{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GHIPPVSPZUHPCTW4PBOWILVMRI","short_pith_number":"pith:GHIPPVSP","schema_version":"1.0","canonical_sha256":"31d0f7d64fcd0ef14edc785d642eac8a1780e11f538d7efddb1099ecfe343add","source":{"kind":"arxiv","id":"2607.10805","version":1},"attestation_state":"computed","paper":{"title":"Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Li, Keqin Peng, Liang Ding, Yancheng Yuan, Yuanxin Ouyang","submitted_at":"2026-07-12T15:24:25Z","abstract_excerpt":"On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxically degrades downstream performance. In this paper, we systematically investigate this pathology and identify a severe optimization trap we define as \\textbf{Thinking Collapse} -- a sharp decline in the model's native intermediate reasoning behavior, measured by epistemic-token density (ET per 1k). Through entropy-based gradient masking and token-level target analysis, we show that this collapse is triggered by aggress"},"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":"2607.10805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T15:24:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5691d5cce860229214d7fd24e6c6d4954752c6931e42a2d924c0a60a14be7b3d","abstract_canon_sha256":"fc58d6ee37717948197c8f7592a7e1ed971fb1d78351b960945b41161c62b835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:41.123133Z","signature_b64":"tS6AmYJdkocRoqCAzLOBTvL7tfKwwA4T7to1Icfh+e4+W/SpYtMCefkq9s23zE3t+m11IsLAonAG+6TVgW5QCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d0f7d64fcd0ef14edc785d642eac8a1780e11f538d7efddb1099ecfe343add","last_reissued_at":"2026-07-14T01:21:41.122238Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:41.122238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Li, Keqin Peng, Liang Ding, Yancheng Yuan, Yuanxin Ouyang","submitted_at":"2026-07-12T15:24:25Z","abstract_excerpt":"On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxically degrades downstream performance. In this paper, we systematically investigate this pathology and identify a severe optimization trap we define as \\textbf{Thinking Collapse} -- a sharp decline in the model's native intermediate reasoning behavior, measured by epistemic-token density (ET per 1k). Through entropy-based gradient masking and token-level target analysis, we show that this collapse is triggered by aggress"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10805","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/2607.10805/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":"2607.10805","created_at":"2026-07-14T01:21:41.122711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10805v1","created_at":"2026-07-14T01:21:41.122711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10805","created_at":"2026-07-14T01:21:41.122711+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHIPPVSPZUHP","created_at":"2026-07-14T01:21:41.122711+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHIPPVSPZUHPCTW4","created_at":"2026-07-14T01:21:41.122711+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHIPPVSP","created_at":"2026-07-14T01:21:41.122711+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/GHIPPVSPZUHPCTW4PBOWILVMRI","json":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI.json","graph_json":"https://pith.science/api/pith-number/GHIPPVSPZUHPCTW4PBOWILVMRI/graph.json","events_json":"https://pith.science/api/pith-number/GHIPPVSPZUHPCTW4PBOWILVMRI/events.json","paper":"https://pith.science/paper/GHIPPVSP"},"agent_actions":{"view_html":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI","download_json":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI.json","view_paper":"https://pith.science/paper/GHIPPVSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10805&json=true","fetch_graph":"https://pith.science/api/pith-number/GHIPPVSPZUHPCTW4PBOWILVMRI/graph.json","fetch_events":"https://pith.science/api/pith-number/GHIPPVSPZUHPCTW4PBOWILVMRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI/action/storage_attestation","attest_author":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI/action/author_attestation","sign_citation":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI/action/citation_signature","submit_replication":"https://pith.science/pith/GHIPPVSPZUHPCTW4PBOWILVMRI/action/replication_record"}},"created_at":"2026-07-14T01:21:41.122711+00:00","updated_at":"2026-07-14T01:21:41.122711+00:00"}