{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5777KZB3FB4OVQZZ6TXYKLQ7CT","short_pith_number":"pith:5777KZB3","canonical_record":{"source":{"id":"2502.03373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T17:13:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a72661e56a37092fe53122debbf22c68eca59be5bc8fed65e686a65c08a71b3b","abstract_canon_sha256":"c92969eb8c771a0e0f649486792c3f2b28d7a2b299553ab8dc537789b9190484"},"schema_version":"1.0"},"canonical_sha256":"effff5643b2878eac339f4ef852e1f14e521baeb0f82a6f579ec7fdc9608007a","source":{"kind":"arxiv","id":"2502.03373","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03373","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03373v1","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03373","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"pith_short_12","alias_value":"5777KZB3FB4O","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"pith_short_16","alias_value":"5777KZB3FB4OVQZZ","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"pith_short_8","alias_value":"5777KZB3","created_at":"2026-05-19T01:25:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5777KZB3FB4OVQZZ6TXYKLQ7CT","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T17:13:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a72661e56a37092fe53122debbf22c68eca59be5bc8fed65e686a65c08a71b3b","abstract_canon_sha256":"c92969eb8c771a0e0f649486792c3f2b28d7a2b299553ab8dc537789b9190484"},"schema_version":"1.0"},"canonical_sha256":"effff5643b2878eac339f4ef852e1f14e521baeb0f82a6f579ec7fdc9608007a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T01:25:17.942548Z","signature_b64":"C/wqzbKoQPq3puzCdBwVZlPCUUUOlfqgIvIaYWHbmzZKC2+bq5uYeK7/uxQqrV9GNkGelbcDi23Cia5HQ+U/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"effff5643b2878eac339f4ef852e1f14e521baeb0f82a6f579ec7fdc9608007a","last_reissued_at":"2026-05-19T01:25:17.939619Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T01:25:17.939619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03373","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T01:25:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UecvlHrXJRTqBuMfa/ukDBZZAZ/HNH10HVif/MwRonyIbw8kRgh7J23l8LyWkaMxmhNJPUk67IlPMEcBCaFAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:15:02.316656Z"},"content_sha256":"92e3be730ac1eb286cc069dd8891d6221591be30d3ca75780d4e0d6b0f0e7e74","schema_version":"1.0","event_id":"sha256:92e3be730ac1eb286cc069dd8891d6221591be30d3ca75780d4e0d6b0f0e7e74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5777KZB3FB4OVQZZ6TXYKLQ7CT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Edward Yeo, Graham Neubig, Morry Niu, Xiang Yue, Yuxuan Tong","submitted_at":"2025-02-05T17:13:32Z","abstract_excerpt":"Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a crucial method for developing these capabilities, yet the conditions under which long CoTs emerge remain unclear, and RL training requires careful design choices. In this study, we systematically investigate the mechanics of long CoT reasoning, identifying the key factors that enable models to generate long CoT trajectories. Through extensive supervised fine-tuning (SFT) and RL e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03373","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T01:25:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1pdsLjeiq33Dv0tk+qzskkNz+JgYhjKbdcKKnBouT2vYWedNs68IMrK3yF3iJoFgXhPArSuzsMo8qFbtxjPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:15:02.317016Z"},"content_sha256":"cca6b77e7c88e26a7fe52e3382752f36e6f7f0cc9488e0ae19e1c1c0064a863c","schema_version":"1.0","event_id":"sha256:cca6b77e7c88e26a7fe52e3382752f36e6f7f0cc9488e0ae19e1c1c0064a863c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5777KZB3FB4OVQZZ6TXYKLQ7CT/bundle.json","state_url":"https://pith.science/pith/5777KZB3FB4OVQZZ6TXYKLQ7CT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5777KZB3FB4OVQZZ6TXYKLQ7CT/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":"2026-05-30T14:15:02Z","links":{"resolver":"https://pith.science/pith/5777KZB3FB4OVQZZ6TXYKLQ7CT","bundle":"https://pith.science/pith/5777KZB3FB4OVQZZ6TXYKLQ7CT/bundle.json","state":"https://pith.science/pith/5777KZB3FB4OVQZZ6TXYKLQ7CT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5777KZB3FB4OVQZZ6TXYKLQ7CT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5777KZB3FB4OVQZZ6TXYKLQ7CT","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":"c92969eb8c771a0e0f649486792c3f2b28d7a2b299553ab8dc537789b9190484","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T17:13:32Z","title_canon_sha256":"a72661e56a37092fe53122debbf22c68eca59be5bc8fed65e686a65c08a71b3b"},"schema_version":"1.0","source":{"id":"2502.03373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03373","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03373v1","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03373","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"pith_short_12","alias_value":"5777KZB3FB4O","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"pith_short_16","alias_value":"5777KZB3FB4OVQZZ","created_at":"2026-05-19T01:25:17Z"},{"alias_kind":"pith_short_8","alias_value":"5777KZB3","created_at":"2026-05-19T01:25:17Z"}],"graph_snapshots":[{"event_id":"sha256:cca6b77e7c88e26a7fe52e3382752f36e6f7f0cc9488e0ae19e1c1c0064a863c","target":"graph","created_at":"2026-05-19T01:25:17Z","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"},"paper":{"abstract_excerpt":"Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a crucial method for developing these capabilities, yet the conditions under which long CoTs emerge remain unclear, and RL training requires careful design choices. In this study, we systematically investigate the mechanics of long CoT reasoning, identifying the key factors that enable models to generate long CoT trajectories. Through extensive supervised fine-tuning (SFT) and RL e","authors_text":"Edward Yeo, Graham Neubig, Morry Niu, Xiang Yue, Yuxuan Tong","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T17:13:32Z","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03373","kind":"arxiv","version":1},"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":"sha256:92e3be730ac1eb286cc069dd8891d6221591be30d3ca75780d4e0d6b0f0e7e74","target":"record","created_at":"2026-05-19T01:25:17Z","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":"c92969eb8c771a0e0f649486792c3f2b28d7a2b299553ab8dc537789b9190484","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T17:13:32Z","title_canon_sha256":"a72661e56a37092fe53122debbf22c68eca59be5bc8fed65e686a65c08a71b3b"},"schema_version":"1.0","source":{"id":"2502.03373","kind":"arxiv","version":1}},"canonical_sha256":"effff5643b2878eac339f4ef852e1f14e521baeb0f82a6f579ec7fdc9608007a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"effff5643b2878eac339f4ef852e1f14e521baeb0f82a6f579ec7fdc9608007a","first_computed_at":"2026-05-19T01:25:17.939619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-19T01:25:17.939619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C/wqzbKoQPq3puzCdBwVZlPCUUUOlfqgIvIaYWHbmzZKC2+bq5uYeK7/uxQqrV9GNkGelbcDi23Cia5HQ+U/BQ==","signature_status":"signed_v1","signed_at":"2026-05-19T01:25:17.942548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92e3be730ac1eb286cc069dd8891d6221591be30d3ca75780d4e0d6b0f0e7e74","sha256:cca6b77e7c88e26a7fe52e3382752f36e6f7f0cc9488e0ae19e1c1c0064a863c"],"state_sha256":"8386cc54dd2ceaa40454b6f38b8919d7ed206ec3c1a749673709f2dbb0f8d25a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uyXYMx2E5COOsfvD/WsNA5NQEXmHH/ssZoiw1Mjupm4wqp5DtIJ2/yU/tV0gs23J/v3qpMMgDCeJMfzwAZfmAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:15:02.319072Z","bundle_sha256":"0e04304332358a768676a3a7200f0d8cd0020c287c95ff7542e47e5a8898e8fb"}}