{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WYRZ4OQH6GPYKCZD62O74PACQY","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":"7857fac283e5d7f293951d61ff916d5b41367a4247fb0b6c04d3a287e71551f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T10:56:46Z","title_canon_sha256":"ea935a34a1f520ee0112c90cd00fd8d6d6716d3fb702383d677f97feeb0d675d"},"schema_version":"1.0","source":{"id":"2605.26844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26844","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26844v1","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26844","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"WYRZ4OQH6GPY","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"WYRZ4OQH6GPYKCZD","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"WYRZ4OQH","created_at":"2026-05-27T01:06:15Z"}],"graph_snapshots":[{"event_id":"sha256:642c4630ddd57ceee05d1d127fcdc54b799c6b351339d61d673455273709b21e","target":"graph","created_at":"2026-05-27T01:06:15Z","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/2605.26844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We revisit this principle and ask: which token-level teacher signals are actually learnable? Using a fixed-context diagnostic that measures same-context teacher-student KL reduction, we show that raw KL disagreement is a coarse proxy for learning value. It conflates learnable disagreement, where the teacher assigns corrective mass to the student's top-K candidates,","authors_text":"Congkai Xie, Hongxia Yang, Jianmin Wu, Pengkai Wang, Su Lu, Yanggan Gu, Yifan Yang, Yuanyi Wang, Zhaoyi Yan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T10:56:46Z","title":"Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26844","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":"sha256:10adf7a89be29a681055f4ae7a037cc353fdf53171e935b44b4b9e9d146ca28c","target":"record","created_at":"2026-05-27T01:06:15Z","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":"7857fac283e5d7f293951d61ff916d5b41367a4247fb0b6c04d3a287e71551f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T10:56:46Z","title_canon_sha256":"ea935a34a1f520ee0112c90cd00fd8d6d6716d3fb702383d677f97feeb0d675d"},"schema_version":"1.0","source":{"id":"2605.26844","kind":"arxiv","version":1}},"canonical_sha256":"b6239e3a07f19f850b23f69dfe3c02862ac4e4169dc71e5f4c262ed35e0bcbf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6239e3a07f19f850b23f69dfe3c02862ac4e4169dc71e5f4c262ed35e0bcbf3","first_computed_at":"2026-05-27T01:06:15.359067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:15.359067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WHVo31OIcxQMRI+o7l1RSpnQhcplsty5Hqg882BZ5E0Gd16/eN3fbpCrVdu3zXRnOpc2RIBnMWngvfpuNbHTCA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:15.359769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10adf7a89be29a681055f4ae7a037cc353fdf53171e935b44b4b9e9d146ca28c","sha256:642c4630ddd57ceee05d1d127fcdc54b799c6b351339d61d673455273709b21e"],"state_sha256":"60d18c2d30b802b489ce29adbeb534227b4f25fa2e91f409023256ce7ec89fc1"}