{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GWO37TFUAMZN7MX5BRGNSGYXV7","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":"dcca3ed177b1925f375e08da2a07dafb23fc45176f5e518621bf3562708568af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T16:03:33Z","title_canon_sha256":"04aa566e34387fee8a03b104e2d7401f63aa22255721c23f3f69f273c248d824"},"schema_version":"1.0","source":{"id":"2607.23731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23731","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23731v1","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23731","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"GWO37TFUAMZN","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"GWO37TFUAMZN7MX5","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"GWO37TFU","created_at":"2026-07-28T01:23:07Z"}],"graph_snapshots":[{"event_id":"sha256:886322b67991b7b1939fbcd6a86e46a4445b1c04f3cdda197afa6abc109f816d","target":"graph","created_at":"2026-07-28T01:23:07Z","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/2607.23731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes. These likelihoods are often read locally: agreement appears safe to imitate, whereas disagreement appears to identify an error. We show that both readings are confounded by the outcome of the completed trajectory. We introduce an outcome-resolved diagnostic that crosses pointwise teacher-student divergence with final-answer correctness, separating safe imitation, productive divergence, harmful divergence, and agreement-on-failure. In an eight","authors_text":"Guoqing Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T16:03:33Z","title":"Outcome-Confounded Local Supervision in On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23731","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:fa1b130545ec357e21784aba6b62e7f620aa9c0a5bfd3fa06baf47913b144f8b","target":"record","created_at":"2026-07-28T01:23:07Z","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":"dcca3ed177b1925f375e08da2a07dafb23fc45176f5e518621bf3562708568af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T16:03:33Z","title_canon_sha256":"04aa566e34387fee8a03b104e2d7401f63aa22255721c23f3f69f273c248d824"},"schema_version":"1.0","source":{"id":"2607.23731","kind":"arxiv","version":1}},"canonical_sha256":"359dbfccb40332dfb2fd0c4cd91b17afdb808013fcf74d5e96d7489f3743adfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"359dbfccb40332dfb2fd0c4cd91b17afdb808013fcf74d5e96d7489f3743adfe","first_computed_at":"2026-07-28T01:23:07.928284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:07.928284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KzqBTCM7EXkyod8tojMM91I9N3JOPAKAFCkF2yElREFzpXdPBAnINEG09hUK9J1hKIb2bhCeM8yPcU7VG8ZGAg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:07.929138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa1b130545ec357e21784aba6b62e7f620aa9c0a5bfd3fa06baf47913b144f8b","sha256:886322b67991b7b1939fbcd6a86e46a4445b1c04f3cdda197afa6abc109f816d"],"state_sha256":"0ccd810907273b46e2760293742e619c1a7f76994c5e0ea3d0460fe6c1a0e21d"}