{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q2OKYJFM7PI5LV7RKSYPHNGCF6","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":"cd4226445d0f4d9417470e04874a28dfb3d8b2630d659a66d2d281552558610f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T13:30:29Z","title_canon_sha256":"264cb6fd65798cbe7b46385a3db6551bef3bb0a8c605750fd4c50a1292c5e81e"},"schema_version":"1.0","source":{"id":"2606.09475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09475","created_at":"2026-06-09T02:08:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09475v1","created_at":"2026-06-09T02:08:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09475","created_at":"2026-06-09T02:08:50Z"},{"alias_kind":"pith_short_12","alias_value":"Q2OKYJFM7PI5","created_at":"2026-06-09T02:08:50Z"},{"alias_kind":"pith_short_16","alias_value":"Q2OKYJFM7PI5LV7R","created_at":"2026-06-09T02:08:50Z"},{"alias_kind":"pith_short_8","alias_value":"Q2OKYJFM","created_at":"2026-06-09T02:08:50Z"}],"graph_snapshots":[{"event_id":"sha256:ae7784db7fd7f57cb767f7be3353a890a40b5ac34041c49cf2a130b8e87bc94f","target":"graph","created_at":"2026-06-09T02:08:50Z","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/2606.09475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior. This supports the `persona selection' (PSM) hypothesis: during pre-training, LLMs learn to simulate different characters and perspectives, which can be elicited and refined during post-training. This paper investigates the converse phenomenon, `emergent alignment', and uses it to support and refine the PSM and motivate a novel desideratum for alignment. We finetune a helpful-only model on broad and narrow safety tasks. To create SFT samples, we follow the `Constitutional AI' (CAI)","authors_text":"Alejandro Perez Carballo, Cameron McNamara, Guillermo Del Pinal, Youngchan Lee","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T13:30:29Z","title":"Emergent alignment and the projectability of ethical personas"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09475","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":"sha256:829de8f000ac3802dedc3fbcce50a636eb5162b9c9589ff7d2a12ddef106bc94","target":"record","created_at":"2026-06-09T02:08:50Z","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":"cd4226445d0f4d9417470e04874a28dfb3d8b2630d659a66d2d281552558610f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T13:30:29Z","title_canon_sha256":"264cb6fd65798cbe7b46385a3db6551bef3bb0a8c605750fd4c50a1292c5e81e"},"schema_version":"1.0","source":{"id":"2606.09475","kind":"arxiv","version":1}},"canonical_sha256":"869cac24acfbd1d5d7f154b0f3b4c22fb0743e6bd8e67f0e87d68c9d4b6ef06b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"869cac24acfbd1d5d7f154b0f3b4c22fb0743e6bd8e67f0e87d68c9d4b6ef06b","first_computed_at":"2026-06-09T02:08:50.546509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:50.546509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RCcYQ9z5rKCmKIcVLE7mYvhFksoIeNva3gu/4URXxzvBs5Qw8dcXpBM7emlc2uBPQxHPNgtGP3tyuGMjw365Dw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:50.547409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:829de8f000ac3802dedc3fbcce50a636eb5162b9c9589ff7d2a12ddef106bc94","sha256:ae7784db7fd7f57cb767f7be3353a890a40b5ac34041c49cf2a130b8e87bc94f"],"state_sha256":"64226f49e7bdce5f0b95e4d55d754e024c17b598412613f3a71686b1fdf6d708"}