{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6A6P7AVRLQJPFUS3V2UWQC3GBY","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":"8ce0b670209cf4799d250bdc6d69a16473cfad3679f68a0e259890a7595ecd4a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T18:55:05Z","title_canon_sha256":"bfb5e0449780e480126b66a8cac4fa6eaaefcafd84d433d75655f53b0313ec2e"},"schema_version":"1.0","source":{"id":"2502.20380","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20380","created_at":"2026-07-05T11:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20380v2","created_at":"2026-07-05T11:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20380","created_at":"2026-07-05T11:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"6A6P7AVRLQJP","created_at":"2026-07-05T11:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"6A6P7AVRLQJPFUS3","created_at":"2026-07-05T11:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"6A6P7AVR","created_at":"2026-07-05T11:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:5b599cb90bd1adb20ba046a5eb88065ae13ffdd1f503613b99c0a053754c2b1d","target":"graph","created_at":"2026-07-05T11:28:14Z","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/2502.20380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of code generation from multi-turn execution feedback. Existing methods either generate code without feedback or use complex, hierarchical reinforcement learning to optimize multi-turn rewards. We propose a simple yet scalable approach, $\\mu$Code, that solves multi-turn code generation using only single-step rewards. Our key insight is that code generation is a one-step recoverable MDP, where the correct code can be recovered from any intermediate code state in a single turn. $\\mu$Code iteratively trains both a generator to provide code solutions conditioned on multi-tur","authors_text":"Alexander M Rush, Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Sanjiban Choudhury, Wayne Chen, Wenting Zhao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T18:55:05Z","title":"Multi-Turn Code Generation Through Single-Step Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20380","kind":"arxiv","version":2},"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:cb53695dfb798c72bd75a6a04f6cf1df309ee5289010caae0e0e55fb398cd5f6","target":"record","created_at":"2026-07-05T11:28:14Z","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":"8ce0b670209cf4799d250bdc6d69a16473cfad3679f68a0e259890a7595ecd4a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T18:55:05Z","title_canon_sha256":"bfb5e0449780e480126b66a8cac4fa6eaaefcafd84d433d75655f53b0313ec2e"},"schema_version":"1.0","source":{"id":"2502.20380","kind":"arxiv","version":2}},"canonical_sha256":"f03cff82b15c12f2d25baea9680b660e3f6f38c6a9ab5a89e8e6fe74236f05b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f03cff82b15c12f2d25baea9680b660e3f6f38c6a9ab5a89e8e6fe74236f05b9","first_computed_at":"2026-07-05T11:28:14.668614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:14.668614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TShZL8BI5JX4AkcDC6xvnpBmm8jRZ+kko1zMqEQg/pzgT+3mOj1YzxaSOV1+Qz1GZYq4/boA65Vo4HggiEOUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:14.669039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20380","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb53695dfb798c72bd75a6a04f6cf1df309ee5289010caae0e0e55fb398cd5f6","sha256:5b599cb90bd1adb20ba046a5eb88065ae13ffdd1f503613b99c0a053754c2b1d"],"state_sha256":"e7a2c93c9ee4458a715b926e1214ad5fb08ffb5763dcd862d7071702efa3093c"}