{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PYKLJPZJDLIDXNCZ7XZCJQEXTG","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":"b76d62a2fd142e1cdd0289e87ed857046b98a844458e9d0a68e1403f75317ebb","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-05T21:23:15Z","title_canon_sha256":"c7939a15d9e2be0bdcf75ba3ff7a09e1e84b74416cd20b47d0b2c184f6ac9688"},"schema_version":"1.0","source":{"id":"2607.04510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04510","created_at":"2026-07-07T02:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04510v1","created_at":"2026-07-07T02:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04510","created_at":"2026-07-07T02:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"PYKLJPZJDLID","created_at":"2026-07-07T02:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"PYKLJPZJDLIDXNCZ","created_at":"2026-07-07T02:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"PYKLJPZJ","created_at":"2026-07-07T02:19:22Z"}],"graph_snapshots":[{"event_id":"sha256:597d88e75f745d8c69f18e0bbcff4b860a6eded0d91f2f7568ad3f5af8842874","target":"graph","created_at":"2026-07-07T02:19:22Z","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/2607.04510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.5 models by a latent persona direction, and that direction is causal in open weights. Transplanting it into a model that shares only pretraining with its source induces broad EM (2.83 +/- 0.26% misaligned against a random-direction floor of ~1.1%), and ablating a model's own direction roughly halves an overt inducer's broadcast (21% to 10%). The transplant doubles as a measurement method, causally assaying directions that a source model represents but ","authors_text":"Lyndon Drake (University of Oxford), Zandi Eberstadt (University of Oxford)","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-05T21:23:15Z","title":"Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04510","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":"sha256:600299baca78636010ee8f1fa1ed3a0f1fc0ae036d70e1e413d593b66857bc36","target":"record","created_at":"2026-07-07T02:19:22Z","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":"b76d62a2fd142e1cdd0289e87ed857046b98a844458e9d0a68e1403f75317ebb","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-05T21:23:15Z","title_canon_sha256":"c7939a15d9e2be0bdcf75ba3ff7a09e1e84b74416cd20b47d0b2c184f6ac9688"},"schema_version":"1.0","source":{"id":"2607.04510","kind":"arxiv","version":1}},"canonical_sha256":"7e14b4bf291ad03bb459fdf224c09799b96d30d9680260b8d193dd3bb0bcba5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e14b4bf291ad03bb459fdf224c09799b96d30d9680260b8d193dd3bb0bcba5f","first_computed_at":"2026-07-07T02:19:22.612092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:22.612092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"14rJRGLtXEE/89GgZ3zVECL/gf9A51bqEi3FoDa7r3x+d/7frfh7smlyQBSGTde48WkqePRatoEN+09LDgebCA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:22.612764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:600299baca78636010ee8f1fa1ed3a0f1fc0ae036d70e1e413d593b66857bc36","sha256:597d88e75f745d8c69f18e0bbcff4b860a6eded0d91f2f7568ad3f5af8842874"],"state_sha256":"1ae66ae1724ab7062b8b8392828c78b83c39b2897bc35efd4d64e36b1187fc23"}