{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ACNRNWVUDXC4SQR6P3AMG5R2GA","short_pith_number":"pith:ACNRNWVU","schema_version":"1.0","canonical_sha256":"009b16dab41dc5c9423e7ec0c3763a3008daa6d6e04df8a2cf61eddefa7f74b1","source":{"kind":"arxiv","id":"2501.02026","version":1},"attestation_state":"computed","paper":{"title":"Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.LO"],"primary_cat":"cs.CL","authors_text":"Ateeq Ur Rehman Butt, Jiashu Zhang, Kaleem Ullah Qasim, Tariq Alsahfi","submitted_at":"2025-01-03T02:55:44Z","abstract_excerpt":"Enhancing the reasoning capabilities of Large Language Models remains a critical challenge in artificial intelligence. We introduce RDoLT, Recursive Decomposition of Logical Thought prompting, a novel framework that significantly boosts LLM reasoning performance. RDoLT is built on three key innovations: (1) recursively breaking down complex reasoning tasks into sub-tasks of progressive complexity; (2) employing an advanced selection and scoring mechanism to identify the most promising reasoning thoughts; and (3) integrating a knowledge propagation module that mimics human learning by keeping t"},"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":"2501.02026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T02:55:44Z","cross_cats_sorted":["cs.AI","cs.LG","cs.LO"],"title_canon_sha256":"4833975575dd74f01487bf5db7dd9aaf3d93d95c76ac58921d7c8064dab2b44d","abstract_canon_sha256":"64c34ebef3cb74943ac04b0b84b02f3ac1f9a23a06defdc9e3f04ca0e9ca33e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:00.462680Z","signature_b64":"Vw9lYAv1Fhjzbfbie2yA8/GcLP8QEM9QXi0AVNQHwmptmgsrSCwJol4nIYJ28YWLfALBYE6To3hqthAPIx9jDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"009b16dab41dc5c9423e7ec0c3763a3008daa6d6e04df8a2cf61eddefa7f74b1","last_reissued_at":"2026-07-05T09:57:00.462255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:00.462255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.LO"],"primary_cat":"cs.CL","authors_text":"Ateeq Ur Rehman Butt, Jiashu Zhang, Kaleem Ullah Qasim, Tariq Alsahfi","submitted_at":"2025-01-03T02:55:44Z","abstract_excerpt":"Enhancing the reasoning capabilities of Large Language Models remains a critical challenge in artificial intelligence. We introduce RDoLT, Recursive Decomposition of Logical Thought prompting, a novel framework that significantly boosts LLM reasoning performance. RDoLT is built on three key innovations: (1) recursively breaking down complex reasoning tasks into sub-tasks of progressive complexity; (2) employing an advanced selection and scoring mechanism to identify the most promising reasoning thoughts; and (3) integrating a knowledge propagation module that mimics human learning by keeping t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02026","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/2501.02026/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":"2501.02026","created_at":"2026-07-05T09:57:00.462310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02026v1","created_at":"2026-07-05T09:57:00.462310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02026","created_at":"2026-07-05T09:57:00.462310+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACNRNWVUDXC4","created_at":"2026-07-05T09:57:00.462310+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACNRNWVUDXC4SQR6","created_at":"2026-07-05T09:57:00.462310+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACNRNWVU","created_at":"2026-07-05T09:57:00.462310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04893","citing_title":"MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA","json":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA.json","graph_json":"https://pith.science/api/pith-number/ACNRNWVUDXC4SQR6P3AMG5R2GA/graph.json","events_json":"https://pith.science/api/pith-number/ACNRNWVUDXC4SQR6P3AMG5R2GA/events.json","paper":"https://pith.science/paper/ACNRNWVU"},"agent_actions":{"view_html":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA","download_json":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA.json","view_paper":"https://pith.science/paper/ACNRNWVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02026&json=true","fetch_graph":"https://pith.science/api/pith-number/ACNRNWVUDXC4SQR6P3AMG5R2GA/graph.json","fetch_events":"https://pith.science/api/pith-number/ACNRNWVUDXC4SQR6P3AMG5R2GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA/action/storage_attestation","attest_author":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA/action/author_attestation","sign_citation":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA/action/citation_signature","submit_replication":"https://pith.science/pith/ACNRNWVUDXC4SQR6P3AMG5R2GA/action/replication_record"}},"created_at":"2026-07-05T09:57:00.462310+00:00","updated_at":"2026-07-05T09:57:00.462310+00:00"}