{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7FNIQNELJW2QEFLE3AHNDONKBG","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":"00ad2851a0e1a580d4659ebf2fe45ba15b4060ee274c8048ad9c06e3f9cad948","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T04:51:55Z","title_canon_sha256":"aa0051dbe191a5862e5089ef95e9880b4930694eead61469cbcc057bec724e10"},"schema_version":"1.0","source":{"id":"2605.27958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27958","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27958v1","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27958","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"7FNIQNELJW2Q","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"7FNIQNELJW2QEFLE","created_at":"2026-05-28T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"7FNIQNEL","created_at":"2026-05-28T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:d0f798b2863c7a3bfa3ec1cffc47ca288e3ce5b5a879335a21ea4e67cecb17c8","target":"graph","created_at":"2026-05-28T01:04:54Z","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/2605.27958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks while collapsing under distributional shift. This paper systematically pressure-tests probe-based metrics across the Gemma 3 model family (1B-27B parameters), diagnosing why they fail rather than merely documenting that they fail. We test four hypotheses about deception encoding: (1) single linear direction, (2) multi-dimensional subspace, (3) convex conic hull, (4) entropy proxy. Our design includes cross-domain transfer matrices, multi-dimensi","authors_text":"Sachin Kumar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T04:51:55Z","title":"Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27958","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":"sha256:72bc68c4f355ee28aae77afb3a8ac4e5ce348288a19728ed4c97ee0c86b606fa","target":"record","created_at":"2026-05-28T01:04:54Z","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":"00ad2851a0e1a580d4659ebf2fe45ba15b4060ee274c8048ad9c06e3f9cad948","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T04:51:55Z","title_canon_sha256":"aa0051dbe191a5862e5089ef95e9880b4930694eead61469cbcc057bec724e10"},"schema_version":"1.0","source":{"id":"2605.27958","kind":"arxiv","version":1}},"canonical_sha256":"f95a88348b4db5021564d80ed1b9aa09a3fdbcda6e91c7a86e1882848d19ffe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f95a88348b4db5021564d80ed1b9aa09a3fdbcda6e91c7a86e1882848d19ffe7","first_computed_at":"2026-05-28T01:04:54.160289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:54.160289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dqQfuv/eKqtrBpzNxQKPtIwJoWwBS0C5KroCvpCygNcPl9LqxDj7letbGTR2W9+GGc0/w/Cr+yH9vp3YNrtfBQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:54.160710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72bc68c4f355ee28aae77afb3a8ac4e5ce348288a19728ed4c97ee0c86b606fa","sha256:d0f798b2863c7a3bfa3ec1cffc47ca288e3ce5b5a879335a21ea4e67cecb17c8"],"state_sha256":"2ca54324d1b97eb68a15d58dd7b8d19e2c8d47ebf65d8f6997a85b6b7c042d34"}