{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:32IBIBPXXUWUGFXRU5WX4XWF7G","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":"275f196ac6cf7f1e17e85cccf6c53237c7aad6a43127059dd324ab24d06a12d8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T15:17:19Z","title_canon_sha256":"1246bdca0243de5df25e39514dbd0c0535c7631e2aaa20dad240da3b98c12d6e"},"schema_version":"1.0","source":{"id":"2605.30070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30070","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30070v1","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30070","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"32IBIBPXXUWU","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"32IBIBPXXUWUGFXR","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"32IBIBPX","created_at":"2026-05-29T02:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:c902bc168d1321a678aac768dcbf62dbe99d047b5f91aec64b5dadb4732bfd2b","target":"graph","created_at":"2026-05-29T02:06:09Z","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/2605.30070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPSD) is a promising recent approach that uses arbitrary feedback as learning signal, yet its reliability compared to established methods, such as GRPO, remains unclear. We identify a strikingly consistent linear correlation between the initial student-self-teacher performance gap and the final performance improvement in OPSD. This relationship holds across context types and model families, providing a powerful predictive law for anticipating the ou","authors_text":"Jerome Sieber, Matteo Saponati, Tommy He","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T15:17:19Z","title":"A Predictive Law for On-Policy Self-Distillation From World Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30070","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:e5b1fef7a8dc0e8127b67286c3d1135b1fbbb098a2c052a8d75d0fb3de8c52fa","target":"record","created_at":"2026-05-29T02:06:09Z","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":"275f196ac6cf7f1e17e85cccf6c53237c7aad6a43127059dd324ab24d06a12d8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T15:17:19Z","title_canon_sha256":"1246bdca0243de5df25e39514dbd0c0535c7631e2aaa20dad240da3b98c12d6e"},"schema_version":"1.0","source":{"id":"2605.30070","kind":"arxiv","version":1}},"canonical_sha256":"de901405f7bd2d4316f1a76d7e5ec5f9aa019ee78a96dfe41e7072caba9022dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de901405f7bd2d4316f1a76d7e5ec5f9aa019ee78a96dfe41e7072caba9022dc","first_computed_at":"2026-05-29T02:06:09.133214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:09.133214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fl41M6ckzn3adO35FOcUaIYm9LRKC15hHmobY6DPkDAB7eroVDnVzAxWxipywM0ux1NtMYzVk3clQnt/qq+tCw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:09.133625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5b1fef7a8dc0e8127b67286c3d1135b1fbbb098a2c052a8d75d0fb3de8c52fa","sha256:c902bc168d1321a678aac768dcbf62dbe99d047b5f91aec64b5dadb4732bfd2b"],"state_sha256":"08d668069064ccde41f253ba7f793602f630989f544968c60b5fc3c68df96238"}