{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHIPPVSPZUHPCTW4PBOWILVMRI","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":"fc58d6ee37717948197c8f7592a7e1ed971fb1d78351b960945b41161c62b835","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T15:24:25Z","title_canon_sha256":"5691d5cce860229214d7fd24e6c6d4954752c6931e42a2d924c0a60a14be7b3d"},"schema_version":"1.0","source":{"id":"2607.10805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10805","created_at":"2026-07-14T01:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10805v1","created_at":"2026-07-14T01:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10805","created_at":"2026-07-14T01:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"GHIPPVSPZUHP","created_at":"2026-07-14T01:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"GHIPPVSPZUHPCTW4","created_at":"2026-07-14T01:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"GHIPPVSP","created_at":"2026-07-14T01:21:41Z"}],"graph_snapshots":[{"event_id":"sha256:32453e6d863c5a0e4cbc37128a3308f7a6233c7faa7878facd60182bd206d531","target":"graph","created_at":"2026-07-14T01:21:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.10805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Li, Keqin Peng, Liang Ding, Yancheng Yuan, Yuanxin Ouyang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T15:24:25Z","title":"Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10805","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":"sha256:8dee3682a4a825ef5d6c15e84abb0030d5526b60ee2936a49d4bc6699efc05ac","target":"record","created_at":"2026-07-14T01:21:41Z","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":"fc58d6ee37717948197c8f7592a7e1ed971fb1d78351b960945b41161c62b835","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T15:24:25Z","title_canon_sha256":"5691d5cce860229214d7fd24e6c6d4954752c6931e42a2d924c0a60a14be7b3d"},"schema_version":"1.0","source":{"id":"2607.10805","kind":"arxiv","version":1}},"canonical_sha256":"31d0f7d64fcd0ef14edc785d642eac8a1780e11f538d7efddb1099ecfe343add","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31d0f7d64fcd0ef14edc785d642eac8a1780e11f538d7efddb1099ecfe343add","first_computed_at":"2026-07-14T01:21:41.122238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:41.122238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tS6AmYJdkocRoqCAzLOBTvL7tfKwwA4T7to1Icfh+e4+W/SpYtMCefkq9s23zE3t+m11IsLAonAG+6TVgW5QCQ==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:41.123133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dee3682a4a825ef5d6c15e84abb0030d5526b60ee2936a49d4bc6699efc05ac","sha256:32453e6d863c5a0e4cbc37128a3308f7a6233c7faa7878facd60182bd206d531"],"state_sha256":"65d75bbd84a674579bff4743f1c14ccf0447796305838bc24ae6fa0e545dcfa3"}