{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NKOALLLDYIABXXFKLYS76M3P65","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":"4e213dc17a48eb7693f02beaf9998c49e3cdf761313aebc259fe5cf2fd2e8745","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T17:59:46Z","title_canon_sha256":"ad383664d21c0333276ee830db2a8ce69df77ab0eadcf9b2111e402a72a67a51"},"schema_version":"1.0","source":{"id":"2607.26057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26057","created_at":"2026-07-29T01:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26057v1","created_at":"2026-07-29T01:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26057","created_at":"2026-07-29T01:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"NKOALLLDYIAB","created_at":"2026-07-29T01:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"NKOALLLDYIABXXFK","created_at":"2026-07-29T01:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"NKOALLLD","created_at":"2026-07-29T01:26:21Z"}],"graph_snapshots":[{"event_id":"sha256:a179156d80f749829bea59f575ed5a908bce7a2a419e232cb548b013f7014fc9","target":"graph","created_at":"2026-07-29T01:26:21Z","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/2607.26057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all subsequent generation builds on this deviation, producing misdirected continuations that elicit unreliable supervision and waste compute. We identify a teacher-student continuation asymmetry on failed prefixes, where the teacher tends to redirect while the student continues along the original direction, and convert it into a label-free handoff trigger in Relay On-Policy Distillation (Relay-OPD). During traini","authors_text":"Haiwen Hong, Haolei Xu, Hongxing Li, Weiming Lu, Xiaowen Xu, Yiwen Qiu, Yongliang Shen, Zixuan Ni","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T17:59:46Z","title":"Pass the Baton: Trajectory-Relayed On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26057","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":"sha256:073513fb0aa4e2ff4b46c346bf3117208dd8c0ef8b82b5e5f143a970d62420e4","target":"record","created_at":"2026-07-29T01:26:21Z","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":"4e213dc17a48eb7693f02beaf9998c49e3cdf761313aebc259fe5cf2fd2e8745","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T17:59:46Z","title_canon_sha256":"ad383664d21c0333276ee830db2a8ce69df77ab0eadcf9b2111e402a72a67a51"},"schema_version":"1.0","source":{"id":"2607.26057","kind":"arxiv","version":1}},"canonical_sha256":"6a9c05ad63c2001bdcaa5e25ff336ff77b181835601a369fd695a3eb3404d5af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a9c05ad63c2001bdcaa5e25ff336ff77b181835601a369fd695a3eb3404d5af","first_computed_at":"2026-07-29T01:26:21.927102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:26:21.927102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hgfPLP8ar9y/z64/1k5M2XsgdWHOXAJyVxv5mbA8s5RvybDICVKZJM28H0GpdUd4Dzd8CKvnduZSVDctGcXpDA==","signature_status":"signed_v1","signed_at":"2026-07-29T01:26:21.927944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.26057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:073513fb0aa4e2ff4b46c346bf3117208dd8c0ef8b82b5e5f143a970d62420e4","sha256:a179156d80f749829bea59f575ed5a908bce7a2a419e232cb548b013f7014fc9"],"state_sha256":"5e41de40add817a78ad66ad9e96fdaad1a58e5cb7ddf1047e8d466dc2a463f33"}