{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZK5KF34HDP7HU7EC26UVIKZ4ZH","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":"cbe46b4d288d3feae3bb2c0bb0fe16ca4e33eb9901f4b2aabddba9d377466194","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T19:17:36Z","title_canon_sha256":"7e4c4e10278dd106d48fd156ca420d76fc3d9630f1215a839c9afa819d958108"},"schema_version":"1.0","source":{"id":"2503.02951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02951","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02951v2","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02951","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZK5KF34HDP7H","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZK5KF34HDP7HU7EC","created_at":"2026-07-05T11:35:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZK5KF34H","created_at":"2026-07-05T11:35:54Z"}],"graph_snapshots":[{"event_id":"sha256:6f2030d55b1be60d184d8b627d55498cc3e07ce54e7a13baf429dcde2d1d9315","target":"graph","created_at":"2026-07-05T11:35:54Z","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/2503.02951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing code-focused resources typically fail to ensure either the breadth of coverage (e.g., spanning simple coding tasks to advanced algorithmic problems) or verifiable correctness (e.g., unit tests). In contrast, KodCode comprises question-solution-test triplets that are systematically validated via a self-verification procedure. Our pipeline begins by synthesizing a broad","authors_text":"Mingyuan Zhou, Radha Poovendran, Yang Liu, Yueqin Yin, Zhangchen Xu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T19:17:36Z","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02951","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":"sha256:2c9166b486cf8580549d735b9b6a7b31c812dcd472d39ad0b71f6563a96b3441","target":"record","created_at":"2026-07-05T11:35:54Z","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":"cbe46b4d288d3feae3bb2c0bb0fe16ca4e33eb9901f4b2aabddba9d377466194","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T19:17:36Z","title_canon_sha256":"7e4c4e10278dd106d48fd156ca420d76fc3d9630f1215a839c9afa819d958108"},"schema_version":"1.0","source":{"id":"2503.02951","kind":"arxiv","version":2}},"canonical_sha256":"cabaa2ef871bfe7a7c82d7a9542b3cc9fe4049082b9218aa30b57809b6b1aba2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cabaa2ef871bfe7a7c82d7a9542b3cc9fe4049082b9218aa30b57809b6b1aba2","first_computed_at":"2026-07-05T11:35:54.028928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:54.028928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8S0s86F/rcp3vVlBeQHrzUnrpdFbVxrIxH/7EhksB5WgrTO0F2qGlYgQdNeUHSrYV8MEFvpRdgbwuw+0KtabBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:54.029474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c9166b486cf8580549d735b9b6a7b31c812dcd472d39ad0b71f6563a96b3441","sha256:6f2030d55b1be60d184d8b627d55498cc3e07ce54e7a13baf429dcde2d1d9315"],"state_sha256":"7872dcbe14a208d83a56b02afc38a20102adcb578a18c69972c7a7ce0eddab7b"}