{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SO5BGB2GLHKNRPHPXEY3WZ324C","short_pith_number":"pith:SO5BGB2G","schema_version":"1.0","canonical_sha256":"93ba13074659d4d8bcefb931bb677ae0b64d4886b48e18133ca4df50c33840d5","source":{"kind":"arxiv","id":"2502.12744","version":1},"attestation_state":"computed","paper":{"title":"Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingyuan Zhang, Jing Xiao, Jun Ma, Minchuan Chen, Ming Li, Ning Cheng, Shaojun Wang, Tao Wei, Yong Zhang, Zhitao Li","submitted_at":"2025-02-18T11:02:47Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models like GPT-2. Recent research shows that reasoning distillation can help small models acquire reasoning capabilities, but most existing methods focus primarily on improving teacher-generated reasoning paths. Our observations reveal that small models can generate high-quality reasoning paths during sampling, even without chain-of-thought prompting, though these p"},"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":"2502.12744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T11:02:47Z","cross_cats_sorted":[],"title_canon_sha256":"25ce9d4096fd5eaf90c10829700c799f69b2ef08260164b3f9d9bd3aa131b645","abstract_canon_sha256":"3579633815987eebe468c8a4f2e41ee42b0fc1b9cd473044a30556cc5f985ba7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:23.554015Z","signature_b64":"9YEpQ0m+hA9gJ/z/BbofI7p9E2rRgEhYhdvrsUhw+qFWurTogG75KEtkD6+ywaQE388QiAhfXXCFtZAeAneqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93ba13074659d4d8bcefb931bb677ae0b64d4886b48e18133ca4df50c33840d5","last_reissued_at":"2026-07-05T10:16:23.553535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:23.553535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingyuan Zhang, Jing Xiao, Jun Ma, Minchuan Chen, Ming Li, Ning Cheng, Shaojun Wang, Tao Wei, Yong Zhang, Zhitao Li","submitted_at":"2025-02-18T11:02:47Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models like GPT-2. Recent research shows that reasoning distillation can help small models acquire reasoning capabilities, but most existing methods focus primarily on improving teacher-generated reasoning paths. Our observations reveal that small models can generate high-quality reasoning paths during sampling, even without chain-of-thought prompting, though these p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12744","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/2502.12744/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":"2502.12744","created_at":"2026-07-05T10:16:23.553592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12744v1","created_at":"2026-07-05T10:16:23.553592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12744","created_at":"2026-07-05T10:16:23.553592+00:00"},{"alias_kind":"pith_short_12","alias_value":"SO5BGB2GLHKN","created_at":"2026-07-05T10:16:23.553592+00:00"},{"alias_kind":"pith_short_16","alias_value":"SO5BGB2GLHKNRPHP","created_at":"2026-07-05T10:16:23.553592+00:00"},{"alias_kind":"pith_short_8","alias_value":"SO5BGB2G","created_at":"2026-07-05T10:16:23.553592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C","json":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C.json","graph_json":"https://pith.science/api/pith-number/SO5BGB2GLHKNRPHPXEY3WZ324C/graph.json","events_json":"https://pith.science/api/pith-number/SO5BGB2GLHKNRPHPXEY3WZ324C/events.json","paper":"https://pith.science/paper/SO5BGB2G"},"agent_actions":{"view_html":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C","download_json":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C.json","view_paper":"https://pith.science/paper/SO5BGB2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12744&json=true","fetch_graph":"https://pith.science/api/pith-number/SO5BGB2GLHKNRPHPXEY3WZ324C/graph.json","fetch_events":"https://pith.science/api/pith-number/SO5BGB2GLHKNRPHPXEY3WZ324C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C/action/storage_attestation","attest_author":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C/action/author_attestation","sign_citation":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C/action/citation_signature","submit_replication":"https://pith.science/pith/SO5BGB2GLHKNRPHPXEY3WZ324C/action/replication_record"}},"created_at":"2026-07-05T10:16:23.553592+00:00","updated_at":"2026-07-05T10:16:23.553592+00:00"}