{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZSECQMXWOASIOESPBFO6JQLVIB","short_pith_number":"pith:ZSECQMXW","schema_version":"1.0","canonical_sha256":"cc882832f6702487124f095de4c175404bf1444485084e35163444d0a50cc6a6","source":{"kind":"arxiv","id":"2402.06457","version":2},"attestation_state":"computed","paper":{"title":"V-STaR: Training Verifiers for Self-Taught Reasoners","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Alessandro Sordoni, Arian Hosseini, Nikolay Malkin, Rishabh Agarwal, Xingdi Yuan","submitted_at":"2024-02-09T15:02:56Z","abstract_excerpt":"Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is us"},"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":"2402.06457","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T15:02:56Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"81ce3e176326d5c2742d6facd25a0701da7de5d6358c1cd98c9d28da7e49593c","abstract_canon_sha256":"3d3972f906d78cfd62f3984698a1a4326edcdf10c6af2744edd1c7e80d98d4dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:07.885226Z","signature_b64":"/kcF8AYmbfgdmAJ6V2CpLKBwnw+VvYao40/jOl/1RMlBzTIDqZFc7yn06dN8jtK5xhWKJzEJjRlP8PL+fE4VCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc882832f6702487124f095de4c175404bf1444485084e35163444d0a50cc6a6","last_reissued_at":"2026-07-05T08:55:07.884739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:07.884739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V-STaR: Training Verifiers for Self-Taught Reasoners","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Alessandro Sordoni, Arian Hosseini, Nikolay Malkin, Rishabh Agarwal, Xingdi Yuan","submitted_at":"2024-02-09T15:02:56Z","abstract_excerpt":"Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06457","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/2402.06457/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":"2402.06457","created_at":"2026-07-05T08:55:07.884798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06457v2","created_at":"2026-07-05T08:55:07.884798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06457","created_at":"2026-07-05T08:55:07.884798+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSECQMXWOASI","created_at":"2026-07-05T08:55:07.884798+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSECQMXWOASIOESP","created_at":"2026-07-05T08:55:07.884798+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSECQMXW","created_at":"2026-07-05T08:55:07.884798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24937","citing_title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","ref_index":245,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24790","citing_title":"Grad Detect: Gradient-Based Hallucination Detection in LLMs","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21792","citing_title":"Residual Skill Optimization for Text-to-SQL Ensembles","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22675","citing_title":"Self-Policy Distillation via Capability-Selective Subspace Projection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2410.08146","citing_title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17352","citing_title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14445","citing_title":"FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2412.21187","citing_title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01474","citing_title":"ReMedi: Reasoner for Medical Clinical Prediction","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21138","citing_title":"Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB","json":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB.json","graph_json":"https://pith.science/api/pith-number/ZSECQMXWOASIOESPBFO6JQLVIB/graph.json","events_json":"https://pith.science/api/pith-number/ZSECQMXWOASIOESPBFO6JQLVIB/events.json","paper":"https://pith.science/paper/ZSECQMXW"},"agent_actions":{"view_html":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB","download_json":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB.json","view_paper":"https://pith.science/paper/ZSECQMXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06457&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSECQMXWOASIOESPBFO6JQLVIB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSECQMXWOASIOESPBFO6JQLVIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB/action/storage_attestation","attest_author":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB/action/author_attestation","sign_citation":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB/action/citation_signature","submit_replication":"https://pith.science/pith/ZSECQMXWOASIOESPBFO6JQLVIB/action/replication_record"}},"created_at":"2026-07-05T08:55:07.884798+00:00","updated_at":"2026-07-05T08:55:07.884798+00:00"}