{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VVBG2CSPJQNYRMLX7VTQAUXQE6","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":"8e3575341e6d0506e6ea3b8df1a8eae5910ccd6014d316ee488c376e332346fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T16:34:34Z","title_canon_sha256":"a4188de57f9e5565a75cf4eab6c1064f1079e232f8c51c82fa8cbdd6e3fae103"},"schema_version":"1.0","source":{"id":"2603.25620","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.25620","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2603.25620v4","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25620","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"VVBG2CSPJQNY","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"VVBG2CSPJQNYRMLX","created_at":"2026-05-20T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"VVBG2CSP","created_at":"2026-05-20T01:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:e9b7ab87f5a24dbaaa082c76cc74d3d9dc27d35371aaecb3772712d92dff0fca","target":"graph","created_at":"2026-05-20T01:05:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"even systems previously reported as highly consistent fail to meet the human baseline across all three dimensions, revealing contradictions and evasive responses under chained questioning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the specific multi-turn interrogation protocol fairly measures consistency without LLM-specific biases such as prompt sensitivity or tendencies to evade that differ from human response patterns."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PICon demonstrates that even highly regarded LLM persona agents exhibit more contradictions and evasive responses than real humans across internal, external, and retest consistency dimensions under chained interrogation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Persona agents exhibit more contradictions than humans when tested with chained multi-turn questions."}],"snapshot_sha256":"f904b2317e128226d1f87b3df88c5c19ac1ec1461ce8c33c40666f9240d91702"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.25620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM)-based persona agents are rapidly being adopted as scalable proxies for human participants across diverse domains. Yet there is no systematic method for verifying whether a persona agent's responses remain free of contradictions and factual inaccuracies throughout an interaction. A principle from interrogation methodology offers a lens: no matter how elaborate a fabricated identity, systematic interrogation will expose its contradictions. We apply this principle to propose PICon, an evaluation framework that probes persona agents through logically chained multi-turn q","authors_text":"Chaeeun Shim, Edward Choi, Hwajung Hong, Junhee Lee, Junseong Choi, Minseo Kim, Sujeong Im","cross_cats":[],"headline":"Persona agents exhibit more contradictions than humans when tested with chained multi-turn questions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T16:34:34Z","title":"PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25620","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T00:26:26.350873Z","id":"ef3b4730-8d71-46b0-96bb-638144b3260d","model_set":{"reader":"grok-4.3"},"one_line_summary":"PICon demonstrates that even highly regarded LLM persona agents exhibit more contradictions and evasive responses than real humans across internal, external, and retest consistency dimensions under chained interrogation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Persona agents exhibit more contradictions than humans when tested with chained multi-turn questions.","strongest_claim":"even systems previously reported as highly consistent fail to meet the human baseline across all three dimensions, revealing contradictions and evasive responses under chained questioning.","weakest_assumption":"That the specific multi-turn interrogation protocol fairly measures consistency without LLM-specific biases such as prompt sensitivity or tendencies to evade that differ from human response patterns."}},"verdict_id":"ef3b4730-8d71-46b0-96bb-638144b3260d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1879559e9ba2aad80a90937aadc810b7600a153fd5100a07e26698a8ae95e38a","target":"record","created_at":"2026-05-20T01:05:11Z","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":"8e3575341e6d0506e6ea3b8df1a8eae5910ccd6014d316ee488c376e332346fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T16:34:34Z","title_canon_sha256":"a4188de57f9e5565a75cf4eab6c1064f1079e232f8c51c82fa8cbdd6e3fae103"},"schema_version":"1.0","source":{"id":"2603.25620","kind":"arxiv","version":4}},"canonical_sha256":"ad426d0a4f4c1b88b177fd670052f027b207f10daa7bbd115af816b10619c878","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad426d0a4f4c1b88b177fd670052f027b207f10daa7bbd115af816b10619c878","first_computed_at":"2026-05-20T01:05:11.891120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:11.891120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W2sRRLbAauyGHs3GtSo9reOfLcyOxNH64nmKWYltrij7VeFQRlW/And7p1YryMOJKD+YloZAifk7cSpQLYPADQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:11.891922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.25620","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1879559e9ba2aad80a90937aadc810b7600a153fd5100a07e26698a8ae95e38a","sha256:e9b7ab87f5a24dbaaa082c76cc74d3d9dc27d35371aaecb3772712d92dff0fca"],"state_sha256":"ed0c28514d564b4716ba39b0eaa6f6744b8ba001c8a1874683e42c00f46bfd33"}