{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QXXXKLXK3SOU6Z63OE65GARYIV","short_pith_number":"pith:QXXXKLXK","schema_version":"1.0","canonical_sha256":"85ef752eeadc9d4f67db713dd30238455ced76ab388ee0aac2ccd2c6da82fc73","source":{"kind":"arxiv","id":"2608.13040","version":1},"attestation_state":"computed","paper":{"title":"Latent On-Policy Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guibin Zhang, Haoyu Zhao, Jiayang Lyu, Qibing Ren, Ran Sun, Shuicheng Yan, Xinlei Yu","submitted_at":"2026-08-13T10:05:51Z","abstract_excerpt":"Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effective pathway by using a privileged self-teacher to provide dense supervision on the student's own trajectories; however, existing methods still rely heavily on designer-specified privileged artifacts (e.g., answers, feedback, skills, or trajectories), limiting the end-to-end learnability and scalability required for continual self-improvement. In this work, we introduce Latent On-Policy Self-Distillation (LOPD), which,"},"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":"2608.13040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T10:05:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"16badb770780864204a1ab19ae01762137df44108f2ca76c593c41e1e1c2abed","abstract_canon_sha256":"071b695e02305d06158dbab3ea92e93d8c6a9e3cad6edc5cbdf67d375c77a706"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:11.625851Z","signature_b64":"dKDyTrhddn4W/2KeGdUDfZQfrl9FWS8YMvjmlcZGcmv4mW/KTJnb292jUfIoao44c3u//fDXg95k8TYZIaxUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85ef752eeadc9d4f67db713dd30238455ced76ab388ee0aac2ccd2c6da82fc73","last_reissued_at":"2026-08-14T01:00:11.623810Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:11.623810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent On-Policy Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guibin Zhang, Haoyu Zhao, Jiayang Lyu, Qibing Ren, Ran Sun, Shuicheng Yan, Xinlei Yu","submitted_at":"2026-08-13T10:05:51Z","abstract_excerpt":"Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effective pathway by using a privileged self-teacher to provide dense supervision on the student's own trajectories; however, existing methods still rely heavily on designer-specified privileged artifacts (e.g., answers, feedback, skills, or trajectories), limiting the end-to-end learnability and scalability required for continual self-improvement. In this work, we introduce Latent On-Policy Self-Distillation (LOPD), which,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13040","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/2608.13040/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":"2608.13040","created_at":"2026-08-14T01:00:11.624817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13040v1","created_at":"2026-08-14T01:00:11.624817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13040","created_at":"2026-08-14T01:00:11.624817+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXXXKLXK3SOU","created_at":"2026-08-14T01:00:11.624817+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXXXKLXK3SOU6Z63","created_at":"2026-08-14T01:00:11.624817+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXXXKLXK","created_at":"2026-08-14T01:00:11.624817+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/QXXXKLXK3SOU6Z63OE65GARYIV","json":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV.json","graph_json":"https://pith.science/api/pith-number/QXXXKLXK3SOU6Z63OE65GARYIV/graph.json","events_json":"https://pith.science/api/pith-number/QXXXKLXK3SOU6Z63OE65GARYIV/events.json","paper":"https://pith.science/paper/QXXXKLXK"},"agent_actions":{"view_html":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV","download_json":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV.json","view_paper":"https://pith.science/paper/QXXXKLXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13040&json=true","fetch_graph":"https://pith.science/api/pith-number/QXXXKLXK3SOU6Z63OE65GARYIV/graph.json","fetch_events":"https://pith.science/api/pith-number/QXXXKLXK3SOU6Z63OE65GARYIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/action/storage_attestation","attest_author":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/action/author_attestation","sign_citation":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/action/citation_signature","submit_replication":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/action/replication_record"}},"created_at":"2026-08-14T01:00:11.624817+00:00","updated_at":"2026-08-14T01:00:11.624817+00:00"}