{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QXXXKLXK3SOU6Z63OE65GARYIV","short_pith_number":"pith:QXXXKLXK","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"},"canonical_sha256":"85ef752eeadc9d4f67db713dd30238455ced76ab388ee0aac2ccd2c6da82fc73","source":{"kind":"arxiv","id":"2608.13040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13040","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13040v1","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13040","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"QXXXKLXK3SOU","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"QXXXKLXK3SOU6Z63","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"QXXXKLXK","created_at":"2026-08-14T01:00:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QXXXKLXK3SOU6Z63OE65GARYIV","target":"record","payload":{"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"},"canonical_sha256":"85ef752eeadc9d4f67db713dd30238455ced76ab388ee0aac2ccd2c6da82fc73","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"},"source_kind":"arxiv","source_id":"2608.13040","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T01:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IJSuwvCvhwlVgNikcgtlKFwSkWS4aoRmo41yulj38eQha1/wCzEXNbf6l2j9x/xVK0geoMjraqOsX0ZY6VmqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:56:20.143938Z"},"content_sha256":"764609577d1a8c1bc9332ba3e39839a2105ba4df43a676c3fd9b12f23dcf5461","schema_version":"1.0","event_id":"sha256:764609577d1a8c1bc9332ba3e39839a2105ba4df43a676c3fd9b12f23dcf5461"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QXXXKLXK3SOU6Z63OE65GARYIV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T01:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OxF3nplMVbg02YhfOWyYq7Vrzg4758IHu8fOVmosOWPu5BxT4ESBofBSvC+XPd+sjoJv99YyvGlQhhksGmZiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:56:20.144582Z"},"content_sha256":"c9dc2c901e07003233996824463f2da4b9ca3ccd4d3a6a54ebbefa9f5cfe42b4","schema_version":"1.0","event_id":"sha256:c9dc2c901e07003233996824463f2da4b9ca3ccd4d3a6a54ebbefa9f5cfe42b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/bundle.json","state_url":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXXXKLXK3SOU6Z63OE65GARYIV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T00:56:20Z","links":{"resolver":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV","bundle":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/bundle.json","state":"https://pith.science/pith/QXXXKLXK3SOU6Z63OE65GARYIV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXXXKLXK3SOU6Z63OE65GARYIV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QXXXKLXK3SOU6Z63OE65GARYIV","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":"071b695e02305d06158dbab3ea92e93d8c6a9e3cad6edc5cbdf67d375c77a706","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T10:05:51Z","title_canon_sha256":"16badb770780864204a1ab19ae01762137df44108f2ca76c593c41e1e1c2abed"},"schema_version":"1.0","source":{"id":"2608.13040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13040","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13040v1","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13040","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"QXXXKLXK3SOU","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"QXXXKLXK3SOU6Z63","created_at":"2026-08-14T01:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"QXXXKLXK","created_at":"2026-08-14T01:00:11Z"}],"graph_snapshots":[{"event_id":"sha256:c9dc2c901e07003233996824463f2da4b9ca3ccd4d3a6a54ebbefa9f5cfe42b4","target":"graph","created_at":"2026-08-14T01:00:11Z","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/2608.13040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Guibin Zhang, Haoyu Zhao, Jiayang Lyu, Qibing Ren, Ran Sun, Shuicheng Yan, Xinlei Yu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T10:05:51Z","title":"Latent On-Policy Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13040","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":"sha256:764609577d1a8c1bc9332ba3e39839a2105ba4df43a676c3fd9b12f23dcf5461","target":"record","created_at":"2026-08-14T01:00:11Z","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":"071b695e02305d06158dbab3ea92e93d8c6a9e3cad6edc5cbdf67d375c77a706","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T10:05:51Z","title_canon_sha256":"16badb770780864204a1ab19ae01762137df44108f2ca76c593c41e1e1c2abed"},"schema_version":"1.0","source":{"id":"2608.13040","kind":"arxiv","version":1}},"canonical_sha256":"85ef752eeadc9d4f67db713dd30238455ced76ab388ee0aac2ccd2c6da82fc73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85ef752eeadc9d4f67db713dd30238455ced76ab388ee0aac2ccd2c6da82fc73","first_computed_at":"2026-08-14T01:00:11.623810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:11.623810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dKDyTrhddn4W/2KeGdUDfZQfrl9FWS8YMvjmlcZGcmv4mW/KTJnb292jUfIoao44c3u//fDXg95k8TYZIaxUCg==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:11.625851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:764609577d1a8c1bc9332ba3e39839a2105ba4df43a676c3fd9b12f23dcf5461","sha256:c9dc2c901e07003233996824463f2da4b9ca3ccd4d3a6a54ebbefa9f5cfe42b4"],"state_sha256":"092a154ee16587e7e05554ca0b5316bed28592a170147c0115c844174bd8525f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIK6FalmxWgrIufZx3puxBo1PSXtW0kzWTQdUaEvJEfQ28cs6lkinDpdF0sdibSeUzEKL8g5vwtFTOemYtRUCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T00:56:20.150138Z","bundle_sha256":"6cc22c69c20031a2db03f6f3fcb5ccbe82434bdd57c836f6f03f10af9f689f80"}}