{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5PMX4ORINGZ2YCYAUKFVW2J4BD","short_pith_number":"pith:5PMX4ORI","schema_version":"1.0","canonical_sha256":"ebd97e3a2869b3ac0b00a28b5b693c08c27c44114dc3092ae6041ed3b9d753ff","source":{"kind":"arxiv","id":"2503.16385","version":1},"attestation_state":"computed","paper":{"title":"Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Zheng, Gengru Chen, Jiaheng Liu, Weixun Wang, Wenbo Su, Xingyao Zhang, Yijia Luo, Yulin Song","submitted_at":"2025-03-20T17:46:38Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning. The R1 distillation scheme has emerged as a promising approach for training cost-effective models with enhanced reasoning abilities. However, the underlying mechanisms driving its effectiveness remain unclear. This study examines the universality of distillation data and identifies key components that enable the efficient transfer of long-chain reasoning capabilities in LLM distillation. Our findings reveal that the effectiveness of long CoT rea"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.16385","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-20T17:46:38Z","cross_cats_sorted":[],"title_canon_sha256":"46fce7ed1ac15d81328d115d7f1519069578ad5cec417d2d890b8ac9cb8fc4ea","abstract_canon_sha256":"b0c383f1a8f196db2f43b933468fbd9accd4b96ae3166f25aabc839d2521c20a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:18.490738Z","signature_b64":"BB5lLHXuRaJ9r4LDNAG3nTeKGUHzRm6KXyxFIUJcn0nwBWtx2qwBxsDzsn4fSX7JnERLdslWaqLQjF24uXtvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebd97e3a2869b3ac0b00a28b5b693c08c27c44114dc3092ae6041ed3b9d753ff","last_reissued_at":"2026-07-05T10:36:18.490091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:18.490091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Zheng, Gengru Chen, Jiaheng Liu, Weixun Wang, Wenbo Su, Xingyao Zhang, Yijia Luo, Yulin Song","submitted_at":"2025-03-20T17:46:38Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning. The R1 distillation scheme has emerged as a promising approach for training cost-effective models with enhanced reasoning abilities. However, the underlying mechanisms driving its effectiveness remain unclear. This study examines the universality of distillation data and identifies key components that enable the efficient transfer of long-chain reasoning capabilities in LLM distillation. Our findings reveal that the effectiveness of long CoT rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16385","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.16385/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.16385","created_at":"2026-07-05T10:36:18.490161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16385v1","created_at":"2026-07-05T10:36:18.490161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16385","created_at":"2026-07-05T10:36:18.490161+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PMX4ORINGZ2","created_at":"2026-07-05T10:36:18.490161+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PMX4ORINGZ2YCYA","created_at":"2026-07-05T10:36:18.490161+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PMX4ORI","created_at":"2026-07-05T10:36:18.490161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26038","citing_title":"DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28888","citing_title":"Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10348","citing_title":"Training-Trajectory-Aware Token Selection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19285","citing_title":"Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17062","citing_title":"Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27132","citing_title":"TRUST: A Framework for Decentralized AI Service v.0.1","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02290","citing_title":"Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06834","citing_title":"On the Step Length Confounding in LLM Reasoning Data Selection","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD","json":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD.json","graph_json":"https://pith.science/api/pith-number/5PMX4ORINGZ2YCYAUKFVW2J4BD/graph.json","events_json":"https://pith.science/api/pith-number/5PMX4ORINGZ2YCYAUKFVW2J4BD/events.json","paper":"https://pith.science/paper/5PMX4ORI"},"agent_actions":{"view_html":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD","download_json":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD.json","view_paper":"https://pith.science/paper/5PMX4ORI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16385&json=true","fetch_graph":"https://pith.science/api/pith-number/5PMX4ORINGZ2YCYAUKFVW2J4BD/graph.json","fetch_events":"https://pith.science/api/pith-number/5PMX4ORINGZ2YCYAUKFVW2J4BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD/action/storage_attestation","attest_author":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD/action/author_attestation","sign_citation":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD/action/citation_signature","submit_replication":"https://pith.science/pith/5PMX4ORINGZ2YCYAUKFVW2J4BD/action/replication_record"}},"created_at":"2026-07-05T10:36:18.490161+00:00","updated_at":"2026-07-05T10:36:18.490161+00:00"}