{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CRXPDDUKWB55BMOZPI3XRNH6H6","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":"d21ae01a3c5c89f835829ce717bd022a17bb0fa309f181e8755ef370f9a6e0d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T02:31:13Z","title_canon_sha256":"dc67db7a2c8cfea8b8aa527d3b9cad11ff166c29a3a2fbe75679d0cd162ab72f"},"schema_version":"1.0","source":{"id":"2606.04036","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04036","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04036v1","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04036","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"CRXPDDUKWB55","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_16","alias_value":"CRXPDDUKWB55BMOZ","created_at":"2026-06-04T00:06:44Z"},{"alias_kind":"pith_short_8","alias_value":"CRXPDDUK","created_at":"2026-06-04T00:06:44Z"}],"graph_snapshots":[{"event_id":"sha256:b4296ef1ffaba0ea23bd961253f3195af88eda26b1a562076702d805956a6595","target":"graph","created_at":"2026-06-04T00:06:44Z","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/2606.04036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation, where a language model conditions on privileged context to supervise its own generations, is a promising source of dense supervision for sparse-reward reinforcement learning. Actually, it can be instantiated as an auxiliary full-vocabulary student-to-teacher reverse Kullback-Leibler divergence loss. We therefore propose SDPG, a self-distilled policy-gradient framework that combines group-relative verifier advantages with normalized standard deviation, exact full-vocabulary on-policy self-distillation, as well as reference-policy KL regularization. Empirically, SDPG","authors_text":"Quanquan Gu, Shiyuan Zhang, Yifan Zhang, Yifeng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T02:31:13Z","title":"Self-Distilled Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04036","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:fded223af7bf23f5c08dc442d5ebf3cf070f4c0094dc149961e21e65ffb367f9","target":"record","created_at":"2026-06-04T00:06:44Z","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":"d21ae01a3c5c89f835829ce717bd022a17bb0fa309f181e8755ef370f9a6e0d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T02:31:13Z","title_canon_sha256":"dc67db7a2c8cfea8b8aa527d3b9cad11ff166c29a3a2fbe75679d0cd162ab72f"},"schema_version":"1.0","source":{"id":"2606.04036","kind":"arxiv","version":1}},"canonical_sha256":"146ef18e8ab07bd0b1d97a3778b4fe3f883599aa8fe74ef10e2296068faee493","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"146ef18e8ab07bd0b1d97a3778b4fe3f883599aa8fe74ef10e2296068faee493","first_computed_at":"2026-06-04T00:06:44.970102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T00:06:44.970102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"86m12Pakh81TBybLhXAaL/J9H3Hcf9RSKSMGBgm3UbO+cNPosR/jO5VsrxLXSGpn4zhePvh8XCOIXpWMFOLLCA==","signature_status":"signed_v1","signed_at":"2026-06-04T00:06:44.970506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04036","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fded223af7bf23f5c08dc442d5ebf3cf070f4c0094dc149961e21e65ffb367f9","sha256:b4296ef1ffaba0ea23bd961253f3195af88eda26b1a562076702d805956a6595"],"state_sha256":"088f3bd89fb16f5f87cd7e3b2f557b4c05fa6cc96052d7f99ad15292dab4894f"}