{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RQDXIECF7GBRHAS6XXUBEJGOMF","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":"6c83ab8782021ffd913a4fcc4d51bd72c8d4673501a0b2886e71c4e10a88836c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T15:54:24Z","title_canon_sha256":"e357a9b4e485ce54fab81ec2f87fbf098c2abe2e9fdbbb0ac3d29886e346e27c"},"schema_version":"1.0","source":{"id":"2606.03810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03810","created_at":"2026-06-03T02:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03810v1","created_at":"2026-06-03T02:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03810","created_at":"2026-06-03T02:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"RQDXIECF7GBR","created_at":"2026-06-03T02:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"RQDXIECF7GBRHAS6","created_at":"2026-06-03T02:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"RQDXIECF","created_at":"2026-06-03T02:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:352c12b31496ca935772df7e0c661c0767a5cce1e19f66b06a7a724d9797a2f4","target":"graph","created_at":"2026-06-03T02:06:03Z","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/2606.03810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures. Such methods are simple, scalable, and largely label-free, but their effects on model alignment remain poorly understood. Could the self-bootstrapping nature of these methods amplify undesired behavior in models? We test seven consistency training methods on 108 ``model organisms: open-source models (7B--70B) fine-tuned to exhibit various forms of controlled misaligned behavior. We find that outcomes vary significantly: consistency training generally suppresses reward hacking and em","authors_text":"Arathi Mani, David Demitri Africa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T15:54:24Z","title":"Consistency Training Can Entrench Misalignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03810","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:dade6696af9c03286cdd6bb3263ac0c47c037f078d3fcc2d439af1e031810011","target":"record","created_at":"2026-06-03T02:06:03Z","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":"6c83ab8782021ffd913a4fcc4d51bd72c8d4673501a0b2886e71c4e10a88836c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T15:54:24Z","title_canon_sha256":"e357a9b4e485ce54fab81ec2f87fbf098c2abe2e9fdbbb0ac3d29886e346e27c"},"schema_version":"1.0","source":{"id":"2606.03810","kind":"arxiv","version":1}},"canonical_sha256":"8c07741045f98313825ebde81224ce614efd30f7c026d523623e880c13aee4be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c07741045f98313825ebde81224ce614efd30f7c026d523623e880c13aee4be","first_computed_at":"2026-06-03T02:06:03.054718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:03.054718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yR0ZJ+m/6lyqrYjInjffeGF+n2TxkDCQezh/9JQZzLnqu60W5UtqK6HiKsrMn1ESuybwi69nR0U8ek14W2s+Dw==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:03.055130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dade6696af9c03286cdd6bb3263ac0c47c037f078d3fcc2d439af1e031810011","sha256:352c12b31496ca935772df7e0c661c0767a5cce1e19f66b06a7a724d9797a2f4"],"state_sha256":"0a090c69af3ec24b33aebb993f5002444c1d5e7eab0f528271dbd1a01ba95e15"}