{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HKVC6FQENDBA7JPZ5ZOZX7BX2D","short_pith_number":"pith:HKVC6FQE","schema_version":"1.0","canonical_sha256":"3aaa2f160468c20fa5f9ee5d9bfc37d0c98979c7b7d0b28abffe442ea60f5c75","source":{"kind":"arxiv","id":"2501.18645","version":2},"attestation_state":"computed","paper":{"title":"Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Manish Sanwal","submitted_at":"2025-01-29T13:21:09Z","abstract_excerpt":"Large Language Models (LLMs) leverage chain-of-thought (CoT) prompting to provide step-by-step rationales, improving performance on complex tasks. Despite its benefits, vanilla CoT often fails to fully verify intermediate inferences and can produce misleading explanations. In this work, we propose Layered Chain-of-Thought (Layered-CoT) Prompting, a novel framework that systematically segments the reasoning process into multiple layers, each subjected to external checks and optional user feedback. We expand on the key concepts, present three scenarios -- medical triage, financial risk assessmen"},"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":"2501.18645","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T13:21:09Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1da37596d247582a7d5e612451e374ce4cea0eb1b6f536f9e2a326118cccd253","abstract_canon_sha256":"74a500953b0bacf5c7d130792ff73598ec7772dfc3b1f1a03b092c0ae3c68c80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:15.868240Z","signature_b64":"vw7hMR1mON3FyHWfPIs8RV1QKConCo+ct5K4balGawX36K4BsCZg5XKph8VNVVX6B2fg8hh4WaVNqjmzZA/3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aaa2f160468c20fa5f9ee5d9bfc37d0c98979c7b7d0b28abffe442ea60f5c75","last_reissued_at":"2026-07-05T10:09:15.867772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:15.867772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Manish Sanwal","submitted_at":"2025-01-29T13:21:09Z","abstract_excerpt":"Large Language Models (LLMs) leverage chain-of-thought (CoT) prompting to provide step-by-step rationales, improving performance on complex tasks. Despite its benefits, vanilla CoT often fails to fully verify intermediate inferences and can produce misleading explanations. In this work, we propose Layered Chain-of-Thought (Layered-CoT) Prompting, a novel framework that systematically segments the reasoning process into multiple layers, each subjected to external checks and optional user feedback. We expand on the key concepts, present three scenarios -- medical triage, financial risk assessmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18645","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/2501.18645/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":"2501.18645","created_at":"2026-07-05T10:09:15.867827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18645v2","created_at":"2026-07-05T10:09:15.867827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18645","created_at":"2026-07-05T10:09:15.867827+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKVC6FQENDBA","created_at":"2026-07-05T10:09:15.867827+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKVC6FQENDBA7JPZ","created_at":"2026-07-05T10:09:15.867827+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKVC6FQE","created_at":"2026-07-05T10:09:15.867827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.09544","citing_title":"MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13103","citing_title":"Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D","json":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D.json","graph_json":"https://pith.science/api/pith-number/HKVC6FQENDBA7JPZ5ZOZX7BX2D/graph.json","events_json":"https://pith.science/api/pith-number/HKVC6FQENDBA7JPZ5ZOZX7BX2D/events.json","paper":"https://pith.science/paper/HKVC6FQE"},"agent_actions":{"view_html":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D","download_json":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D.json","view_paper":"https://pith.science/paper/HKVC6FQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18645&json=true","fetch_graph":"https://pith.science/api/pith-number/HKVC6FQENDBA7JPZ5ZOZX7BX2D/graph.json","fetch_events":"https://pith.science/api/pith-number/HKVC6FQENDBA7JPZ5ZOZX7BX2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D/action/storage_attestation","attest_author":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D/action/author_attestation","sign_citation":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D/action/citation_signature","submit_replication":"https://pith.science/pith/HKVC6FQENDBA7JPZ5ZOZX7BX2D/action/replication_record"}},"created_at":"2026-07-05T10:09:15.867827+00:00","updated_at":"2026-07-05T10:09:15.867827+00:00"}