{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CC7UDNTT2PGJUSG4T4EQ4WQ33F","short_pith_number":"pith:CC7UDNTT","schema_version":"1.0","canonical_sha256":"10bf41b673d3cc9a48dc9f090e5a1bd971aa4cbb80b7e6c908f9642542dff766","source":{"kind":"arxiv","id":"2606.17229","version":1},"attestation_state":"computed","paper":{"title":"Rift: A Conflict Signature for Deception in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Petr Nyoma","submitted_at":"2026-06-15T19:22:02Z","abstract_excerpt":"A model that lies while knowing the truth is the central case ELK cannot handle with behavioral evaluation alone. We ask whether such deception leaves an internal signature distinguishing it from honest error. Our key move is a control for wrongness: we contrast a sleeper agent (knows the truth, lies on trigger) against a naive liar (fine-tuned to emit the same wrong answers with no honest training). Both produce identical wrong outputs; any difference is about knowledge conflict, not incorrectness. We find deceptive forward passes carry a conflict signature - 2.1-2.3x higher residual rank tha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.17229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T19:22:02Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"382a48e744f9cbab674a64da319dda84ec3596d88ed45f5b59ea348b029611f5","abstract_canon_sha256":"6d3d96cc4cb769b5c9a25c2c7d786dffb6603213f73708deb1d144d8011c67ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:06.447087Z","signature_b64":"mq7zbWb+r8SmDVGNAety4vdwhTsc+cV5BDedC4QOIyTMJxvjsNowvkQsFzo8aXA0nCk/S8X9x9F9WwZwepS1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10bf41b673d3cc9a48dc9f090e5a1bd971aa4cbb80b7e6c908f9642542dff766","last_reissued_at":"2026-06-19T16:10:06.446692Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:06.446692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rift: A Conflict Signature for Deception in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Petr Nyoma","submitted_at":"2026-06-15T19:22:02Z","abstract_excerpt":"A model that lies while knowing the truth is the central case ELK cannot handle with behavioral evaluation alone. We ask whether such deception leaves an internal signature distinguishing it from honest error. Our key move is a control for wrongness: we contrast a sleeper agent (knows the truth, lies on trigger) against a naive liar (fine-tuned to emit the same wrong answers with no honest training). Both produce identical wrong outputs; any difference is about knowledge conflict, not incorrectness. We find deceptive forward passes carry a conflict signature - 2.1-2.3x higher residual rank tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17229","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.17229/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.17229","created_at":"2026-06-19T16:10:06.446755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17229v1","created_at":"2026-06-19T16:10:06.446755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17229","created_at":"2026-06-19T16:10:06.446755+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC7UDNTT2PGJ","created_at":"2026-06-19T16:10:06.446755+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC7UDNTT2PGJUSG4","created_at":"2026-06-19T16:10:06.446755+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC7UDNTT","created_at":"2026-06-19T16:10:06.446755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F","json":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F.json","graph_json":"https://pith.science/api/pith-number/CC7UDNTT2PGJUSG4T4EQ4WQ33F/graph.json","events_json":"https://pith.science/api/pith-number/CC7UDNTT2PGJUSG4T4EQ4WQ33F/events.json","paper":"https://pith.science/paper/CC7UDNTT"},"agent_actions":{"view_html":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F","download_json":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F.json","view_paper":"https://pith.science/paper/CC7UDNTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17229&json=true","fetch_graph":"https://pith.science/api/pith-number/CC7UDNTT2PGJUSG4T4EQ4WQ33F/graph.json","fetch_events":"https://pith.science/api/pith-number/CC7UDNTT2PGJUSG4T4EQ4WQ33F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F/action/storage_attestation","attest_author":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F/action/author_attestation","sign_citation":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F/action/citation_signature","submit_replication":"https://pith.science/pith/CC7UDNTT2PGJUSG4T4EQ4WQ33F/action/replication_record"}},"created_at":"2026-06-19T16:10:06.446755+00:00","updated_at":"2026-06-19T16:10:06.446755+00:00"}