{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CA4TMG6PFOFJ5ZPATV2PNUD7RP","short_pith_number":"pith:CA4TMG6P","schema_version":"1.0","canonical_sha256":"1039361bcf2b8a9ee5e09d74f6d07f8bd305edf1adc87098ecde674d4f2013af","source":{"kind":"arxiv","id":"2412.10827","version":4},"attestation_state":"computed","paper":{"title":"Rethinking Chain-of-Thought from the Perspective of Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baoduo Xu, Lei Feng, Mengmeng Zhan, Ruochen Cui, Xiaofeng Zhu, Zongqian Wu","submitted_at":"2024-12-14T13:12:50Z","abstract_excerpt":"Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging model-generated information to progressively reduce prediction uncertainty. Building on this insight, we propose a novel CoT framework to improve reasoning performance. Our framework integrates two key components: (i) a task-specific prompt module that optimizes the initial reasoning process, and (ii) an adaptive reasoning iteration module that dynamically refines th"},"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":"2412.10827","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T13:12:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"332da2da2f2d7991d9269f739d313de090ceef9669418dc6203fa9152ad8e6a1","abstract_canon_sha256":"96edc6a5e17f81a4bc28cb6efffc521577a6c6172fb83b2346358d6d0d6fd2c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:05.349600Z","signature_b64":"I/KFsNCGc0pYB1KyNWbEOys1oG9SgksNACyRz6MVNZyo0tT1k+Wi3ubNtNwPVQGQzTQMLoj669HUlgmiLELfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1039361bcf2b8a9ee5e09d74f6d07f8bd305edf1adc87098ecde674d4f2013af","last_reissued_at":"2026-07-05T11:09:05.349013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:05.349013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Chain-of-Thought from the Perspective of Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baoduo Xu, Lei Feng, Mengmeng Zhan, Ruochen Cui, Xiaofeng Zhu, Zongqian Wu","submitted_at":"2024-12-14T13:12:50Z","abstract_excerpt":"Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging model-generated information to progressively reduce prediction uncertainty. Building on this insight, we propose a novel CoT framework to improve reasoning performance. Our framework integrates two key components: (i) a task-specific prompt module that optimizes the initial reasoning process, and (ii) an adaptive reasoning iteration module that dynamically refines th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10827","kind":"arxiv","version":4},"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/2412.10827/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":"2412.10827","created_at":"2026-07-05T11:09:05.349099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10827v4","created_at":"2026-07-05T11:09:05.349099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10827","created_at":"2026-07-05T11:09:05.349099+00:00"},{"alias_kind":"pith_short_12","alias_value":"CA4TMG6PFOFJ","created_at":"2026-07-05T11:09:05.349099+00:00"},{"alias_kind":"pith_short_16","alias_value":"CA4TMG6PFOFJ5ZPA","created_at":"2026-07-05T11:09:05.349099+00:00"},{"alias_kind":"pith_short_8","alias_value":"CA4TMG6P","created_at":"2026-07-05T11:09:05.349099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01511","citing_title":"Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26795","citing_title":"What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP","json":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP.json","graph_json":"https://pith.science/api/pith-number/CA4TMG6PFOFJ5ZPATV2PNUD7RP/graph.json","events_json":"https://pith.science/api/pith-number/CA4TMG6PFOFJ5ZPATV2PNUD7RP/events.json","paper":"https://pith.science/paper/CA4TMG6P"},"agent_actions":{"view_html":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP","download_json":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP.json","view_paper":"https://pith.science/paper/CA4TMG6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10827&json=true","fetch_graph":"https://pith.science/api/pith-number/CA4TMG6PFOFJ5ZPATV2PNUD7RP/graph.json","fetch_events":"https://pith.science/api/pith-number/CA4TMG6PFOFJ5ZPATV2PNUD7RP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP/action/storage_attestation","attest_author":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP/action/author_attestation","sign_citation":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP/action/citation_signature","submit_replication":"https://pith.science/pith/CA4TMG6PFOFJ5ZPATV2PNUD7RP/action/replication_record"}},"created_at":"2026-07-05T11:09:05.349099+00:00","updated_at":"2026-07-05T11:09:05.349099+00:00"}