{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GTYZLGW6BXCIL53K4TD3TXQ24K","short_pith_number":"pith:GTYZLGW6","schema_version":"1.0","canonical_sha256":"34f1959ade0dc485f76ae4c7b9de1ae29e775aeb5ee07efe3ecb83d1a2a81a69","source":{"kind":"arxiv","id":"2502.14333","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haowei Liu, Ting-Ruen Wei, Xuyang Wu, Yi Fang","submitted_at":"2025-02-20T07:31:00Z","abstract_excerpt":"Recent progress in large language models (LLM) found chain-of-thought prompting strategies to improve the reasoning ability of LLMs by encouraging problem solving through multiple steps. Therefore, subsequent research aimed to integrate the multi-step reasoning process into the LLM itself through process rewards as feedback and achieved improvements over prompting strategies. Due to the cost of step-level annotation, some turn to outcome rewards as feedback. Aside from these training-based approaches, training-free techniques leverage frozen LLMs or external tools for feedback at each step to "},"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":"2502.14333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T07:31:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a4a974e3df6144e8d8f5eeb9ae163b99f583fb610bece39c5c239140bbb9356","abstract_canon_sha256":"a2e353805427aaa9af8290bb90a6c82c36589c1a73018927917c1d4d2211435e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:24.608498Z","signature_b64":"9+EhZ4IhC8uAuunpcELEBq4653OGeF4HC1QpjkNRtuM3zKtEFuPefA2fGGqWp/CtSn+e6UzrF4r9UoJLrJi/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f1959ade0dc485f76ae4c7b9de1ae29e775aeb5ee07efe3ecb83d1a2a81a69","last_reissued_at":"2026-07-05T10:17:24.608083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:24.608083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haowei Liu, Ting-Ruen Wei, Xuyang Wu, Yi Fang","submitted_at":"2025-02-20T07:31:00Z","abstract_excerpt":"Recent progress in large language models (LLM) found chain-of-thought prompting strategies to improve the reasoning ability of LLMs by encouraging problem solving through multiple steps. Therefore, subsequent research aimed to integrate the multi-step reasoning process into the LLM itself through process rewards as feedback and achieved improvements over prompting strategies. Due to the cost of step-level annotation, some turn to outcome rewards as feedback. Aside from these training-based approaches, training-free techniques leverage frozen LLMs or external tools for feedback at each step to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14333","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/2502.14333/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":"2502.14333","created_at":"2026-07-05T10:17:24.608137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14333v1","created_at":"2026-07-05T10:17:24.608137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14333","created_at":"2026-07-05T10:17:24.608137+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTYZLGW6BXCI","created_at":"2026-07-05T10:17:24.608137+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTYZLGW6BXCIL53K","created_at":"2026-07-05T10:17:24.608137+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTYZLGW6","created_at":"2026-07-05T10:17:24.608137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":217,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08299","citing_title":"SeLaR: Selective Latent Reasoning in Large Language Models","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K","json":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K.json","graph_json":"https://pith.science/api/pith-number/GTYZLGW6BXCIL53K4TD3TXQ24K/graph.json","events_json":"https://pith.science/api/pith-number/GTYZLGW6BXCIL53K4TD3TXQ24K/events.json","paper":"https://pith.science/paper/GTYZLGW6"},"agent_actions":{"view_html":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K","download_json":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K.json","view_paper":"https://pith.science/paper/GTYZLGW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14333&json=true","fetch_graph":"https://pith.science/api/pith-number/GTYZLGW6BXCIL53K4TD3TXQ24K/graph.json","fetch_events":"https://pith.science/api/pith-number/GTYZLGW6BXCIL53K4TD3TXQ24K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K/action/storage_attestation","attest_author":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K/action/author_attestation","sign_citation":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K/action/citation_signature","submit_replication":"https://pith.science/pith/GTYZLGW6BXCIL53K4TD3TXQ24K/action/replication_record"}},"created_at":"2026-07-05T10:17:24.608137+00:00","updated_at":"2026-07-05T10:17:24.608137+00:00"}