{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3X7F2TFYUR3OWYQ7PPAHQ4QWLK","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":"9202cfd71b6c6adaae2be1473cffd2b8db085f242d1f393a5ba4fc30dbdc2c1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:17:56Z","title_canon_sha256":"a5d5d6abd60b6a87ce8a2bfe246f732c526b0c35e26873ce896c2bbf98ba49c2"},"schema_version":"1.0","source":{"id":"2606.03089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03089","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03089v1","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03089","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"3X7F2TFYUR3O","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"3X7F2TFYUR3OWYQ7","created_at":"2026-06-03T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"3X7F2TFY","created_at":"2026-06-03T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:516bc91b9fa6a84ce4373ca1ef960532e655b5adbd88c8d1f0d419fca9d2f721","target":"graph","created_at":"2026-06-03T01:05:31Z","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/2606.03089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervision. Prior work has shown that OPSD can collapse in verifiable reasoning tasks, but safety alignment differs in that it is guided by high-level constitutions rather than explicit target answers, making it a natural setting to revisit dense distillation. However, our pilot study show that safety OPSD still suffers from severe collapse: constitutional conditioning contracts the teacher distribution toward short and ove","authors_text":"Kun Yang, Ming Wen, Shiwen Cui, Xiang Zheng, Xingjun Ma, Yu-Gang Jiang, Yuhao Sun, Yunhao Feng, Yuxuan Liu, Zhuoer Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:17:56Z","title":"Constitutional On-Policy Safe Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03089","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:d71b2246c4081c4240b3ec2739654715ea68adac8b1eefd2d999ab8fd58a0392","target":"record","created_at":"2026-06-03T01:05:31Z","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":"9202cfd71b6c6adaae2be1473cffd2b8db085f242d1f393a5ba4fc30dbdc2c1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:17:56Z","title_canon_sha256":"a5d5d6abd60b6a87ce8a2bfe246f732c526b0c35e26873ce896c2bbf98ba49c2"},"schema_version":"1.0","source":{"id":"2606.03089","kind":"arxiv","version":1}},"canonical_sha256":"ddfe5d4cb8a476eb621f7bc07872165a99a6e235f33cff20165e4f6c64e4ca69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddfe5d4cb8a476eb621f7bc07872165a99a6e235f33cff20165e4f6c64e4ca69","first_computed_at":"2026-06-03T01:05:31.316637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:31.316637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAjeIBocVo/t8v8aCd33rKn6jAFhuYcGFubAjtAU7GX41Bd0vzHIuxkjrWhYmZEoIvhUGQymZ8gCv+vMt8JBDg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:31.317074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d71b2246c4081c4240b3ec2739654715ea68adac8b1eefd2d999ab8fd58a0392","sha256:516bc91b9fa6a84ce4373ca1ef960532e655b5adbd88c8d1f0d419fca9d2f721"],"state_sha256":"52f5c08ec9b035727d829e9199af206a65309377b75e3bc3c64e6855dcb5587e"}