{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SPCOZ5WANYK6L6LD5XPD3NC3XG","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":"382026ece93bd183bf85be064a11154cf55778cf8013876033d4a15024c0064a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:34:25Z","title_canon_sha256":"a7410862830f1c8bad046732868f004710db2d7090d25e4b0796f1051bbf4653"},"schema_version":"1.0","source":{"id":"2506.11613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11613","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11613v1","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11613","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_12","alias_value":"SPCOZ5WANYK6","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_16","alias_value":"SPCOZ5WANYK6L6LD","created_at":"2026-07-05T11:21:07Z"},{"alias_kind":"pith_short_8","alias_value":"SPCOZ5WA","created_at":"2026-07-05T11:21:07Z"}],"graph_snapshots":[{"event_id":"sha256:9f702b26ce11313deaf4109004cd0afed92b2967dfd116fa535b631c2c41c472","target":"graph","created_at":"2026-07-05T11:21:07Z","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/2506.11613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected, demonstrating critical gaps in our understanding of model alignment. In this work, we both advance understanding and provide tools for future research. Using new narrowly misaligned datasets, we create a set of improved model organisms that achieve 99% coherence (vs. 67% prior), work with smaller 0.5B parameter models (vs. 32B), and that induce misalignment usin","authors_text":"Anna Soligo, Edward Turner, Mia Taylor, Neel Nanda, Senthooran Rajamanoharan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:34:25Z","title":"Model Organisms for Emergent Misalignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11613","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:e05f60748b8a581c60dea8e696fcf074d7e5127366c8e2d04be839a30cd27034","target":"record","created_at":"2026-07-05T11:21:07Z","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":"382026ece93bd183bf85be064a11154cf55778cf8013876033d4a15024c0064a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T09:34:25Z","title_canon_sha256":"a7410862830f1c8bad046732868f004710db2d7090d25e4b0796f1051bbf4653"},"schema_version":"1.0","source":{"id":"2506.11613","kind":"arxiv","version":1}},"canonical_sha256":"93c4ecf6c06e15e5f963edde3db45bb9944c355a655e523076edcf9196ebf274","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93c4ecf6c06e15e5f963edde3db45bb9944c355a655e523076edcf9196ebf274","first_computed_at":"2026-07-05T11:21:07.667709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:07.667709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5VRfuaCE9QyCfD82dS4qu+c60NU+obiFvbJeMG4zGs2For4Uod06waOwdVc86lVMkh1W4f0vXsRTY8vgrySTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:07.668166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e05f60748b8a581c60dea8e696fcf074d7e5127366c8e2d04be839a30cd27034","sha256:9f702b26ce11313deaf4109004cd0afed92b2967dfd116fa535b631c2c41c472"],"state_sha256":"aa85c3c0c9013e84682892d74d33edeced0d21e377db1e6afca130cc78504a73"}