN/action/author_attestation","sign_citation":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN/action/citation_signature","submit_replication":"https://pith.science/pith/OJYDWZTC6QUCGKV4M743A72BKN/action/replication_record"}},"created_at":"2026-05-18T00:25:07.369707+00:00","updated_at":"2026-05-18T00:25:07.369707+00:00"}