{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VVBG2CSPJQNYRMLX7VTQAUXQE6","short_pith_number":"pith:VVBG2CSP","schema_version":"1.0","canonical_sha256":"ad426d0a4f4c1b88b177fd670052f027b207f10daa7bbd115af816b10619c878","source":{"kind":"arxiv","id":"2603.25620","version":4},"attestation_state":"computed","paper":{"title":"PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Persona agents exhibit more contradictions than humans when tested with chained multi-turn questions.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaeeun Shim, Edward Choi, Hwajung Hong, Junhee Lee, Junseong Choi, Minseo Kim, Sujeong Im","submitted_at":"2026-03-26T16:34:34Z","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"},"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":"2603.25620","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T16:34:34Z","cross_cats_sorted":[],"title_canon_sha256":"a4188de57f9e5565a75cf4eab6c1064f1079e232f8c51c82fa8cbdd6e3fae103","abstract_canon_sha256":"8e3575341e6d0506e6ea3b8df1a8eae5910ccd6014d316ee488c376e332346fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:11.891922Z","signature_b64":"W2sRRLbAauyGHs3GtSo9reOfLcyOxNH64nmKWYltrij7VeFQRlW/And7p1YryMOJKD+YloZAifk7cSpQLYPADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad426d0a4f4c1b88b177fd670052f027b207f10daa7bbd115af816b10619c878","last_reissued_at":"2026-05-20T01:05:11.891120Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:11.891120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Persona agents exhibit more contradictions than humans when tested with chained multi-turn questions.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaeeun Shim, Edward Choi, Hwajung Hong, Junhee Lee, Junseong Choi, Minseo Kim, Sujeong Im","submitted_at":"2026-03-26T16:34:34Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Persona agents exhibit more contradictions than humans when tested with chained multi-turn questions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f904b2317e128226d1f87b3df88c5c19ac1ec1461ce8c33c40666f9240d91702"},"source":{"id":"2603.25620","kind":"arxiv","version":4},"verdict":{"id":"ef3b4730-8d71-46b0-96bb-638144b3260d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:26:26.350873Z","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.","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","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.","pith_extraction_headline":"Persona agents exhibit more contradictions than humans when tested with chained multi-turn questions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.25620/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":"2603.25620","created_at":"2026-05-20T01:05:11.891214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.25620v4","created_at":"2026-05-20T01:05:11.891214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25620","created_at":"2026-05-20T01:05:11.891214+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVBG2CSPJQNY","created_at":"2026-05-20T01:05:11.891214+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVBG2CSPJQNYRMLX","created_at":"2026-05-20T01:05:11.891214+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVBG2CSP","created_at":"2026-05-20T01:05:11.891214+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/VVBG2CSPJQNYRMLX7VTQAUXQE6","json":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6.json","graph_json":"https://pith.science/api/pith-number/VVBG2CSPJQNYRMLX7VTQAUXQE6/graph.json","events_json":"https://pith.science/api/pith-number/VVBG2CSPJQNYRMLX7VTQAUXQE6/events.json","paper":"https://pith.science/paper/VVBG2CSP"},"agent_actions":{"view_html":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6","download_json":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6.json","view_paper":"https://pith.science/paper/VVBG2CSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.25620&json=true","fetch_graph":"https://pith.science/api/pith-number/VVBG2CSPJQNYRMLX7VTQAUXQE6/graph.json","fetch_events":"https://pith.science/api/pith-number/VVBG2CSPJQNYRMLX7VTQAUXQE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6/action/storage_attestation","attest_author":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6/action/author_attestation","sign_citation":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6/action/citation_signature","submit_replication":"https://pith.science/pith/VVBG2CSPJQNYRMLX7VTQAUXQE6/action/replication_record"}},"created_at":"2026-05-20T01:05:11.891214+00:00","updated_at":"2026-05-20T01:05:11.891214+00:00"}