{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AZYETMJ5DE4LJDCFVLUIUDYIPG","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":"96727bf12aee54e7089036ee361c685185a16514169f1175bd1e8d5213867053","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T09:24:19Z","title_canon_sha256":"587141b1dce7756f782ab58139ce2c7e66ad8dad10eb0cce8beb630f8a1ba16b"},"schema_version":"1.0","source":{"id":"2606.18844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18844","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18844v1","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18844","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"AZYETMJ5DE4L","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"AZYETMJ5DE4LJDCF","created_at":"2026-06-19T16:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"AZYETMJ5","created_at":"2026-06-19T16:11:49Z"}],"graph_snapshots":[{"event_id":"sha256:4e46f68561a89335a382d85dd89652081270650b8144bbe28d31d418185b59a4","target":"graph","created_at":"2026-06-19T16:11:49Z","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/2606.18844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns. Consequently, the model learns to imitate a privileged distribution rather than receiving fine-grained corrections that pinpoint where and why its reasoning fails. ","authors_text":"Chujun Qin, Guanjun Jiang, Hang Gao, Jingyi Wang, Yang Yang, Yifeng Luo, Yuan Chen, Zhilin Huang, Ziqiang Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T09:24:19Z","title":"Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18844","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":"sha256:8fba24b8168fddaa9dcc04ca85fb553ada5a19b11031ff5b76c2cfde3b8fa429","target":"record","created_at":"2026-06-19T16:11:49Z","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":"96727bf12aee54e7089036ee361c685185a16514169f1175bd1e8d5213867053","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T09:24:19Z","title_canon_sha256":"587141b1dce7756f782ab58139ce2c7e66ad8dad10eb0cce8beb630f8a1ba16b"},"schema_version":"1.0","source":{"id":"2606.18844","kind":"arxiv","version":1}},"canonical_sha256":"067049b13d1938b48c45aae88a0f0879af72e3e972d3cb6b29a032a7bc25cd7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"067049b13d1938b48c45aae88a0f0879af72e3e972d3cb6b29a032a7bc25cd7c","first_computed_at":"2026-06-19T16:11:49.178635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:49.178635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Exs5rhhV9x4TfdNbLoBu8GdfnhSi22a6WIatAO3StGc/kJJxDUomPJlPU6/FrQBOpAN+hjAhU+W49YFlBHqoCg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:49.178980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fba24b8168fddaa9dcc04ca85fb553ada5a19b11031ff5b76c2cfde3b8fa429","sha256:4e46f68561a89335a382d85dd89652081270650b8144bbe28d31d418185b59a4"],"state_sha256":"ff036ebf3198ad8f1aff442dd135373dff8bf9e703462db955700f9970a6086a"}