{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7QRCYGXDBE3TVICUWSICZUL4CM","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":"c1db695b5ebb5abad0411c8d941e60cc3800329d543a0b32e194205d0eff0541","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T10:11:58Z","title_canon_sha256":"94afbce500e64b94f43cdab39ed016edd224928f53e511e7062636a342be92f9"},"schema_version":"1.0","source":{"id":"2606.09304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09304","created_at":"2026-06-09T02:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09304v1","created_at":"2026-06-09T02:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09304","created_at":"2026-06-09T02:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"7QRCYGXDBE3T","created_at":"2026-06-09T02:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"7QRCYGXDBE3TVICU","created_at":"2026-06-09T02:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"7QRCYGXD","created_at":"2026-06-09T02:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:341ba880fe7453bec5cd8699ad0c59ba2123b734bcdd9c960fb74d13e28d450e","target":"graph","created_at":"2026-06-09T02:08:13Z","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/2606.09304/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 trajectories with dense per-token supervision from a stronger teacher, and often outperforms off-policy distillation and standard reinforcement learning. However, we find that its effectiveness implicitly relies on two assumptions that frequently break in practice: trajectory-level alignment between the student and the teacher, and uniform token-level reliability of the teacher's preferences. We therefore propose Sign-Gated On-Policy Distillation (SG-OPD), which uses a binary verifier as a trust signal for the teacher at two complementar","authors_text":"Haoran Xu, Hongyu Wang, Jiaze Li, Xiaofeng Zhang, Xiaosong Yuan, Yifei Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T10:11:58Z","title":"SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09304","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":"sha256:0c48e8dab07f2e2479af98e96770f7f17033d308a011b8ff47ee28ce9baa6809","target":"record","created_at":"2026-06-09T02:08:13Z","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":"c1db695b5ebb5abad0411c8d941e60cc3800329d543a0b32e194205d0eff0541","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T10:11:58Z","title_canon_sha256":"94afbce500e64b94f43cdab39ed016edd224928f53e511e7062636a342be92f9"},"schema_version":"1.0","source":{"id":"2606.09304","kind":"arxiv","version":1}},"canonical_sha256":"fc222c1ae309373aa054b4902cd17c130f5b323035be9bdae8a70c39ada32a66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc222c1ae309373aa054b4902cd17c130f5b323035be9bdae8a70c39ada32a66","first_computed_at":"2026-06-09T02:08:13.797549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:13.797549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jPIGeWNr933KsIDg4vTWt8rQ9pjDcXlkLtFdKM8il4lHax6xnAn334+P+gq6MbeVtEvNtDg9JRCSF3xgnfOaAQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:13.798366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c48e8dab07f2e2479af98e96770f7f17033d308a011b8ff47ee28ce9baa6809","sha256:341ba880fe7453bec5cd8699ad0c59ba2123b734bcdd9c960fb74d13e28d450e"],"state_sha256":"84881b1f7db1dc4bd4937d1935d4adf3edca7b1de1ed2b1d79482b94cb9c2210"}