{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KHQV23NUBYIMYY6AK2KOPWUPRW","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":"7acc7a20d8d7d8f03c4cf67cd97076aa19e75768b488f24a4878adb9843c14b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-11T08:48:48Z","title_canon_sha256":"38433bc43b1964b25753751921159d6f88067c9deb8d782c920d72510900c70d"},"schema_version":"1.0","source":{"id":"2502.07374","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07374","created_at":"2026-07-05T10:15:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07374v2","created_at":"2026-07-05T10:15:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07374","created_at":"2026-07-05T10:15:49Z"},{"alias_kind":"pith_short_12","alias_value":"KHQV23NUBYIM","created_at":"2026-07-05T10:15:49Z"},{"alias_kind":"pith_short_16","alias_value":"KHQV23NUBYIMYY6A","created_at":"2026-07-05T10:15:49Z"},{"alias_kind":"pith_short_8","alias_value":"KHQV23NU","created_at":"2026-07-05T10:15:49Z"}],"graph_snapshots":[{"event_id":"sha256:b25b32c6ab05af5e055e352f92e4ad01de569443088ccd6e737cd17ea0c7e54a","target":"graph","created_at":"2026-07-05T10:15:49Z","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/2502.07374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT) that incorporate reflection, backtracking, and self-validation. However, the training techniques and data requirements to elicit Long CoT remain poorly understood. In this work, we find that a Large Language model (LLM) can effectively learn Long CoT reasoning through data-efficient supervised fine-tuning (SFT) and parameter-efficient low-rank adaptation (LoRA). With just 17k long CoT training samples, the Qwen2.5-32B-Instruct model achieves significant improvements on a wide range of","authors_text":"Dacheng Li, Eric Tang, Ion Stoica, Joseph E. Gonzalez, Kourosh Hakhamaneshi, Matei Zaharia, Shishir G. Patil, Shiyi Cao, Shu Liu, Sumanth Hegde, Tyler Griggs, Xiangxi Mo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-11T08:48:48Z","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07374","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:b85763f772c72804a557105bb65491308bcd4fb837bba560d156c14d791f456d","target":"record","created_at":"2026-07-05T10:15:49Z","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":"7acc7a20d8d7d8f03c4cf67cd97076aa19e75768b488f24a4878adb9843c14b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-11T08:48:48Z","title_canon_sha256":"38433bc43b1964b25753751921159d6f88067c9deb8d782c920d72510900c70d"},"schema_version":"1.0","source":{"id":"2502.07374","kind":"arxiv","version":2}},"canonical_sha256":"51e15d6db40e10cc63c05694e7da8f8d8ed7379aad99bb3e1a5a6e983bd7350d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51e15d6db40e10cc63c05694e7da8f8d8ed7379aad99bb3e1a5a6e983bd7350d","first_computed_at":"2026-07-05T10:15:49.043285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:49.043285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uAuGzzBOTgOhgnJf8jYKUeYsRZ7QfigJGD5sBGqgXhLLV/DoNXWz5WohFLtjezhr4c58HQ8eqUC7jMWbZ5A6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:49.043845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07374","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b85763f772c72804a557105bb65491308bcd4fb837bba560d156c14d791f456d","sha256:b25b32c6ab05af5e055e352f92e4ad01de569443088ccd6e737cd17ea0c7e54a"],"state_sha256":"30e6a51e5c7f71a78da7d9c79902612181f9fb1d818e426ec37dc74335b4480a"}