{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U4FQP4QWNBZ233IUD3EOTWRKWV","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":"ea4941bbfb396b081f079d18fd0e94558056c4da40267e73caa22decf2518ff8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T19:15:50Z","title_canon_sha256":"f82f61d02a7f64076c557c4aaf4981e0fc17a9916caa6d126b17168c58253540"},"schema_version":"1.0","source":{"id":"2606.20881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20881","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20881v1","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20881","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"pith_short_12","alias_value":"U4FQP4QWNBZ2","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"pith_short_16","alias_value":"U4FQP4QWNBZ233IU","created_at":"2026-06-23T00:12:01Z"},{"alias_kind":"pith_short_8","alias_value":"U4FQP4QW","created_at":"2026-06-23T00:12:01Z"}],"graph_snapshots":[{"event_id":"sha256:3476f7d1cf429d0bcd764b12a898f36f180a94def39196989203f446b459ff87","target":"graph","created_at":"2026-06-23T00:12:01Z","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/2606.20881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in large language model reasoning, but relies on ground-truth supervision that is costly or infeasible, especially in coding tasks. Recent work addresses this by deriving rewards from a model's own signals, such as majority voting or confidence-based scores, achieving notable success on mathematical reasoning benchmarks. However, code generation poses distinct challenges: programs are structurally complex, semantically equivalent solutions may differ syntactically, and verification typically requires executio","authors_text":"Dawn Song, Wenbo Guo, Xiangyu Zhang, Xiaolong Jin, Xuandong Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T19:15:50Z","title":"When Do Intrinsic Rewards Work for Code Reasoning? A Comprehensive Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20881","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":"sha256:6e3267822faf84e04f093667e9557503ed9364014335dc0cf5dddcb3503c12ac","target":"record","created_at":"2026-06-23T00:12:01Z","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":"ea4941bbfb396b081f079d18fd0e94558056c4da40267e73caa22decf2518ff8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T19:15:50Z","title_canon_sha256":"f82f61d02a7f64076c557c4aaf4981e0fc17a9916caa6d126b17168c58253540"},"schema_version":"1.0","source":{"id":"2606.20881","kind":"arxiv","version":1}},"canonical_sha256":"a70b07f2166873aded141ec8e9da2ab5769e190e2ea93d1a081fc85d543b7c93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a70b07f2166873aded141ec8e9da2ab5769e190e2ea93d1a081fc85d543b7c93","first_computed_at":"2026-06-23T00:12:01.623424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:12:01.623424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h3/WrBjLCN/+cgH+RrPX8KJHPr0vM+PUouR9yYAE0hl+PUTDVh/zVZjnrIIb3tTiYrlkO5f/b7lI714+/DuxAA==","signature_status":"signed_v1","signed_at":"2026-06-23T00:12:01.623848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e3267822faf84e04f093667e9557503ed9364014335dc0cf5dddcb3503c12ac","sha256:3476f7d1cf429d0bcd764b12a898f36f180a94def39196989203f446b459ff87"],"state_sha256":"c34d95d505af5ed10bb96d7dec6e9445ba3a8d3041d41f5390925574041a535d"}