{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XIHANZK65NKDF5ZDDC5WRWMWFN","short_pith_number":"pith:XIHANZK6","schema_version":"1.0","canonical_sha256":"ba0e06e55eeb5432f72318bb68d9962b7bb3001e20197722fcf4afabaec104ed","source":{"kind":"arxiv","id":"2605.21606","version":1},"attestation_state":"computed","paper":{"title":"When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaowei Xiao, Xiaogeng Liu, Xinyan Wang, Yechao Zhang, Yingzi Ma","submitted_at":"2026-05-20T18:14:03Z","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"},"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":"2605.21606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T18:14:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"110b2b5f3dfee9b2789bb7172032c4753a6dc21a6cb4620b5616db3c19239d9e","abstract_canon_sha256":"b99e95096ddf6355c7227a9fc51aa97f64e2a1e37368fb4eac9014a7da3a3d58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:25.135655Z","signature_b64":"RyaywLgzzdto5zowaq5mVnSmq6GVQ8qhIbGIyyHU0SFmuIdUWZ0duCqDgilJY1vxgl6ZDNnXTVmFH5ByU2PLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba0e06e55eeb5432f72318bb68d9962b7bb3001e20197722fcf4afabaec104ed","last_reissued_at":"2026-05-22T01:03:25.134858Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:25.134858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaowei Xiao, Xiaogeng Liu, Xinyan Wang, Yechao Zhang, Yingzi Ma","submitted_at":"2026-05-20T18:14:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21606","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/2605.21606/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":"2605.21606","created_at":"2026-05-22T01:03:25.134989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21606v1","created_at":"2026-05-22T01:03:25.134989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21606","created_at":"2026-05-22T01:03:25.134989+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIHANZK65NKD","created_at":"2026-05-22T01:03:25.134989+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIHANZK65NKDF5ZD","created_at":"2026-05-22T01:03:25.134989+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIHANZK6","created_at":"2026-05-22T01:03:25.134989+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/XIHANZK65NKDF5ZDDC5WRWMWFN","json":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN.json","graph_json":"https://pith.science/api/pith-number/XIHANZK65NKDF5ZDDC5WRWMWFN/graph.json","events_json":"https://pith.science/api/pith-number/XIHANZK65NKDF5ZDDC5WRWMWFN/events.json","paper":"https://pith.science/paper/XIHANZK6"},"agent_actions":{"view_html":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN","download_json":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN.json","view_paper":"https://pith.science/paper/XIHANZK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21606&json=true","fetch_graph":"https://pith.science/api/pith-number/XIHANZK65NKDF5ZDDC5WRWMWFN/graph.json","fetch_events":"https://pith.science/api/pith-number/XIHANZK65NKDF5ZDDC5WRWMWFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN/action/storage_attestation","attest_author":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN/action/author_attestation","sign_citation":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN/action/citation_signature","submit_replication":"https://pith.science/pith/XIHANZK65NKDF5ZDDC5WRWMWFN/action/replication_record"}},"created_at":"2026-05-22T01:03:25.134989+00:00","updated_at":"2026-05-22T01:03:25.134989+00:00"}