{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WWBSSZ5VMCYJ427E4SFUZVTO7L","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":"0d15857deb3b4f592c9c9ce4c186248e5f195361e2b59b91f94a99a882894531","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T09:46:35Z","title_canon_sha256":"9062c62a5bfe889d85b58c7558e144de278ff835c4d902c8b52e0783dd303bf5"},"schema_version":"1.0","source":{"id":"2606.23104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23104","created_at":"2026-06-23T03:14:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23104v1","created_at":"2026-06-23T03:14:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23104","created_at":"2026-06-23T03:14:10Z"},{"alias_kind":"pith_short_12","alias_value":"WWBSSZ5VMCYJ","created_at":"2026-06-23T03:14:10Z"},{"alias_kind":"pith_short_16","alias_value":"WWBSSZ5VMCYJ427E","created_at":"2026-06-23T03:14:10Z"},{"alias_kind":"pith_short_8","alias_value":"WWBSSZ5V","created_at":"2026-06-23T03:14:10Z"}],"graph_snapshots":[{"event_id":"sha256:d6d9a112d492b5d848c4aea031b2021402198b9f48e97d81b95a9ef2aaaefd87","target":"graph","created_at":"2026-06-23T03:14:10Z","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/2606.23104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally regardless of their informativeness. We observe a consistent asymmetry in controlled filtering experiments: in both OPD and on-policy self distillation (OPSD), training only on incorrect SGOs outperforms training only on correct ones. Our further analysis suggests that models trained on correct-only SGOs tend to generate shorter reasoning traces and show weaker reflection behavior, while incorrect SGOs better preserve","authors_text":"Chen Lin, Kedi Chen, Wei Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T09:46:35Z","title":"ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23104","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:e04e7f103a002afd6d8ff07eb22ffa0118437c9ea79cceaaa7a38ba1c7f083e6","target":"record","created_at":"2026-06-23T03:14:10Z","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":"0d15857deb3b4f592c9c9ce4c186248e5f195361e2b59b91f94a99a882894531","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T09:46:35Z","title_canon_sha256":"9062c62a5bfe889d85b58c7558e144de278ff835c4d902c8b52e0783dd303bf5"},"schema_version":"1.0","source":{"id":"2606.23104","kind":"arxiv","version":1}},"canonical_sha256":"b5832967b560b09e6be4e48b4cd66efae9003a5c65cbda9433ed979caaaf3bf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5832967b560b09e6be4e48b4cd66efae9003a5c65cbda9433ed979caaaf3bf3","first_computed_at":"2026-06-23T03:14:10.012840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:10.012840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mtL7txGu2EQvzspQUUMkKEYm7ASTZUcZdlbYMJLTq/jNIjNsCvZLMeSQduNAqZuOuPKl2MYaeBs7r15P+289Cg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:10.013239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e04e7f103a002afd6d8ff07eb22ffa0118437c9ea79cceaaa7a38ba1c7f083e6","sha256:d6d9a112d492b5d848c4aea031b2021402198b9f48e97d81b95a9ef2aaaefd87"],"state_sha256":"6bf410fb6b8289e320691c3c354afc62ae04f1fb289fc2f6e2e979a6a522346e"}