{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CDH7ZATWULWSLJECB5UVFIOWRE","short_pith_number":"pith:CDH7ZATW","schema_version":"1.0","canonical_sha256":"10cffc8276a2ed25a4820f6952a1d689323d6b449b027cc0b3c2b1812dbb4bf8","source":{"kind":"arxiv","id":"2201.06515","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Rule Induction with Learned Relational Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Christian de Sainte Marie, Marine Collery, Remy Kusters, Shubham Gupta, Yusik Kim","submitted_at":"2022-01-17T16:46:50Z","abstract_excerpt":"Rule-based decision models are attractive due to their interpretability. However, existing rule induction methods often result in long and consequently less interpretable rule models. This problem can often be attributed to the lack of appropriately expressive vocabulary, i.e., relevant predicates used as literals in the decision model. Most existing rule induction algorithms presume pre-defined literals, naturally decoupling the definition of the literals from the rule learning phase. In contrast, we propose the Relational Rule Network (R2N), a neural architecture that learns literals that re"},"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":"2201.06515","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-01-17T16:46:50Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"d73cb978d0c6a56c9bf2913600b3999b2eb8889816fcfe3bb9e972da2a582607","abstract_canon_sha256":"150bd105f715111ead724d0618a6cdf84c30bc9c09ebc8bdc8fa22e7cfb9af3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:19.677499Z","signature_b64":"pbyhCN6xWBEdIFIwGNj4cIfQUSAAXdKAlSuI+4Ftutey1IYgN9nbcK/gYdQZcD34BStBugIINu2ttdqs+oyWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10cffc8276a2ed25a4820f6952a1d689323d6b449b027cc0b3c2b1812dbb4bf8","last_reissued_at":"2026-07-05T04:44:19.676986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:19.676986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Rule Induction with Learned Relational Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Christian de Sainte Marie, Marine Collery, Remy Kusters, Shubham Gupta, Yusik Kim","submitted_at":"2022-01-17T16:46:50Z","abstract_excerpt":"Rule-based decision models are attractive due to their interpretability. However, existing rule induction methods often result in long and consequently less interpretable rule models. This problem can often be attributed to the lack of appropriately expressive vocabulary, i.e., relevant predicates used as literals in the decision model. Most existing rule induction algorithms presume pre-defined literals, naturally decoupling the definition of the literals from the rule learning phase. In contrast, we propose the Relational Rule Network (R2N), a neural architecture that learns literals that re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06515","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.06515/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":"2201.06515","created_at":"2026-07-05T04:44:19.677057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.06515v2","created_at":"2026-07-05T04:44:19.677057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06515","created_at":"2026-07-05T04:44:19.677057+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDH7ZATWULWS","created_at":"2026-07-05T04:44:19.677057+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDH7ZATWULWSLJEC","created_at":"2026-07-05T04:44:19.677057+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDH7ZATW","created_at":"2026-07-05T04:44:19.677057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.21663","citing_title":"Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE","json":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE.json","graph_json":"https://pith.science/api/pith-number/CDH7ZATWULWSLJECB5UVFIOWRE/graph.json","events_json":"https://pith.science/api/pith-number/CDH7ZATWULWSLJECB5UVFIOWRE/events.json","paper":"https://pith.science/paper/CDH7ZATW"},"agent_actions":{"view_html":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE","download_json":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE.json","view_paper":"https://pith.science/paper/CDH7ZATW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.06515&json=true","fetch_graph":"https://pith.science/api/pith-number/CDH7ZATWULWSLJECB5UVFIOWRE/graph.json","fetch_events":"https://pith.science/api/pith-number/CDH7ZATWULWSLJECB5UVFIOWRE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE/action/storage_attestation","attest_author":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE/action/author_attestation","sign_citation":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE/action/citation_signature","submit_replication":"https://pith.science/pith/CDH7ZATWULWSLJECB5UVFIOWRE/action/replication_record"}},"created_at":"2026-07-05T04:44:19.677057+00:00","updated_at":"2026-07-05T04:44:19.677057+00:00"}