{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CGTO6CK7GH5LMD5H2FSJPHWQV7","short_pith_number":"pith:CGTO6CK7","canonical_record":{"source":{"id":"2504.01943","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T17:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"34c6bea33b5a9cb12fd8d3f3014a2aa0d679dff002e6c13132b8b6ce59ae4f67","abstract_canon_sha256":"f7db4dcfc0769cd1fbf77368df90707c829f2c81aca628cd793299b3693a86ce"},"schema_version":"1.0"},"canonical_sha256":"11a6ef095f31fab60fa7d164979ed0afc5ea6a14d3320363a985ac08f569bb44","source":{"kind":"arxiv","id":"2504.01943","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01943","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01943v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01943","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"CGTO6CK7GH5L","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CGTO6CK7GH5LMD5H","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CGTO6CK7","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CGTO6CK7GH5LMD5H2FSJPHWQV7","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01943","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T17:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"34c6bea33b5a9cb12fd8d3f3014a2aa0d679dff002e6c13132b8b6ce59ae4f67","abstract_canon_sha256":"f7db4dcfc0769cd1fbf77368df90707c829f2c81aca628cd793299b3693a86ce"},"schema_version":"1.0"},"canonical_sha256":"11a6ef095f31fab60fa7d164979ed0afc5ea6a14d3320363a985ac08f569bb44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.308434Z","signature_b64":"4+L7H0Myh9W56W22YAqqwdpdcuNGZ4n1+tzNaCqbi6BeaBJFBy1Z5pb6BW3Jvp8Ttd61/C3rdth5jUifSREWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11a6ef095f31fab60fa7d164979ed0afc5ea6a14d3320363a985ac08f569bb44","last_reissued_at":"2026-05-17T23:38:13.307892Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.307892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01943","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9Uj4qf6qKkmj/mi+VwS76Gy9D6Dqo0QXcS0GXfUAyBHh4b/H6BlxwlDysI1501oNWXHUAPtOOKVpxXE4w7+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:07:36.299359Z"},"content_sha256":"5be6d5cd9b298f124852fb6a6533cb2dd5e6efe8e7aaf87e23679ae2c9cc980f","schema_version":"1.0","event_id":"sha256:5be6d5cd9b298f124852fb6a6533cb2dd5e6efe8e7aaf87e23679ae2c9cc980f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CGTO6CK7GH5LMD5H2FSJPHWQV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Curating a diverse dataset for supervised fine-tuning lets coding models outperform reinforcement learning on competitive benchmarks.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksander Ficek, Boris Ginsburg, Jocelyn Huang, Sean Narenthiran, Siddhartha Jain, Somshubra Majumdar, Vahid Noroozi, Wasi Uddin Ahmad","submitted_at":"2025-04-02T17:50:31Z","abstract_excerpt":"Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on coding tasks. Despite this, much of the progress on distilling reasoning models remains locked behind proprietary datasets or lacks details on data curation, filtering and subsequent training. To address this, we construct a superior supervised fine-tuning (SFT) dataset that we use to achieve state-of-the-art coding capability results in models of various siz"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our distilled models use only SFT to achieve 61.8% on LiveCodeBench and 24.6% on CodeContests, surpassing alternatives trained with reinforcement learning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That prioritizing instruction and solution diversity over code-execution filtering produces superior benchmark performance, as concluded from their post-training analysis.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A new open SFT dataset for reasoning distillation lets coding models hit state-of-the-art scores on LiveCodeBench and CodeContests with supervised fine-tuning alone, outperforming RL-trained baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Curating a diverse dataset for supervised fine-tuning lets coding models outperform reinforcement learning on competitive benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"94b7c1ebcf43f4c5c49ed1858cdafc7fdb6ed046482193d00a7a23a46aae249d"},"source":{"id":"2504.01943","kind":"arxiv","version":2},"verdict":{"id":"7b2eb1ad-2f8a-4773-8af2-effc80f3b2c6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T19:16:46.259013Z","strongest_claim":"Our distilled models use only SFT to achieve 61.8% on LiveCodeBench and 24.6% on CodeContests, surpassing alternatives trained with reinforcement learning.","one_line_summary":"A new open SFT dataset for reasoning distillation lets coding models hit state-of-the-art scores on LiveCodeBench and CodeContests with supervised fine-tuning alone, outperforming RL-trained baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That prioritizing instruction and solution diversity over code-execution filtering produces superior benchmark performance, as concluded from their post-training analysis.","pith_extraction_headline":"Curating a diverse dataset for supervised fine-tuning lets coding models outperform reinforcement learning on competitive benchmarks."},"references":{"count":27,"sample":[{"doi":"","year":2021,"title":"Unified pre-training for program understanding and generation","work_id":"eb9f47e4-7b74-4aff-b5ea-afee05bf91c0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2021.naacl-main.211","year":2021,"title":"Unified Pre-training for Program Understanding and Generation","work_id":"4b70b1ee-c108-4de8-9d25-d8770eead579","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","ref_index":3,"cited_arxiv_id":"2108.07732","is_internal_anchor":true},{"doi":"","year":2025,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":4,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":null,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","ref_index":5,"cited_arxiv_id":"2501.12948","is_internal_anchor":true}],"resolved_work":27,"snapshot_sha256":"3f7876529e85604d3df8de73d934c7ac64df61aeb07a0940f99d25b13b514f69","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5196f73509967d08a5f4d67325627fb262fe33269c790d4a96c53d7122f36272"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"7b2eb1ad-2f8a-4773-8af2-effc80f3b2c6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vxu+Iaup/kV32V7s0QVRLsEk70NIrnokIdf9AsStXTUMkzRFOPpcmGbwatVMyKWAK4j81uWxlszX2RQcoZ9PBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:07:36.299878Z"},"content_sha256":"50193bfd29e3b904975dfb2b38a77954f1b692d19472ebf499d187998e47ac63","schema_version":"1.0","event_id":"sha256:50193bfd29e3b904975dfb2b38a77954f1b692d19472ebf499d187998e47ac63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGTO6CK7GH5LMD5H2FSJPHWQV7/bundle.json","state_url":"https://pith.science/pith/CGTO6CK7GH5LMD5H2FSJPHWQV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGTO6CK7GH5LMD5H2FSJPHWQV7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T11:07:36Z","links":{"resolver":"https://pith.science/pith/CGTO6CK7GH5LMD5H2FSJPHWQV7","bundle":"https://pith.science/pith/CGTO6CK7GH5LMD5H2FSJPHWQV7/bundle.json","state":"https://pith.science/pith/CGTO6CK7GH5LMD5H2FSJPHWQV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGTO6CK7GH5LMD5H2FSJPHWQV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CGTO6CK7GH5LMD5H2FSJPHWQV7","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":"f7db4dcfc0769cd1fbf77368df90707c829f2c81aca628cd793299b3693a86ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T17:50:31Z","title_canon_sha256":"34c6bea33b5a9cb12fd8d3f3014a2aa0d679dff002e6c13132b8b6ce59ae4f67"},"schema_version":"1.0","source":{"id":"2504.01943","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01943","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01943v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01943","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"CGTO6CK7GH5L","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CGTO6CK7GH5LMD5H","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CGTO6CK7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:50193bfd29e3b904975dfb2b38a77954f1b692d19472ebf499d187998e47ac63","target":"graph","created_at":"2026-05-17T23:38:13Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our distilled models use only SFT to achieve 61.8% on LiveCodeBench and 24.6% on CodeContests, surpassing alternatives trained with reinforcement learning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That prioritizing instruction and solution diversity over code-execution filtering produces superior benchmark performance, as concluded from their post-training analysis."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A new open SFT dataset for reasoning distillation lets coding models hit state-of-the-art scores on LiveCodeBench and CodeContests with supervised fine-tuning alone, outperforming RL-trained baselines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Curating a diverse dataset for supervised fine-tuning lets coding models outperform reinforcement learning on competitive benchmarks."}],"snapshot_sha256":"94b7c1ebcf43f4c5c49ed1858cdafc7fdb6ed046482193d00a7a23a46aae249d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5196f73509967d08a5f4d67325627fb262fe33269c790d4a96c53d7122f36272"},"paper":{"abstract_excerpt":"Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on coding tasks. Despite this, much of the progress on distilling reasoning models remains locked behind proprietary datasets or lacks details on data curation, filtering and subsequent training. To address this, we construct a superior supervised fine-tuning (SFT) dataset that we use to achieve state-of-the-art coding capability results in models of various siz","authors_text":"Aleksander Ficek, Boris Ginsburg, Jocelyn Huang, Sean Narenthiran, Siddhartha Jain, Somshubra Majumdar, Vahid Noroozi, Wasi Uddin Ahmad","cross_cats":[],"headline":"Curating a diverse dataset for supervised fine-tuning lets coding models outperform reinforcement learning on competitive benchmarks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T17:50:31Z","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding"},"references":{"count":27,"internal_anchors":10,"resolved_work":27,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Unified pre-training for program understanding and generation","work_id":"eb9f47e4-7b74-4aff-b5ea-afee05bf91c0","year":2021},{"cited_arxiv_id":"","doi":"10.18653/v1/2021.naacl-main.211","is_internal_anchor":false,"ref_index":2,"title":"Unified Pre-training for Program Understanding and Generation","work_id":"4b70b1ee-c108-4de8-9d25-d8770eead579","year":2021},{"cited_arxiv_id":"2108.07732","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","year":null},{"cited_arxiv_id":"2107.03374","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2025},{"cited_arxiv_id":"2501.12948","doi":"","is_internal_anchor":true,"ref_index":5,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","year":null}],"snapshot_sha256":"3f7876529e85604d3df8de73d934c7ac64df61aeb07a0940f99d25b13b514f69"},"source":{"id":"2504.01943","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T19:16:46.259013Z","id":"7b2eb1ad-2f8a-4773-8af2-effc80f3b2c6","model_set":{"reader":"grok-4.3"},"one_line_summary":"A new open SFT dataset for reasoning distillation lets coding models hit state-of-the-art scores on LiveCodeBench and CodeContests with supervised fine-tuning alone, outperforming RL-trained baselines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Curating a diverse dataset for supervised fine-tuning lets coding models outperform reinforcement learning on competitive benchmarks.","strongest_claim":"Our distilled models use only SFT to achieve 61.8% on LiveCodeBench and 24.6% on CodeContests, surpassing alternatives trained with reinforcement learning.","weakest_assumption":"That prioritizing instruction and solution diversity over code-execution filtering produces superior benchmark performance, as concluded from their post-training analysis."}},"verdict_id":"7b2eb1ad-2f8a-4773-8af2-effc80f3b2c6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5be6d5cd9b298f124852fb6a6533cb2dd5e6efe8e7aaf87e23679ae2c9cc980f","target":"record","created_at":"2026-05-17T23:38:13Z","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":"f7db4dcfc0769cd1fbf77368df90707c829f2c81aca628cd793299b3693a86ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T17:50:31Z","title_canon_sha256":"34c6bea33b5a9cb12fd8d3f3014a2aa0d679dff002e6c13132b8b6ce59ae4f67"},"schema_version":"1.0","source":{"id":"2504.01943","kind":"arxiv","version":2}},"canonical_sha256":"11a6ef095f31fab60fa7d164979ed0afc5ea6a14d3320363a985ac08f569bb44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11a6ef095f31fab60fa7d164979ed0afc5ea6a14d3320363a985ac08f569bb44","first_computed_at":"2026-05-17T23:38:13.307892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.307892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4+L7H0Myh9W56W22YAqqwdpdcuNGZ4n1+tzNaCqbi6BeaBJFBy1Z5pb6BW3Jvp8Ttd61/C3rdth5jUifSREWBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.308434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01943","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5be6d5cd9b298f124852fb6a6533cb2dd5e6efe8e7aaf87e23679ae2c9cc980f","sha256:50193bfd29e3b904975dfb2b38a77954f1b692d19472ebf499d187998e47ac63"],"state_sha256":"3b6def3acb261a2eb5bd1eb2f37451c7544ca83bb934e367ca7ca424d20b3fa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDfn2zJLDwEIJBWTZZn/u0FX0SL3Vaub9D/03mlbuf2iH1nA+93YQFIqYvUMXS4mZkHrWcTzE/gCgARDr3IGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T11:07:36.301904Z","bundle_sha256":"743cab936f3cc7019ac125532c1efcf06cc4aef40d1921b7941d730505241bdd"}}