{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2PXFC44XRAW7IAOFJBQFXJXBCI","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":"7dfb6df145eb8aed49a534fa678228af46640ed618109efc3d2abcc8ba159621","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T15:29:22Z","title_canon_sha256":"9dce75478fad8465aba69808edf9350e25539e7a6e4e48e35d19f17dcc661f17"},"schema_version":"1.0","source":{"id":"2503.10460","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10460","created_at":"2026-07-05T11:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10460v4","created_at":"2026-07-05T11:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10460","created_at":"2026-07-05T11:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"2PXFC44XRAW7","created_at":"2026-07-05T11:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"2PXFC44XRAW7IAOF","created_at":"2026-07-05T11:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"2PXFC44X","created_at":"2026-07-05T11:10:54Z"}],"graph_snapshots":[{"event_id":"sha256:f1b4e06486e37e0c4a655f065ef594d8942d375cecda345db62cf90690d9419a","target":"graph","created_at":"2026-07-05T11:10:54Z","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/2503.10460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively public data and models. Our curriculum training progressively increases data difficulty, combined with multi-staged post-training. Our Light-R1-32B model, trained from Qwen2.5-32B-Instruct, outperforms DeepSeek-R1-Distill-Qwen-32B in math reasoning.\n  Experimental results show that this curriculum approach becomes more effective whe","authors_text":"Fenrui Xiao, Haosheng Zou, Junchen Liu, Liang Wen, Lifu Tang, Qi An, Shousheng Jia, Xiangzheng Zhang, Xiaowei Lv, Xin He, Yimin Du, Yongchao Deng, Yunke Cai, Zhenyu Duan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T15:29:22Z","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10460","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:b03dfaa94cf559ebe966a3af692f4a2c5b6e33ad8f4b3e5489630c1b21475f49","target":"record","created_at":"2026-07-05T11:10:54Z","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":"7dfb6df145eb8aed49a534fa678228af46640ed618109efc3d2abcc8ba159621","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T15:29:22Z","title_canon_sha256":"9dce75478fad8465aba69808edf9350e25539e7a6e4e48e35d19f17dcc661f17"},"schema_version":"1.0","source":{"id":"2503.10460","kind":"arxiv","version":4}},"canonical_sha256":"d3ee517397882df401c548605ba6e11226570b717bf6081d07dffe6444c4b29a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3ee517397882df401c548605ba6e11226570b717bf6081d07dffe6444c4b29a","first_computed_at":"2026-07-05T11:10:54.251056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:54.251056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ePStIAdUFgczbUFAzTarlueFRstY7jfLLtDJBYcnwofLTM0M6DIDYdkAOqo9W9MjqNP79WYlcxCAAbEDWBcjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:54.251608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10460","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b03dfaa94cf559ebe966a3af692f4a2c5b6e33ad8f4b3e5489630c1b21475f49","sha256:f1b4e06486e37e0c4a655f065ef594d8942d375cecda345db62cf90690d9419a"],"state_sha256":"eb90f8bbfe36b5914a227a8823e2710a6d59264921ed818ad3ce001f91d26926"}