{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZJYZJGWD5ASROHGAY3PENYE645","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":"3a9629a09ff0cf72374f1381c85fd5f294bf9dbe59a65bf2f3ef0002176f9caa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T17:18:23Z","title_canon_sha256":"25f84eac2fbfa0a91ddf9461650d62f99d5a30644f4d07bc6fd7d4f4270a24a4"},"schema_version":"1.0","source":{"id":"2608.06296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06296","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06296v1","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06296","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZJYZJGWD5ASR","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZJYZJGWD5ASROHGA","created_at":"2026-08-07T01:41:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZJYZJGWD","created_at":"2026-08-07T01:41:19Z"}],"graph_snapshots":[{"event_id":"sha256:20a7c743f3e1f68b20a3f1aa461cee29d5bf87689160259e65ead0e4b4d67c62","target":"graph","created_at":"2026-08-07T01:41:19Z","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/2608.06296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external supervision, including ground-truth signals, environmental feedback, or guidance from larger models, and therefore fall short of genuine \"self\"-distillation. In this study, we show that on-policy self-distillation can be achieved using only a model's own generations via internal consistency. We propose Unsupervised On-Policy Self-Distillation (U-OPSD). U-OPSD first samples multiple rollouts and constructs a pseudo-solutio","authors_text":"Bingyang Wang, Di Fu, Nuno Vasconcelos, Yijiang Li, Yijun Liang, Yunjie Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T17:18:23Z","title":"On-Policy Self-Distillation without Any Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06296","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":"sha256:28a10e1ee024d17b46787f7a13ea4ced076ac9f836023330d35b91cea32a36ae","target":"record","created_at":"2026-08-07T01:41:19Z","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":"3a9629a09ff0cf72374f1381c85fd5f294bf9dbe59a65bf2f3ef0002176f9caa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T17:18:23Z","title_canon_sha256":"25f84eac2fbfa0a91ddf9461650d62f99d5a30644f4d07bc6fd7d4f4270a24a4"},"schema_version":"1.0","source":{"id":"2608.06296","kind":"arxiv","version":1}},"canonical_sha256":"ca71949ac3e825171cc0c6de46e09ee764591bb974f660edbb085a63773bf4f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca71949ac3e825171cc0c6de46e09ee764591bb974f660edbb085a63773bf4f1","first_computed_at":"2026-08-07T01:41:19.146483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T01:41:19.146483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YTx9R68803tCzPtSxwUL7VTjNRlAscratvgtcwPqKHn1jBtONq/b85Wz+PTkz23aEwN8+8aEqJTr/Zi8aDsOAA==","signature_status":"signed_v1","signed_at":"2026-08-07T01:41:19.148427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28a10e1ee024d17b46787f7a13ea4ced076ac9f836023330d35b91cea32a36ae","sha256:20a7c743f3e1f68b20a3f1aa461cee29d5bf87689160259e65ead0e4b4d67c62"],"state_sha256":"efee1f51613eeea4208f2a44d543d797e09028c22e801b7fc92738ab3ad25d0d"}