{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FCPQML7QH5IJCFDCRSOGCJZJJG","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":"2b74c6abd7ad6bf75ed9839a04d76eb7072be951819423c01ac7d731adff2973","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-05T02:52:16Z","title_canon_sha256":"643e87b4465c9d6842aefc4ac08b1d595255a90d538d2005405eff6cefde37ba"},"schema_version":"1.0","source":{"id":"2504.04030","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04030","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04030v2","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04030","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"FCPQML7QH5IJ","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"FCPQML7QH5IJCFDC","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"FCPQML7Q","created_at":"2026-07-05T11:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:2881abd8959eca70e8cef4f3818756a461b1084ce5fb238ec2a5b13e2160143a","target":"graph","created_at":"2026-07-05T11:50:34Z","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/2504.04030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have transformed software development by enabling code generation, automated debugging, and complex reasoning. However, their continued advancement is constrained by the scarcity of high-quality, publicly available supervised fine-tuning (SFT) datasets tailored for coding tasks. To bridge this gap, we introduce OpenCodeInstruct, the largest open-access instruction tuning dataset, comprising 5 million diverse samples. Each sample includes a programming question, solution, test cases, execution feedback, and LLM-generated quality assessments. We fine-tune various bas","authors_text":"Aleksander Ficek, Boris Ginsburg, Jocelyn Huang, Mehrzad Samadi, Somshubra Majumdar, Vahid Noroozi, Wasi Uddin Ahmad","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-05T02:52:16Z","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04030","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:ae9e8ee9e87994fd261d43ced4885b118c4bb1bf874a515e2ae14b2a89adf6a7","target":"record","created_at":"2026-07-05T11:50:34Z","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":"2b74c6abd7ad6bf75ed9839a04d76eb7072be951819423c01ac7d731adff2973","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-05T02:52:16Z","title_canon_sha256":"643e87b4465c9d6842aefc4ac08b1d595255a90d538d2005405eff6cefde37ba"},"schema_version":"1.0","source":{"id":"2504.04030","kind":"arxiv","version":2}},"canonical_sha256":"289f062ff03f509114628c9c61272949b04e744a56208418a6b76a00608f050b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"289f062ff03f509114628c9c61272949b04e744a56208418a6b76a00608f050b","first_computed_at":"2026-07-05T11:50:34.498710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:34.498710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZFeaUSG24gaPijAcunfPNqR94dzoB0Dg9UWHTeHsB0mG4+qAbj8Z63wMrFWxPlF5C/5ZGP2NXyNnEQ4tuhsCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:34.499161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04030","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae9e8ee9e87994fd261d43ced4885b118c4bb1bf874a515e2ae14b2a89adf6a7","sha256:2881abd8959eca70e8cef4f3818756a461b1084ce5fb238ec2a5b13e2160143a"],"state_sha256":"47da90e9bd899a03e07109b24af43284bfd72689a16225c9ad19516ce8931a79"}