{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GDD6QSU3F6MNBHEJQSEUYAOSMF","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":"d4ea9febb9c2c0c59a909e8d4ef2cc5b1ce67b0da2f73d4ff1c738888774c920","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-03T23:41:25Z","title_canon_sha256":"b4a699e3fd96f04ba01ccd5e1bda715210cd153862e5f793326358c04266dec1"},"schema_version":"1.0","source":{"id":"2607.03640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03640","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03640v1","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03640","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"GDD6QSU3F6MN","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"GDD6QSU3F6MNBHEJ","created_at":"2026-07-07T02:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"GDD6QSU3","created_at":"2026-07-07T02:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:b7a6d793f8655b3d7e91805d4ee73bb461194d43769b14679de67abb7d38c35e","target":"graph","created_at":"2026-07-07T02:17:58Z","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/2607.03640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt touches a particular topic. We introduce the Stabilized Adapter for self-Report (SAR), a lightweight LoRA adapter that makes a fine-tuned model describe its own hidden behavior in plain language, using only the model and the dataset it was trained on. Across seven implanted behaviors (plus a no-behavior control), SAR detects the hidden behavior in every one--even when the model has generalized into broad misalignment that the training data alone","authors_text":"Bartosz Zieli\\'nski, Taras Kutsyk","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-03T23:41:25Z","title":"Revealing Hidden Model Behaviors with Task-Specific Self-Reports"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03640","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":"sha256:8add1da669275d6ee59048c672dcc2a6fc107010d96ce72e1b3707352bb48a8d","target":"record","created_at":"2026-07-07T02:17:58Z","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":"d4ea9febb9c2c0c59a909e8d4ef2cc5b1ce67b0da2f73d4ff1c738888774c920","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-03T23:41:25Z","title_canon_sha256":"b4a699e3fd96f04ba01ccd5e1bda715210cd153862e5f793326358c04266dec1"},"schema_version":"1.0","source":{"id":"2607.03640","kind":"arxiv","version":1}},"canonical_sha256":"30c7e84a9b2f98d09c8984894c01d2617fafac38a43f02816ce452adcd3c1865","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30c7e84a9b2f98d09c8984894c01d2617fafac38a43f02816ce452adcd3c1865","first_computed_at":"2026-07-07T02:17:58.953660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:58.953660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"72jJqELK5hMaDsjSJ6p5HmIbCsM708Il3RePvLxWpEzTmePvwGvnR1dzXv/ufcWrmjj843Eyq6w4CYmRYLoWBA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:58.954383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8add1da669275d6ee59048c672dcc2a6fc107010d96ce72e1b3707352bb48a8d","sha256:b7a6d793f8655b3d7e91805d4ee73bb461194d43769b14679de67abb7d38c35e"],"state_sha256":"c76574d8c0d4a1bd3dba0b2683b93b88a5fbc953e3ccd9b2a26a86cb3b65e470"}