{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UCRAOYDOWKYMC6NQ7HJAPWZWC5","short_pith_number":"pith:UCRAOYDO","schema_version":"1.0","canonical_sha256":"a0a207606eb2b0c179b0f9d207db361759440238fe2c0db1a297d69a35fa0118","source":{"kind":"arxiv","id":"1904.11694","version":1},"attestation_state":"computed","paper":{"title":"Neural Logic Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Chong Wang, Denny Zhou, Honghua Dong, Jiayuan Mao, Lihong Li, Tian LIN","submitted_at":"2019-04-26T06:52:53Z","abstract_excerpt":"We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning. NLMs exploit the power of both neural networks---as function approximators, and logic programming---as a symbolic processor for objects with properties, relations, logic connectives, and quantifiers. After being trained on small-scale tasks (such as sorting short arrays), NLMs can recover lifted rules, and generalize to large-scale tasks (such as sorting longer arrays). In our experiments, NLMs achieve perfect generalization in a number of tasks, from relational reasoning "},"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":"1904.11694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-04-26T06:52:53Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"761a49b2c76c0b87d9c1c56707dce3de6a7b356df1b12106e5712dd9f776e8c8","abstract_canon_sha256":"15b28962b279968d72d39432a2be80d637a1b2d0dae97ac995001a5097948fa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:43.023769Z","signature_b64":"+w/6y+Iqz5I1DgqEmG4t+Rw3YyGsencPIMo5to7YOsmpuJwg7LnmBNQshBOic/7yo2X7lZ/P8rGXKnBkV6YpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0a207606eb2b0c179b0f9d207db361759440238fe2c0db1a297d69a35fa0118","last_reissued_at":"2026-05-17T23:47:43.023278Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:43.023278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Logic Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Chong Wang, Denny Zhou, Honghua Dong, Jiayuan Mao, Lihong Li, Tian LIN","submitted_at":"2019-04-26T06:52:53Z","abstract_excerpt":"We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning. NLMs exploit the power of both neural networks---as function approximators, and logic programming---as a symbolic processor for objects with properties, relations, logic connectives, and quantifiers. After being trained on small-scale tasks (such as sorting short arrays), NLMs can recover lifted rules, and generalize to large-scale tasks (such as sorting longer arrays). In our experiments, NLMs achieve perfect generalization in a number of tasks, from relational reasoning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11694","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":""},"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":"1904.11694","created_at":"2026-05-17T23:47:43.023364+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11694v1","created_at":"2026-05-17T23:47:43.023364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11694","created_at":"2026-05-17T23:47:43.023364+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCRAOYDOWKYM","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCRAOYDOWKYMC6NQ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCRAOYDO","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.12109","citing_title":"A Neuro-Symbolic Framework for Accountability in Public-Sector AI","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04243","citing_title":"Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2201.11903","citing_title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15623","citing_title":"Overmind NSA: A Unified Neuro-Symbolic Computing Architecture with Approximate Nonlinear Activations and Preemptive Memory Bypass","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5","json":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5.json","graph_json":"https://pith.science/api/pith-number/UCRAOYDOWKYMC6NQ7HJAPWZWC5/graph.json","events_json":"https://pith.science/api/pith-number/UCRAOYDOWKYMC6NQ7HJAPWZWC5/events.json","paper":"https://pith.science/paper/UCRAOYDO"},"agent_actions":{"view_html":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5","download_json":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5.json","view_paper":"https://pith.science/paper/UCRAOYDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11694&json=true","fetch_graph":"https://pith.science/api/pith-number/UCRAOYDOWKYMC6NQ7HJAPWZWC5/graph.json","fetch_events":"https://pith.science/api/pith-number/UCRAOYDOWKYMC6NQ7HJAPWZWC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5/action/storage_attestation","attest_author":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5/action/author_attestation","sign_citation":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5/action/citation_signature","submit_replication":"https://pith.science/pith/UCRAOYDOWKYMC6NQ7HJAPWZWC5/action/replication_record"}},"created_at":"2026-05-17T23:47:43.023364+00:00","updated_at":"2026-05-17T23:47:43.023364+00:00"}