{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JB3SLP4SK7VBFMV52W6OSXYGVE","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":"f7c6c02e66e790af086fe589d83515305c3665a7cf5fdd12a0ec6241fd3b08ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-30T22:58:35Z","title_canon_sha256":"51d78bd84d95d785d125792044f688441e16d1da22beadbe5c1d0e8c7ebb90ac"},"schema_version":"1.0","source":{"id":"2506.00296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00296","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00296v1","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00296","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"JB3SLP4SK7VB","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"JB3SLP4SK7VBFMV5","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"JB3SLP4S","created_at":"2026-07-05T11:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:6ff61cf6edf8d31a5e446abf3956f279049400c80d95b75139ed3026f74439e5","target":"graph","created_at":"2026-07-05T11:13:32Z","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/2506.00296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and RL with AI Feedback (RLAIF), offer trade-offs: RLVR provides reliable feedback for structured tasks like code generation, while RLAIF works for unstructured outputs but is subjective. We bridge this gap with CRScore++, an RL framework that leverages both LLM-based subjective feedback and verifiable signals for training. Extending CRScore, a code review eval","authors_text":"Atharva Naik, Carolyn Rose, Manav Nitin Kapadnis","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-30T22:58:35Z","title":"CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00296","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":"sha256:34ca77d15383aca40bcd0f93af8ac3972bcf5cdcb843af51596d5cf55d611bde","target":"record","created_at":"2026-07-05T11:13:32Z","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":"f7c6c02e66e790af086fe589d83515305c3665a7cf5fdd12a0ec6241fd3b08ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-30T22:58:35Z","title_canon_sha256":"51d78bd84d95d785d125792044f688441e16d1da22beadbe5c1d0e8c7ebb90ac"},"schema_version":"1.0","source":{"id":"2506.00296","kind":"arxiv","version":1}},"canonical_sha256":"487725bf9257ea12b2bdd5bce95f06a92810f9dd2b80bca96978a92ef24260b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"487725bf9257ea12b2bdd5bce95f06a92810f9dd2b80bca96978a92ef24260b4","first_computed_at":"2026-07-05T11:13:32.247942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:32.247942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kYWsv0ZW1+DUBtxc1fq1QB+sDknshYDLC6eqip2QB8GxP/C6NNWLRK94WiXugxd0WQ5ag5lND/qbkNKc+x8kCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:32.248379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34ca77d15383aca40bcd0f93af8ac3972bcf5cdcb843af51596d5cf55d611bde","sha256:6ff61cf6edf8d31a5e446abf3956f279049400c80d95b75139ed3026f74439e5"],"state_sha256":"c1c508870fc36b299de74efa33b4b024da253793a1d71014325afacdc4bc6ee8"}