{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W3XCWBR2LKV357YCUHR7IAXUGB","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":"33b480c82fd2ad7e71f63803d1ac141d89b238f4c2464a09f2f7ffa89d0f34c2","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T15:32:11Z","title_canon_sha256":"63ec110846a72621c2f3e8c5e0fd9020439222d1cd76f5b48cbdbb5c494b8483"},"schema_version":"1.0","source":{"id":"2502.13820","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13820","created_at":"2026-07-05T11:45:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13820v3","created_at":"2026-07-05T11:45:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13820","created_at":"2026-07-05T11:45:31Z"},{"alias_kind":"pith_short_12","alias_value":"W3XCWBR2LKV3","created_at":"2026-07-05T11:45:31Z"},{"alias_kind":"pith_short_16","alias_value":"W3XCWBR2LKV357YC","created_at":"2026-07-05T11:45:31Z"},{"alias_kind":"pith_short_8","alias_value":"W3XCWBR2","created_at":"2026-07-05T11:45:31Z"}],"graph_snapshots":[{"event_id":"sha256:e2ceb690a8f1bf902871e624f44e42e4c70f414a2c3ad24c1097a499d3419057","target":"graph","created_at":"2026-07-05T11:45:31Z","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/2502.13820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic verification techniques such as generating test cases and reward modelling are common ways to enhance the coding capabilities of large language models (LLM) beyond predefined tests. Additionally, code verification has recently found great success as a critical component in improving reasoning capability of LLMs via reinforcement learning. In this paper, we propose an approach which can transform existing coding benchmarks into scoring and ranking datasets to evaluate the effectiveness of synthetic verifiers. We also propose multiple metrics to measure different aspects of the synthet","authors_text":"Aleksander Ficek, Boris Ginsburg, Somshubra Majumdar, Vahid Noroozi","cross_cats":["cs.CL","cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T15:32:11Z","title":"Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13820","kind":"arxiv","version":3},"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:d09afac7d37932aef33af2efd1e6d67fb90300016d4a08831c4d40340f55ff03","target":"record","created_at":"2026-07-05T11:45:31Z","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":"33b480c82fd2ad7e71f63803d1ac141d89b238f4c2464a09f2f7ffa89d0f34c2","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T15:32:11Z","title_canon_sha256":"63ec110846a72621c2f3e8c5e0fd9020439222d1cd76f5b48cbdbb5c494b8483"},"schema_version":"1.0","source":{"id":"2502.13820","kind":"arxiv","version":3}},"canonical_sha256":"b6ee2b063a5aabbeff02a1e3f402f4306244793cc085fb06eaf613538d5f23d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6ee2b063a5aabbeff02a1e3f402f4306244793cc085fb06eaf613538d5f23d5","first_computed_at":"2026-07-05T11:45:31.623700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:31.623700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w30RUVwwEBJ1vt0z4tYVk1zev4lFY0y+ZNB/kT1wqoA+KE38Q2N4X8suD43b682DnXhChSIdPxV+tSnd/n9cCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:31.624218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13820","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d09afac7d37932aef33af2efd1e6d67fb90300016d4a08831c4d40340f55ff03","sha256:e2ceb690a8f1bf902871e624f44e42e4c70f414a2c3ad24c1097a499d3419057"],"state_sha256":"37de133917e692d46b3155cdf2a75f9435c398899a1de04786fa830fb933853f"}