{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4KFQZ4ID33B5YVETS4V5VJWJDG","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":"8e68bfd1cc43d7be412cb9346ec62a72ddecb4eef73040c182cdecbced0fab3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","title_canon_sha256":"08d1640b9aede080c9360fa2374dbbdb58813fb03256bbdc8cc2b28e66a221e4"},"schema_version":"1.0","source":{"id":"2605.22263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22263","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22263v1","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22263","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"4KFQZ4ID33B5","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"4KFQZ4ID33B5YVET","created_at":"2026-05-22T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"4KFQZ4ID","created_at":"2026-05-22T01:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:0e761465734d27df513d90abf95e2ef5631f1528de80f11255586c6d79e940b8","target":"graph","created_at":"2026-05-22T01:04:35Z","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/2605.22263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level supervision on its own rollouts. However, recent studies show that OPSD degrades complex reasoning by suppressing predictive uncertainty, which supports exploration and hypothesis revision. Our token-level analysis shows that this failure arises from applying a uniform direction of teacher supervision across tokens with different uncertainty levels: conformit","authors_text":"Chaozheng Wang, Hongbin Zhang, Jinpeng Wang, Kehai Chen, Min Zhang, Yang Xiang, Youcheng Pan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22263","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:bd92be3acec018e1cd0acf00ae433012923a40a7ca4c6dbfcf614b8e756a5c85","target":"record","created_at":"2026-05-22T01:04:35Z","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":"8e68bfd1cc43d7be412cb9346ec62a72ddecb4eef73040c182cdecbced0fab3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46Z","title_canon_sha256":"08d1640b9aede080c9360fa2374dbbdb58813fb03256bbdc8cc2b28e66a221e4"},"schema_version":"1.0","source":{"id":"2605.22263","kind":"arxiv","version":1}},"canonical_sha256":"e28b0cf103dec3dc5493972bdaa6c919aa6aea9e9dd4bad93208d24f3a249fe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e28b0cf103dec3dc5493972bdaa6c919aa6aea9e9dd4bad93208d24f3a249fe7","first_computed_at":"2026-05-22T01:04:35.124222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:35.124222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QzWzP5DwQPoF6XnW4afyLzMi+vCpS2HSViUNMWYYn8lFEN5lkJKjZADgqVXCP8phD+/ZSdYMiW7mSkrCJzV8AA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:35.124996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd92be3acec018e1cd0acf00ae433012923a40a7ca4c6dbfcf614b8e756a5c85","sha256:0e761465734d27df513d90abf95e2ef5631f1528de80f11255586c6d79e940b8"],"state_sha256":"9805fe6c3d3e2ab90937695d27e40970677042a23d1a7de09ff3e8e719db53d9"}