{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZZSJASEKSP2ZDJETK35KUGSL3Y","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":"c05733ff63443716d7d248d7bbae8bcf8485ae7b31551c0d28eca9382fbd0482","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T11:15:26Z","title_canon_sha256":"287f7711834e264462b2f864a1aadbae92c4bd4526972ab616795b6f17254c3c"},"schema_version":"1.0","source":{"id":"2606.29340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29340","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29340v1","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29340","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZZSJASEKSP2Z","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZZSJASEKSP2ZDJET","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZZSJASEK","created_at":"2026-06-30T01:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:f57b2915cffa8d066f6e2e4d8f60ad0b5ccca844fac9d77405c81fe78673afd5","target":"graph","created_at":"2026-06-30T01:18:02Z","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/2606.29340/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 reasoning model on rollouts sampled from its own policy by matching a privileged teacher that also sees verified reference solutions. Existing OPSD objectives supervise only the output distribution, so privileged context affects training through a token-level divergence without directly supervising the internal computation that produced that distribution. We propose Privileged Hidden Flow (PHF), which additionally distills how a privileged teacher's hidden states move along the same rollout. Rather than forcing each student hidden vector to match the","authors_text":"Dazhong Shen, Mingxu Zhang, Ying Sun, Yuhan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T11:15:26Z","title":"PHF: Privileged Hidden Flow for On-Policy Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29340","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":"sha256:92b7c3a97ecff18ac59cb69444f2219b27afdae572416666247dfd590ccb2fc9","target":"record","created_at":"2026-06-30T01:18:02Z","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":"c05733ff63443716d7d248d7bbae8bcf8485ae7b31551c0d28eca9382fbd0482","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T11:15:26Z","title_canon_sha256":"287f7711834e264462b2f864a1aadbae92c4bd4526972ab616795b6f17254c3c"},"schema_version":"1.0","source":{"id":"2606.29340","kind":"arxiv","version":1}},"canonical_sha256":"ce6490488a93f591a49356faaa1a4bde2f94b884ff5031d1f631e759bdb1ed55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce6490488a93f591a49356faaa1a4bde2f94b884ff5031d1f631e759bdb1ed55","first_computed_at":"2026-06-30T01:18:02.117761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:02.117761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HAuKaZdcGHX9wQF5mFCac944lCTXzSoMOcfFXOXuYiCpbkbnZHFknJj8kBaI1MHXu/rjB9o9RBxOU830BmdpDQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:02.118185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92b7c3a97ecff18ac59cb69444f2219b27afdae572416666247dfd590ccb2fc9","sha256:f57b2915cffa8d066f6e2e4d8f60ad0b5ccca844fac9d77405c81fe78673afd5"],"state_sha256":"5538b1f91d9b85a5c8b7a77e51437ab9be40ae1e53db1db0e10603f4b6d6e1b5"}