{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7JWZCKSNFMVWAJGWSKAT5AXQWU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"68e354a11c450dc850180ef2c6a7d15a7a2796d191d804c463fb251d468a7da3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T04:28:16Z","title_canon_sha256":"cf47666b50feac96bd05356caef30a64f0a4761cfce1b8ee6cd2585a56767de3"},"schema_version":"1.0","source":{"id":"2402.11452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11452","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11452v1","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11452","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"pith_short_12","alias_value":"7JWZCKSNFMVW","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"pith_short_16","alias_value":"7JWZCKSNFMVWAJGW","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"pith_short_8","alias_value":"7JWZCKSN","created_at":"2026-07-05T07:46:39Z"}],"graph_snapshots":[{"event_id":"sha256:c4d02b570d5e30223602950738fb85004c324988f8cc8b05be1f891ffb4be68a","target":"graph","created_at":"2026-07-05T07:46:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.11452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Bhiksha Raj, Huaxiu Yao, Ruiqi Zhang, Xiang Li, Zhaorun Chen, Zhihong Zhu, Zhuokai Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T04:28:16Z","title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11452","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:47b0837ae27317616a5bebf098d9bb809ba1d142041fbea58e608eb7f718b462","target":"record","created_at":"2026-07-05T07:46:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"68e354a11c450dc850180ef2c6a7d15a7a2796d191d804c463fb251d468a7da3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T04:28:16Z","title_canon_sha256":"cf47666b50feac96bd05356caef30a64f0a4761cfce1b8ee6cd2585a56767de3"},"schema_version":"1.0","source":{"id":"2402.11452","kind":"arxiv","version":1}},"canonical_sha256":"fa6d912a4d2b2b6024d692813e82f0b5049297690cced42737931c47a7ae449a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa6d912a4d2b2b6024d692813e82f0b5049297690cced42737931c47a7ae449a","first_computed_at":"2026-07-05T07:46:39.220791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:39.220791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M6A4maYhgP7sECR6Qnk8+KMw1GsX5U8FnzXMTSNTNSXKYX4osGuPcLFFlyAHucqE/BBuBnW7N0elFm8EGcK4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:39.221200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47b0837ae27317616a5bebf098d9bb809ba1d142041fbea58e608eb7f718b462","sha256:c4d02b570d5e30223602950738fb85004c324988f8cc8b05be1f891ffb4be68a"],"state_sha256":"94c6b7dc7134a94d2be683c7f7c4286733c875c952545fe1972c229f5cf7f575"}