{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XIHANZK65NKDF5ZDDC5WRWMWFN","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":"b99e95096ddf6355c7227a9fc51aa97f64e2a1e37368fb4eac9014a7da3a3d58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T18:14:03Z","title_canon_sha256":"110b2b5f3dfee9b2789bb7172032c4753a6dc21a6cb4620b5616db3c19239d9e"},"schema_version":"1.0","source":{"id":"2605.21606","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21606","created_at":"2026-05-22T01:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21606v1","created_at":"2026-05-22T01:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21606","created_at":"2026-05-22T01:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"XIHANZK65NKD","created_at":"2026-05-22T01:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"XIHANZK65NKDF5ZD","created_at":"2026-05-22T01:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"XIHANZK6","created_at":"2026-05-22T01:03:25Z"}],"graph_snapshots":[{"event_id":"sha256:9091b687fae591c6d2735e240e99f1cef43950e90823ff7e2e60d97245f75066","target":"graph","created_at":"2026-05-22T01:03:25Z","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/2605.21606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly treating the privileged teacher target as equally reliable at every student-visited prefix. Existing entropy-based OPD methods relax this uniformity by modulating token-level supervision with teacher entropy, but high teacher entropy in reasoning has an ambiguous reliability meaning: it can reflect either non-viable uncertainty or benign solution diversity. To identify this phenomenon, we introduce a branch-viability dia","authors_text":"Chaowei Xiao, Xiaogeng Liu, Xinyan Wang, Yechao Zhang, Yingzi Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T18:14:03Z","title":"When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21606","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":"sha256:5c23749a3941134887c9dd3f8c798560d4090a8566aee6f7b4c835c42d67d5ce","target":"record","created_at":"2026-05-22T01:03:25Z","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":"b99e95096ddf6355c7227a9fc51aa97f64e2a1e37368fb4eac9014a7da3a3d58","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T18:14:03Z","title_canon_sha256":"110b2b5f3dfee9b2789bb7172032c4753a6dc21a6cb4620b5616db3c19239d9e"},"schema_version":"1.0","source":{"id":"2605.21606","kind":"arxiv","version":1}},"canonical_sha256":"ba0e06e55eeb5432f72318bb68d9962b7bb3001e20197722fcf4afabaec104ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba0e06e55eeb5432f72318bb68d9962b7bb3001e20197722fcf4afabaec104ed","first_computed_at":"2026-05-22T01:03:25.134858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:25.134858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RyaywLgzzdto5zowaq5mVnSmq6GVQ8qhIbGIyyHU0SFmuIdUWZ0duCqDgilJY1vxgl6ZDNnXTVmFH5ByU2PLCQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:25.135655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21606","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c23749a3941134887c9dd3f8c798560d4090a8566aee6f7b4c835c42d67d5ce","sha256:9091b687fae591c6d2735e240e99f1cef43950e90823ff7e2e60d97245f75066"],"state_sha256":"64bb540b55dd5cf958f523490c7dbcb15d4d59222074e89d4ecae3e624696b46"}