{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MONTFCUERKAFZOQUPE6SWX6TPH","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":"4ac15cd245f97f1e1fd82f5044880de0a5b87fa09ae3b1a7fa991e043616d445","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T07:35:06Z","title_canon_sha256":"840009308f714c00eee9015b2f112a8fc033a04eaa0b50fb1ae8f6d4fb8a52b9"},"schema_version":"1.0","source":{"id":"2608.00494","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00494","created_at":"2026-08-04T00:37:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00494v1","created_at":"2026-08-04T00:37:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00494","created_at":"2026-08-04T00:37:03Z"},{"alias_kind":"pith_short_12","alias_value":"MONTFCUERKAF","created_at":"2026-08-04T00:37:03Z"},{"alias_kind":"pith_short_16","alias_value":"MONTFCUERKAFZOQU","created_at":"2026-08-04T00:37:03Z"},{"alias_kind":"pith_short_8","alias_value":"MONTFCUE","created_at":"2026-08-04T00:37:03Z"}],"graph_snapshots":[{"event_id":"sha256:b8c5a733c30646a778b255dad9f434dce158ad69f7d8270fd1a86ad64a388612","target":"graph","created_at":"2026-08-04T00:37:03Z","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/2608.00494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-turn code agents rely on execution feedback to repair incorrect programs, yet standard reinforcement learning paradigms optimize and evaluate policy performance primarily using single-shot outcome rewards. This misalignment conflates initial code generation with feedback-driven refinement, discards granular execution signals across intermediate turns, and fails to evaluate whether the policy actually acquires self-repair capabilities. We propose Test-aware Policy Refinement (TaPR), a framework that transforms execution feedback into a dense per-turn test-pass-ratio reward under a consist","authors_text":"Aofan Liu, Fangxin Liu, Jingxiang Meng, Yongbiao Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T07:35:06Z","title":"TaPR: Test-Aware Policy Refinement for Feedback-Conditioned Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00494","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":"sha256:0dea9aa864cd44db1a97ed079c90e0b27bf576b0946ae509784068e960b8febe","target":"record","created_at":"2026-08-04T00:37:03Z","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":"4ac15cd245f97f1e1fd82f5044880de0a5b87fa09ae3b1a7fa991e043616d445","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T07:35:06Z","title_canon_sha256":"840009308f714c00eee9015b2f112a8fc033a04eaa0b50fb1ae8f6d4fb8a52b9"},"schema_version":"1.0","source":{"id":"2608.00494","kind":"arxiv","version":1}},"canonical_sha256":"639b328a848a805cba14793d2b5fd379f6786fe87bd674ced0ceb11f2faccbbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"639b328a848a805cba14793d2b5fd379f6786fe87bd674ced0ceb11f2faccbbe","first_computed_at":"2026-08-04T00:37:03.153106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:37:03.153106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3PFyinM8Pa/2MG21JosGZBdifx8tVbOA5zer5srqxuj8blcrcVLIDQyNuDQlCC8K6vZeCGpuCamS1Z79jcXDg==","signature_status":"signed_v1","signed_at":"2026-08-04T00:37:03.154561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00494","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dea9aa864cd44db1a97ed079c90e0b27bf576b0946ae509784068e960b8febe","sha256:b8c5a733c30646a778b255dad9f434dce158ad69f7d8270fd1a86ad64a388612"],"state_sha256":"6a185f421ab931975ae118ec497e1f4454abbd53d60694d609b2771ed616d5f2"}