{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S3J27AACTNZKH7GT3SIA2UMFMH","short_pith_number":"pith:S3J27AAC","schema_version":"1.0","canonical_sha256":"96d3af80029b72a3fcd3dc900d518561f641897d295b7f0852a767ee6562b5fb","source":{"kind":"arxiv","id":"2204.13570","version":1},"attestation_state":"computed","paper":{"title":"Learning First-Order Rules with Differentiable Logic Program Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanpin Wang, Katsumi Inoue, Kun Gao, Yongzhi Cao","submitted_at":"2022-04-28T15:33:43Z","abstract_excerpt":"Learning first-order logic programs (LPs) from relational facts which yields intuitive insights into the data is a challenging topic in neuro-symbolic research. We introduce a novel differentiable inductive logic programming (ILP) model, called differentiable first-order rule learner (DFOL), which finds the correct LPs from relational facts by searching for the interpretable matrix representations of LPs. These interpretable matrices are deemed as trainable tensors in neural networks (NNs). The NNs are devised according to the differentiable semantics of LPs. Specifically, we first adopt a nov"},"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":"2204.13570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-04-28T15:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"fdad1e240a069b7cc3fe55aa3d5d57bfa9177d2aae80583da6cb1479b2f243a8","abstract_canon_sha256":"a3e7b535e9e09473db58323253b5904e1c6e20d9a0cf4945e610d52fde37bb5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:43.619032Z","signature_b64":"gw6VWjJQWr0+Cq2RDuo+TS975pAVT4EnHrQeLw8ivEhjQ4+k+D0fnI2bOnXZStwjjmwx3m+zZ5duD6MqB2LMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96d3af80029b72a3fcd3dc900d518561f641897d295b7f0852a767ee6562b5fb","last_reissued_at":"2026-07-05T04:18:43.618634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:43.618634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning First-Order Rules with Differentiable Logic Program Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanpin Wang, Katsumi Inoue, Kun Gao, Yongzhi Cao","submitted_at":"2022-04-28T15:33:43Z","abstract_excerpt":"Learning first-order logic programs (LPs) from relational facts which yields intuitive insights into the data is a challenging topic in neuro-symbolic research. We introduce a novel differentiable inductive logic programming (ILP) model, called differentiable first-order rule learner (DFOL), which finds the correct LPs from relational facts by searching for the interpretable matrix representations of LPs. These interpretable matrices are deemed as trainable tensors in neural networks (NNs). The NNs are devised according to the differentiable semantics of LPs. Specifically, we first adopt a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13570","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/2204.13570/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":"2204.13570","created_at":"2026-07-05T04:18:43.618692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.13570v1","created_at":"2026-07-05T04:18:43.618692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13570","created_at":"2026-07-05T04:18:43.618692+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3J27AACTNZK","created_at":"2026-07-05T04:18:43.618692+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3J27AACTNZKH7GT","created_at":"2026-07-05T04:18:43.618692+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3J27AAC","created_at":"2026-07-05T04:18:43.618692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH","json":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH.json","graph_json":"https://pith.science/api/pith-number/S3J27AACTNZKH7GT3SIA2UMFMH/graph.json","events_json":"https://pith.science/api/pith-number/S3J27AACTNZKH7GT3SIA2UMFMH/events.json","paper":"https://pith.science/paper/S3J27AAC"},"agent_actions":{"view_html":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH","download_json":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH.json","view_paper":"https://pith.science/paper/S3J27AAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.13570&json=true","fetch_graph":"https://pith.science/api/pith-number/S3J27AACTNZKH7GT3SIA2UMFMH/graph.json","fetch_events":"https://pith.science/api/pith-number/S3J27AACTNZKH7GT3SIA2UMFMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH/action/storage_attestation","attest_author":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH/action/author_attestation","sign_citation":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH/action/citation_signature","submit_replication":"https://pith.science/pith/S3J27AACTNZKH7GT3SIA2UMFMH/action/replication_record"}},"created_at":"2026-07-05T04:18:43.618692+00:00","updated_at":"2026-07-05T04:18:43.618692+00:00"}