{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PEUYWCASHQ4TK7PKUP2B7NB2QN","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":"3a3b124c72524adf91a87d8fedc75054564b7cdc96af5e0f4225ab904c637f8f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-15T00:11:42Z","title_canon_sha256":"bbfd2ab6969e5bdea3d3e5f3796da0318341ad0b86f76095088c109c927ab73a"},"schema_version":"1.0","source":{"id":"2607.13346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13346","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13346v1","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13346","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"PEUYWCASHQ4T","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"PEUYWCASHQ4TK7PK","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"PEUYWCAS","created_at":"2026-07-16T00:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:35229815a2ed29002822bc61b77d490a25b86ee0a055c732f508b7908da9db85","target":"graph","created_at":"2026-07-16T00:22:13Z","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/2607.13346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored. When no scratchpad is visible, behavior alone cannot distinguish strategic from genuine compliance. We ask whether hidden states reveal what outputs hide.\n  We run a 13-model sweep for naturally-emerging faking, then probe and steer hidden states on the two models that fake. Natural faking appears only in Qwen3-32B (+18.2pp) and Llama-3.1-8B (+24.4pp at n=10, p<10^-15), while explicit scratchpad self-reports are rare (a Claude Opus 4 judge flags faking","authors_text":"Aman Mehta","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-15T00:11:42Z","title":"The Refusal Residue: When Probes Catch Alignment Faking and When They Don't"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13346","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":"sha256:4481c6387bfd92e634aa01cf3afd245102267a2e390b397b3dcc32541e8b813b","target":"record","created_at":"2026-07-16T00:22:13Z","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":"3a3b124c72524adf91a87d8fedc75054564b7cdc96af5e0f4225ab904c637f8f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-15T00:11:42Z","title_canon_sha256":"bbfd2ab6969e5bdea3d3e5f3796da0318341ad0b86f76095088c109c927ab73a"},"schema_version":"1.0","source":{"id":"2607.13346","kind":"arxiv","version":1}},"canonical_sha256":"79298b08123c39357deaa3f41fb43a8370953ec4ff8628951b81e77e6f7cfcac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79298b08123c39357deaa3f41fb43a8370953ec4ff8628951b81e77e6f7cfcac","first_computed_at":"2026-07-16T00:22:13.463973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:22:13.463973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d085Zro10Dm/yFh59Qev+rhIVjwFBZuWkfVPp+0q/RrtNIj5IHiZ7i0Pxk8C9MffEnqIvmUNEFIqSrNSW7avDg==","signature_status":"signed_v1","signed_at":"2026-07-16T00:22:13.464763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4481c6387bfd92e634aa01cf3afd245102267a2e390b397b3dcc32541e8b813b","sha256:35229815a2ed29002822bc61b77d490a25b86ee0a055c732f508b7908da9db85"],"state_sha256":"cd8906164ac8dff7578fec9319d21c3c5d261785c1698c5b7eaeb84b6472b0da"}