{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TEBUDABL7Q6NGZBAB3DFFT6LBB","short_pith_number":"pith:TEBUDABL","schema_version":"1.0","canonical_sha256":"990341802bfc3cd364200ec652cfcb08497d9f675861a86abdf0f196c4a86e8b","source":{"kind":"arxiv","id":"1809.02193","version":3},"attestation_state":"computed","paper":{"title":"Logical Rule Induction and Theory Learning Using Neural Theorem Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aldo Pareja, Andres Campero, Josh Tenenbaum, Sebastian Riedel, Tim Klinger","submitted_at":"2018-09-06T19:49:20Z","abstract_excerpt":"A hallmark of human cognition is the ability to continually acquire and distill observations of the world into meaningful, predictive theories. In this paper we present a new mechanism for logical theory acquisition which takes a set of observed facts and learns to extract from them a set of logical rules and a small set of core facts which together entail the observations. Our approach is neuro-symbolic in the sense that the rule pred- icates and core facts are given dense vector representations. The rules are applied to the core facts using a soft unification procedure to infer additional fa"},"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":"1809.02193","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-06T19:49:20Z","cross_cats_sorted":[],"title_canon_sha256":"39095b65dee85847e187bd3a421aec76a2378105dc89ded51b2ec4668a837b3b","abstract_canon_sha256":"2b68f5af1d6d4be3d773c80a90a8973c86a4fecc72de3e87012e9006498d6e37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:50.303335Z","signature_b64":"qNt7R3pYU9WzI0nIJlPV5hYcB91L0LmjvpmqCUtnygn/Q9IgCB+NNTk6Pc7slwIaF2Dvd4b+loE7y56585QbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"990341802bfc3cd364200ec652cfcb08497d9f675861a86abdf0f196c4a86e8b","last_reissued_at":"2026-05-18T00:05:50.302699Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:50.302699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logical Rule Induction and Theory Learning Using Neural Theorem Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aldo Pareja, Andres Campero, Josh Tenenbaum, Sebastian Riedel, Tim Klinger","submitted_at":"2018-09-06T19:49:20Z","abstract_excerpt":"A hallmark of human cognition is the ability to continually acquire and distill observations of the world into meaningful, predictive theories. In this paper we present a new mechanism for logical theory acquisition which takes a set of observed facts and learns to extract from them a set of logical rules and a small set of core facts which together entail the observations. Our approach is neuro-symbolic in the sense that the rule pred- icates and core facts are given dense vector representations. The rules are applied to the core facts using a soft unification procedure to infer additional fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02193","kind":"arxiv","version":3},"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":"1809.02193","created_at":"2026-05-18T00:05:50.302797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02193v3","created_at":"2026-05-18T00:05:50.302797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02193","created_at":"2026-05-18T00:05:50.302797+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEBUDABL7Q6N","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEBUDABL7Q6NGZBA","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEBUDABL","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.21663","citing_title":"Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB","json":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB.json","graph_json":"https://pith.science/api/pith-number/TEBUDABL7Q6NGZBAB3DFFT6LBB/graph.json","events_json":"https://pith.science/api/pith-number/TEBUDABL7Q6NGZBAB3DFFT6LBB/events.json","paper":"https://pith.science/paper/TEBUDABL"},"agent_actions":{"view_html":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB","download_json":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB.json","view_paper":"https://pith.science/paper/TEBUDABL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02193&json=true","fetch_graph":"https://pith.science/api/pith-number/TEBUDABL7Q6NGZBAB3DFFT6LBB/graph.json","fetch_events":"https://pith.science/api/pith-number/TEBUDABL7Q6NGZBAB3DFFT6LBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB/action/storage_attestation","attest_author":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB/action/author_attestation","sign_citation":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB/action/citation_signature","submit_replication":"https://pith.science/pith/TEBUDABL7Q6NGZBAB3DFFT6LBB/action/replication_record"}},"created_at":"2026-05-18T00:05:50.302797+00:00","updated_at":"2026-05-18T00:05:50.302797+00:00"}