{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:46EPMDWDBYUN53NWAI4TUUNFGV","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":"902a2a074efa80f169de7a7b8723345e1349375a4a6e75021ed47ac754694d49","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T15:40:07Z","title_canon_sha256":"f75b5af941746c85b196894abab4245d5b92932c4da99d3960b409dacc0d5fd5"},"schema_version":"1.0","source":{"id":"2608.09745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09745","created_at":"2026-08-11T02:24:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09745v1","created_at":"2026-08-11T02:24:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09745","created_at":"2026-08-11T02:24:55Z"},{"alias_kind":"pith_short_12","alias_value":"46EPMDWDBYUN","created_at":"2026-08-11T02:24:55Z"},{"alias_kind":"pith_short_16","alias_value":"46EPMDWDBYUN53NW","created_at":"2026-08-11T02:24:55Z"},{"alias_kind":"pith_short_8","alias_value":"46EPMDWD","created_at":"2026-08-11T02:24:55Z"}],"graph_snapshots":[{"event_id":"sha256:d5b19387a5b67d7578b1425f49c225c789d74d24ca87b9d9ecebec5306d1b2a6","target":"graph","created_at":"2026-08-11T02:24:55Z","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/2608.09745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards. However, the self-teacher policy used in OPSD is typically a stop-gradient or exponential-moving-average copy of the policy conditioned on additional context information, and thus co-evolves with both the student policy and its on-policy context distribution. Directly matching such a moving target with a fixed projection objective can lead to unstable optimization or ","authors_text":"Che Liu, Entong Li, Harrison Bo Hua Zhu, Huihang Liu, Kaiyu Li, Li Zeng, Wenxuan Yuan, Xiaoyuan Cheng, Yanlong Zhao, Zhuo Sun","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T15:40:07Z","title":"SR-OPSD: Self-Referenced On-Policy Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09745","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":"sha256:76f4c82dd9df17a31f4427a12dfafd4cf387ec259298e637dc8da358e0f17c96","target":"record","created_at":"2026-08-11T02:24:55Z","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":"902a2a074efa80f169de7a7b8723345e1349375a4a6e75021ed47ac754694d49","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T15:40:07Z","title_canon_sha256":"f75b5af941746c85b196894abab4245d5b92932c4da99d3960b409dacc0d5fd5"},"schema_version":"1.0","source":{"id":"2608.09745","kind":"arxiv","version":1}},"canonical_sha256":"e788f60ec30e28deedb602393a51a535712c6dee31795373a15d16fb0f0e1877","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e788f60ec30e28deedb602393a51a535712c6dee31795373a15d16fb0f0e1877","first_computed_at":"2026-08-11T02:24:55.968604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:24:55.968604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dIK8AttOHG2K8ka42KAINhKm6g205wVpSCGYgh4BwgZeGTSih2F/n23dKhbTep14UWO46dvd5G41yn5L2xvbCA==","signature_status":"signed_v1","signed_at":"2026-08-11T02:24:55.970336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76f4c82dd9df17a31f4427a12dfafd4cf387ec259298e637dc8da358e0f17c96","sha256:d5b19387a5b67d7578b1425f49c225c789d74d24ca87b9d9ecebec5306d1b2a6"],"state_sha256":"7aeee63340878a1a3e8e4d2a6dd735e36b3774d36c574ed46299d056630444ab"}