{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XIHZVD46O5Y5226XBUSHWPVSNZ","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":"501d1168dc19a577811ef10844f8ee41ffee9adc20086fd98e18078fb265da70","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T18:46:04Z","title_canon_sha256":"817b6693d839f17264e6f5c933eebffe90eb9e37f36b9af1d59184e1cc356b9d"},"schema_version":"1.0","source":{"id":"2502.01718","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01718","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01718v4","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01718","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_12","alias_value":"XIHZVD46O5Y5","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_16","alias_value":"XIHZVD46O5Y5226X","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_8","alias_value":"XIHZVD46","created_at":"2026-07-05T11:08:39Z"}],"graph_snapshots":[{"event_id":"sha256:3cd42661e2bdb9e665cc098f2655d7c89428daa22b5f69441db0abe456d62641","target":"graph","created_at":"2026-07-05T11:08:39Z","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/2502.01718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most progress in recent coder models has been driven by supervised fine-tuning (SFT), while the potential of reinforcement learning (RL) remains largely unexplored, primarily due to the lack of reliable reward data/model in the code domain. In this paper, we address this challenge by leveraging automated large-scale test-case synthesis to enhance code model training. Specifically, we design a pipeline that generates extensive (question, test-cases) pairs from existing code data. Using these test cases, we construct preference pairs based on pass rates over sampled programs to train reward mode","authors_text":"Dongfu Jiang, Haozhe Wang, Huaye Zeng, Ping Nie, Wenhu Chen, Xiaotong Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T18:46:04Z","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01718","kind":"arxiv","version":4},"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":"sha256:3225d7a8a2697a55c42c5eeb1d40c44d380da9b778568977b582586f56f14886","target":"record","created_at":"2026-07-05T11:08:39Z","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":"501d1168dc19a577811ef10844f8ee41ffee9adc20086fd98e18078fb265da70","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T18:46:04Z","title_canon_sha256":"817b6693d839f17264e6f5c933eebffe90eb9e37f36b9af1d59184e1cc356b9d"},"schema_version":"1.0","source":{"id":"2502.01718","kind":"arxiv","version":4}},"canonical_sha256":"ba0f9a8f9e7771dd6bd70d247b3eb26e676940ac2197e274f4836ca45fe7ea09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba0f9a8f9e7771dd6bd70d247b3eb26e676940ac2197e274f4836ca45fe7ea09","first_computed_at":"2026-07-05T11:08:39.972411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:39.972411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LyyVqHO7a1XJn/EccyiVB1E294q9OH5dCxwDCSWZzzQbKYP9A6XmVPXSW0+3JMTmbFT+nWktizJnopI6vVuKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:39.972898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01718","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3225d7a8a2697a55c42c5eeb1d40c44d380da9b778568977b582586f56f14886","sha256:3cd42661e2bdb9e665cc098f2655d7c89428daa22b5f69441db0abe456d62641"],"state_sha256":"c603af2a1294974e0f79ff284c0d22266fda6f29a269848df6ace679233c2d94"}