{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7JWZCKSNFMVWAJGWSKAT5AXQWU","short_pith_number":"pith:7JWZCKSN","schema_version":"1.0","canonical_sha256":"fa6d912a4d2b2b6024d692813e82f0b5049297690cced42737931c47a7ae449a","source":{"kind":"arxiv","id":"2402.11452","version":1},"attestation_state":"computed","paper":{"title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhiksha Raj, Huaxiu Yao, Ruiqi Zhang, Xiang Li, Zhaorun Chen, Zhihong Zhu, Zhuokai Zhao","submitted_at":"2024-02-18T04:28:16Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this challenge, in this paper, we propose a novel self-supervised framework AutoPRM that efficiently enhances the fine-tuning of LLMs for intricate reasoning challenges. Specifically, AutoPRM first decomposes complex problems into more manageable subquestions with a controllable granularity switch, then sequentially apply reinforcement learning to iteratively improve the "},"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":"2402.11452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T04:28:16Z","cross_cats_sorted":[],"title_canon_sha256":"cf47666b50feac96bd05356caef30a64f0a4761cfce1b8ee6cd2585a56767de3","abstract_canon_sha256":"68e354a11c450dc850180ef2c6a7d15a7a2796d191d804c463fb251d468a7da3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:39.221200Z","signature_b64":"M6A4maYhgP7sECR6Qnk8+KMw1GsX5U8FnzXMTSNTNSXKYX4osGuPcLFFlyAHucqE/BBuBnW7N0elFm8EGcK4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa6d912a4d2b2b6024d692813e82f0b5049297690cced42737931c47a7ae449a","last_reissued_at":"2026-07-05T07:46:39.220791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:39.220791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhiksha Raj, Huaxiu Yao, Ruiqi Zhang, Xiang Li, Zhaorun Chen, Zhihong Zhu, Zhuokai Zhao","submitted_at":"2024-02-18T04:28:16Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this challenge, in this paper, we propose a novel self-supervised framework AutoPRM that efficiently enhances the fine-tuning of LLMs for intricate reasoning challenges. Specifically, AutoPRM first decomposes complex problems into more manageable subquestions with a controllable granularity switch, then sequentially apply reinforcement learning to iteratively improve the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11452","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/2402.11452/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":"2402.11452","created_at":"2026-07-05T07:46:39.220850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11452v1","created_at":"2026-07-05T07:46:39.220850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11452","created_at":"2026-07-05T07:46:39.220850+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JWZCKSNFMVW","created_at":"2026-07-05T07:46:39.220850+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JWZCKSNFMVWAJGW","created_at":"2026-07-05T07:46:39.220850+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JWZCKSN","created_at":"2026-07-05T07:46:39.220850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00606","citing_title":"Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU","json":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU.json","graph_json":"https://pith.science/api/pith-number/7JWZCKSNFMVWAJGWSKAT5AXQWU/graph.json","events_json":"https://pith.science/api/pith-number/7JWZCKSNFMVWAJGWSKAT5AXQWU/events.json","paper":"https://pith.science/paper/7JWZCKSN"},"agent_actions":{"view_html":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU","download_json":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU.json","view_paper":"https://pith.science/paper/7JWZCKSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11452&json=true","fetch_graph":"https://pith.science/api/pith-number/7JWZCKSNFMVWAJGWSKAT5AXQWU/graph.json","fetch_events":"https://pith.science/api/pith-number/7JWZCKSNFMVWAJGWSKAT5AXQWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU/action/storage_attestation","attest_author":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU/action/author_attestation","sign_citation":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU/action/citation_signature","submit_replication":"https://pith.science/pith/7JWZCKSNFMVWAJGWSKAT5AXQWU/action/replication_record"}},"created_at":"2026-07-05T07:46:39.220850+00:00","updated_at":"2026-07-05T07:46:39.220850+00:00"}