{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NKOALLLDYIABXXFKLYS76M3P65","short_pith_number":"pith:NKOALLLD","schema_version":"1.0","canonical_sha256":"6a9c05ad63c2001bdcaa5e25ff336ff77b181835601a369fd695a3eb3404d5af","source":{"kind":"arxiv","id":"2607.26057","version":1},"attestation_state":"computed","paper":{"title":"Pass the Baton: Trajectory-Relayed On-Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haiwen Hong, Haolei Xu, Hongxing Li, Weiming Lu, Xiaowen Xu, Yiwen Qiu, Yongliang Shen, Zixuan Ni","submitted_at":"2026-07-28T17:59:46Z","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"},"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":"2607.26057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T17:59:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad383664d21c0333276ee830db2a8ce69df77ab0eadcf9b2111e402a72a67a51","abstract_canon_sha256":"4e213dc17a48eb7693f02beaf9998c49e3cdf761313aebc259fe5cf2fd2e8745"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:26:21.927944Z","signature_b64":"hgfPLP8ar9y/z64/1k5M2XsgdWHOXAJyVxv5mbA8s5RvybDICVKZJM28H0GpdUd4Dzd8CKvnduZSVDctGcXpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a9c05ad63c2001bdcaa5e25ff336ff77b181835601a369fd695a3eb3404d5af","last_reissued_at":"2026-07-29T01:26:21.927102Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:26:21.927102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pass the Baton: Trajectory-Relayed On-Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haiwen Hong, Haolei Xu, Hongxing Li, Weiming Lu, Xiaowen Xu, Yiwen Qiu, Yongliang Shen, Zixuan Ni","submitted_at":"2026-07-28T17:59:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26057","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/2607.26057/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":"2607.26057","created_at":"2026-07-29T01:26:21.927546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26057v1","created_at":"2026-07-29T01:26:21.927546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26057","created_at":"2026-07-29T01:26:21.927546+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKOALLLDYIAB","created_at":"2026-07-29T01:26:21.927546+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKOALLLDYIABXXFK","created_at":"2026-07-29T01:26:21.927546+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKOALLLD","created_at":"2026-07-29T01:26:21.927546+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/NKOALLLDYIABXXFKLYS76M3P65","json":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65.json","graph_json":"https://pith.science/api/pith-number/NKOALLLDYIABXXFKLYS76M3P65/graph.json","events_json":"https://pith.science/api/pith-number/NKOALLLDYIABXXFKLYS76M3P65/events.json","paper":"https://pith.science/paper/NKOALLLD"},"agent_actions":{"view_html":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65","download_json":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65.json","view_paper":"https://pith.science/paper/NKOALLLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26057&json=true","fetch_graph":"https://pith.science/api/pith-number/NKOALLLDYIABXXFKLYS76M3P65/graph.json","fetch_events":"https://pith.science/api/pith-number/NKOALLLDYIABXXFKLYS76M3P65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65/action/storage_attestation","attest_author":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65/action/author_attestation","sign_citation":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65/action/citation_signature","submit_replication":"https://pith.science/pith/NKOALLLDYIABXXFKLYS76M3P65/action/replication_record"}},"created_at":"2026-07-29T01:26:21.927546+00:00","updated_at":"2026-07-29T01:26:21.927546+00:00"}