{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UCL75T4JFHD3XYJEDK3KAZV5NT","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":"35cf03329c8d0d94f3e2f36cd46c218bec7a9a330f7917348892f6e1efa1c935","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T17:56:00Z","title_canon_sha256":"a01681e96c3db43a12e4edc52772fa822672880f07cf4fd1b73137b2386e4be2"},"schema_version":"1.0","source":{"id":"2602.17684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17684","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17684v2","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17684","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"UCL75T4JFHD3","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"UCL75T4JFHD3XYJE","created_at":"2026-05-20T00:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"UCL75T4J","created_at":"2026-05-20T00:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:42d23dab7ab9d033f1d983c8037b9f99783c59200da56a641d1382ec10101661","target":"graph","created_at":"2026-05-20T00:04:26Z","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/2602.17684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and reliability of high-quality test cases. We propose CodeScaler, a reward model designed to scale both reinforcement learning training and test-time inference for code generation. CodeScaler is trained on carefully curated preference data derived from verified code problems and incorporates syntax-aware code extraction and validity-preserving reward shaping to","authors_text":"Boyu Zhu, Hanxu Hu, Haotian Zhang, Huiming Wang, Mingzhe Du, Xiao Zhu, Xinyu Zhou, Zhijiang Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T17:56:00Z","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17684","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:c90aa3ede44a67c4ca017636659a0470462d1d585fa4824bf43ebd003d16b09a","target":"record","created_at":"2026-05-20T00:04:26Z","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":"35cf03329c8d0d94f3e2f36cd46c218bec7a9a330f7917348892f6e1efa1c935","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T17:56:00Z","title_canon_sha256":"a01681e96c3db43a12e4edc52772fa822672880f07cf4fd1b73137b2386e4be2"},"schema_version":"1.0","source":{"id":"2602.17684","kind":"arxiv","version":2}},"canonical_sha256":"a097fecf8929c7bbe1241ab6a066bd6ce190e61eb4daf9da715bd055557c10ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a097fecf8929c7bbe1241ab6a066bd6ce190e61eb4daf9da715bd055557c10ea","first_computed_at":"2026-05-20T00:04:26.151084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:26.151084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"epLzXgUF++Hhxmw2pllYCmKEwn2rQ0K0rKx21u3QUakEOfDgSHFUEY95crWrlvEWDtnDqRmH7G12gn4C4HX8Aw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:26.152000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c90aa3ede44a67c4ca017636659a0470462d1d585fa4824bf43ebd003d16b09a","sha256:42d23dab7ab9d033f1d983c8037b9f99783c59200da56a641d1382ec10101661"],"state_sha256":"d0fe98d2fef770fdc30b886449e4b840d969d0094620d7d22b37d7f0fe6aacf9"}