{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XVC6RJ465SCZNCXO63PALMEQDX","short_pith_number":"pith:XVC6RJ46","schema_version":"1.0","canonical_sha256":"bd45e8a79eec85968aeef6de05b0901de98318cc81ea27f00cd295c880665cf1","source":{"kind":"arxiv","id":"2412.00207","version":2},"attestation_state":"computed","paper":{"title":"Can LLM \"Self-report\"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Huiqi Zou, Pengda Wang, Tianjun Sun, Ziang Xiao, Zihan Yan","submitted_at":"2024-11-29T19:05:05Z","abstract_excerpt":"A chatbot's personality design is key to interaction quality. As chatbots evolved from rule-based systems to those powered by large language models (LLMs), evaluating the effectiveness of their personality design has become increasingly complex, particularly due to the open-ended nature of interactions. A recent and widely adopted method for assessing the personality design of LLM-based chatbots is the use of self-report questionnaires. These questionnaires, often borrowed from established human personality inventories, ask the chatbot to rate itself on various personality traits. Can LLM-base"},"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":"2412.00207","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2024-11-29T19:05:05Z","cross_cats_sorted":[],"title_canon_sha256":"0be241ef806abafa63334f324c14583ac49c1e24c18723df4167fe514f922ccc","abstract_canon_sha256":"30903306907a7182a341196e5ceaa5d06b9e6208244777a50ae57685ed05ad4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:29.232844Z","signature_b64":"4DY/LPyr/g2vB96AFlBNeb0LW5Z+eplJO2S+He+25RaeIpTOJ5tGqaXyRCqOS/JoKCdykwgpk/WqLCzDllaTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd45e8a79eec85968aeef6de05b0901de98318cc81ea27f00cd295c880665cf1","last_reissued_at":"2026-07-05T11:50:29.232417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:29.232417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLM \"Self-report\"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Huiqi Zou, Pengda Wang, Tianjun Sun, Ziang Xiao, Zihan Yan","submitted_at":"2024-11-29T19:05:05Z","abstract_excerpt":"A chatbot's personality design is key to interaction quality. As chatbots evolved from rule-based systems to those powered by large language models (LLMs), evaluating the effectiveness of their personality design has become increasingly complex, particularly due to the open-ended nature of interactions. A recent and widely adopted method for assessing the personality design of LLM-based chatbots is the use of self-report questionnaires. These questionnaires, often borrowed from established human personality inventories, ask the chatbot to rate itself on various personality traits. Can LLM-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00207","kind":"arxiv","version":2},"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/2412.00207/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":"2412.00207","created_at":"2026-07-05T11:50:29.232473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00207v2","created_at":"2026-07-05T11:50:29.232473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00207","created_at":"2026-07-05T11:50:29.232473+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVC6RJ465SCZ","created_at":"2026-07-05T11:50:29.232473+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVC6RJ465SCZNCXO","created_at":"2026-07-05T11:50:29.232473+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVC6RJ46","created_at":"2026-07-05T11:50:29.232473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23339","citing_title":"When Robots Rate Their Own Interactions: Engagement Validity and the Strangeness Failure","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12730","citing_title":"Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03357","citing_title":"The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX","json":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX.json","graph_json":"https://pith.science/api/pith-number/XVC6RJ465SCZNCXO63PALMEQDX/graph.json","events_json":"https://pith.science/api/pith-number/XVC6RJ465SCZNCXO63PALMEQDX/events.json","paper":"https://pith.science/paper/XVC6RJ46"},"agent_actions":{"view_html":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX","download_json":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX.json","view_paper":"https://pith.science/paper/XVC6RJ46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00207&json=true","fetch_graph":"https://pith.science/api/pith-number/XVC6RJ465SCZNCXO63PALMEQDX/graph.json","fetch_events":"https://pith.science/api/pith-number/XVC6RJ465SCZNCXO63PALMEQDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX/action/storage_attestation","attest_author":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX/action/author_attestation","sign_citation":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX/action/citation_signature","submit_replication":"https://pith.science/pith/XVC6RJ465SCZNCXO63PALMEQDX/action/replication_record"}},"created_at":"2026-07-05T11:50:29.232473+00:00","updated_at":"2026-07-05T11:50:29.232473+00:00"}