{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MJWNTKKP3L3RXJXAO3A3WI4KDA","short_pith_number":"pith:MJWNTKKP","schema_version":"1.0","canonical_sha256":"626cd9a94fdaf71ba6e076c1bb238a180f45d33884f9f22ca9202a9f6cd4a684","source":{"kind":"arxiv","id":"2510.19698","version":3},"attestation_state":"computed","paper":{"title":"RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hua Xu, Yang Yang, Yutao Yue, Zhangyi Hu","submitted_at":"2025-10-22T15:50:04Z","abstract_excerpt":"Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule learning. Yet many LLM-based approaches ignore interactions among rules, and the opportunity to couple LLMs with probabilistic rule learning for robust inference remains underexplored. We present RLIE, a unified framework that integrates LLMs with probabilistic modeling to learn a set of weighted rules. RLIE has four stages: (1) Rule generation, where an LLM proposes and filters candidates; (2) Logistic regression, which learns probabilistic weights for"},"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":"2510.19698","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-22T15:50:04Z","cross_cats_sorted":[],"title_canon_sha256":"439ed8abb3a595c2b76b9ae80f665d1b7c5d86e0ac5fa7e8ef68312abc71a73c","abstract_canon_sha256":"38e10138373c80a0368e4a55d7ff2501d29563bf2310a21b0693d6984de9b573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:12.336435Z","signature_b64":"o3so7jfqsPLSpOUourpcaGWkx7ZscA7usfvuKrKq/dcsyMX/t3iKYrMx3gp0u68Ri/DjvGJqfTresqArlWmQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"626cd9a94fdaf71ba6e076c1bb238a180f45d33884f9f22ca9202a9f6cd4a684","last_reissued_at":"2026-07-07T02:17:12.335497Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:12.335497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hua Xu, Yang Yang, Yutao Yue, Zhangyi Hu","submitted_at":"2025-10-22T15:50:04Z","abstract_excerpt":"Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule learning. Yet many LLM-based approaches ignore interactions among rules, and the opportunity to couple LLMs with probabilistic rule learning for robust inference remains underexplored. We present RLIE, a unified framework that integrates LLMs with probabilistic modeling to learn a set of weighted rules. RLIE has four stages: (1) Rule generation, where an LLM proposes and filters candidates; (2) Logistic regression, which learns probabilistic weights for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.19698","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.19698/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":"2510.19698","created_at":"2026-07-07T02:17:12.335597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.19698v3","created_at":"2026-07-07T02:17:12.335597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.19698","created_at":"2026-07-07T02:17:12.335597+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJWNTKKP3L3R","created_at":"2026-07-07T02:17:12.335597+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJWNTKKP3L3RXJXA","created_at":"2026-07-07T02:17:12.335597+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJWNTKKP","created_at":"2026-07-07T02:17:12.335597+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/MJWNTKKP3L3RXJXAO3A3WI4KDA","json":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA.json","graph_json":"https://pith.science/api/pith-number/MJWNTKKP3L3RXJXAO3A3WI4KDA/graph.json","events_json":"https://pith.science/api/pith-number/MJWNTKKP3L3RXJXAO3A3WI4KDA/events.json","paper":"https://pith.science/paper/MJWNTKKP"},"agent_actions":{"view_html":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA","download_json":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA.json","view_paper":"https://pith.science/paper/MJWNTKKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.19698&json=true","fetch_graph":"https://pith.science/api/pith-number/MJWNTKKP3L3RXJXAO3A3WI4KDA/graph.json","fetch_events":"https://pith.science/api/pith-number/MJWNTKKP3L3RXJXAO3A3WI4KDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA/action/storage_attestation","attest_author":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA/action/author_attestation","sign_citation":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA/action/citation_signature","submit_replication":"https://pith.science/pith/MJWNTKKP3L3RXJXAO3A3WI4KDA/action/replication_record"}},"created_at":"2026-07-07T02:17:12.335597+00:00","updated_at":"2026-07-07T02:17:12.335597+00:00"}