{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DRMGGMGCWXJDUKML6KQJNFMNHK","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":"5fa76177c7ca9b796b370c085c72a2f9819d6a31695cdaea474a96162adc5d1c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T16:53:14Z","title_canon_sha256":"eeabed5d5dc7cbeb8ff2c3c3aefc9655736b5f07b4d0ecbd09947d4cf8939242"},"schema_version":"1.0","source":{"id":"2608.09836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09836","created_at":"2026-08-11T02:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09836v1","created_at":"2026-08-11T02:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09836","created_at":"2026-08-11T02:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"DRMGGMGCWXJD","created_at":"2026-08-11T02:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"DRMGGMGCWXJDUKML","created_at":"2026-08-11T02:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"DRMGGMGC","created_at":"2026-08-11T02:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:acc2d8554f64b8c2ad525da4bbdb6ca3371a712845383a924268355091c59225","target":"graph","created_at":"2026-08-11T02:25:13Z","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/2608.09836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses. We therefore shift our focus from agreement to teacher-student mismatch, and find that mismatch tokens can be mainly categorized into two types: student-excess tokens and student-deficit tokens. Student-excess tokens are generated by the student but assigned near-zero probability by the teacher; their log-ratio cor","authors_text":"Bingqing Jiang, Chengzhi Yu, Difan Zou, Shengze Xu, Xu Wang, Yujin Han, Zichao Yu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T16:53:14Z","title":"Mismatch Matters: On-Policy Distillation Beyond Token Agreement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09836","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":"sha256:9f708133127fba41116a9647afa8b560b52d5d40db3462b6e81d3ee2e75c81dc","target":"record","created_at":"2026-08-11T02:25:13Z","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":"5fa76177c7ca9b796b370c085c72a2f9819d6a31695cdaea474a96162adc5d1c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T16:53:14Z","title_canon_sha256":"eeabed5d5dc7cbeb8ff2c3c3aefc9655736b5f07b4d0ecbd09947d4cf8939242"},"schema_version":"1.0","source":{"id":"2608.09836","kind":"arxiv","version":1}},"canonical_sha256":"1c586330c2b5d23a298bf2a096958d3aa885c5ecfc00688f6f016c155284d9ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c586330c2b5d23a298bf2a096958d3aa885c5ecfc00688f6f016c155284d9ac","first_computed_at":"2026-08-11T02:25:13.220586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:25:13.220586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XaZBIIDIcvsKDjzHMy1mSDWCcvQWIk54qBvN1ny8tQRS6wX/6tVQCMQUpkgYABcllKm/89R73oC7pXvFyz1DBQ==","signature_status":"signed_v1","signed_at":"2026-08-11T02:25:13.222535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f708133127fba41116a9647afa8b560b52d5d40db3462b6e81d3ee2e75c81dc","sha256:acc2d8554f64b8c2ad525da4bbdb6ca3371a712845383a924268355091c59225"],"state_sha256":"8301daf04932436451a1507cf872ba257e2233021f79b894819cad7926586609"}