{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y2E6XHWKWQRZBRYGAXPSMFCTBE","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":"f8e3146de87172a38c33434a1d6379a56145c7323db3cb3bd160c3b41642a6fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T15:23:25Z","title_canon_sha256":"bbdf77534df57d987f7d373961604e49f1e06b32520f8ddc7284c76cc057c2cf"},"schema_version":"1.0","source":{"id":"2608.08764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08764","created_at":"2026-08-11T01:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08764v1","created_at":"2026-08-11T01:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08764","created_at":"2026-08-11T01:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"Y2E6XHWKWQRZ","created_at":"2026-08-11T01:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"Y2E6XHWKWQRZBRYG","created_at":"2026-08-11T01:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"Y2E6XHWK","created_at":"2026-08-11T01:25:16Z"}],"graph_snapshots":[{"event_id":"sha256:7b48712e0baeee9e2630a5702bb5c073abd50226fbd9a5229ff4bc2e6e67c3ef","target":"graph","created_at":"2026-08-11T01:25:16Z","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/2608.08764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation improves language-model reasoning by querying a teacher on states actually visited by the student. Recent methods create a powerful information asymmetry by exposing the teacher to privileged context, yet they fundamentally rely on external supervision---such as gold solutions or verifiers---to construct this advantage. We introduce CoDA (Consensus and Disagreement Alignment), a fully unsupervised framework that creates reliable privileged information entirely from the latent uncertainty structure of a model's own unlabeled rollouts. CoDA extracts two complementary ","authors_text":"Chunyu Yang, Jiaxin Guo, Xuanbo Fan, Yanwei Yue, Yan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T15:23:25Z","title":"Learning from Consensus and Disagreement: Unsupervised On-Policy Self-Distillation with Minority-Trajectory Contrast"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08764","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":"sha256:63d3da51497274a65ebff3a4af87e1f454af63d9d395c8e1166ab0612cd475bc","target":"record","created_at":"2026-08-11T01:25:16Z","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":"f8e3146de87172a38c33434a1d6379a56145c7323db3cb3bd160c3b41642a6fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T15:23:25Z","title_canon_sha256":"bbdf77534df57d987f7d373961604e49f1e06b32520f8ddc7284c76cc057c2cf"},"schema_version":"1.0","source":{"id":"2608.08764","kind":"arxiv","version":1}},"canonical_sha256":"c689eb9ecab42390c70605df261453092b2fd8c58768a94893c82971415fcd6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c689eb9ecab42390c70605df261453092b2fd8c58768a94893c82971415fcd6d","first_computed_at":"2026-08-11T01:25:16.153326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:25:16.153326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TRQiMrw66uX5izkgJ1BjvKb2OIVzPB97EbT10E9SCWEo+PBbLz43FKdlrPsPLyVKI3xYhI/S2WFio2Qx1FMSDQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:25:16.155862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63d3da51497274a65ebff3a4af87e1f454af63d9d395c8e1166ab0612cd475bc","sha256:7b48712e0baeee9e2630a5702bb5c073abd50226fbd9a5229ff4bc2e6e67c3ef"],"state_sha256":"904479f9f0a4dbcfacca473593db39ba062c819d47be3a58c183bfcdfb68fda3"}