{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PP5HLIYRUGOGF52ROEGBFF6T3U","short_pith_number":"pith:PP5HLIYR","schema_version":"1.0","canonical_sha256":"7bfa75a311a19c62f751710c1297d3dd16045aea3401fed4b99ad051702e5d6f","source":{"kind":"arxiv","id":"2309.08631","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models Can Infer Psychological Dispositions of Social Media Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Heinrich Peters, Sandra Matz","submitted_at":"2023-09-13T01:27:48Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate increasingly human-like abilities across a wide variety of tasks. In this paper, we investigate whether LLMs like ChatGPT can accurately infer the psychological dispositions of social media users and whether their ability to do so varies across socio-demographic groups. Specifically, we test whether GPT-3.5 and GPT-4 can derive the Big Five personality traits from users' Facebook status updates in a zero-shot learning scenario. Our results show an average correlation of r = .29 (range = [.22, .33]) between LLM-inferred and self-reported trait scores - a"},"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":"2309.08631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-13T01:27:48Z","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG","cs.SI"],"title_canon_sha256":"ba0691d30c49574fa86e9cc2d41b818293c59ece2e51a13c74605452ef4ca8c3","abstract_canon_sha256":"116825e403c8de82d4ba70679c6486835934c2cbecd817d437a6ca59b90550df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:42.355195Z","signature_b64":"Uwh6XuPuGLzQ8q4qQwYWfemVnDY3Lq/kk7c3OpBvfY0CqSR2bfTw1fz5uElUQifi3+Zm4qKWxURTwrzSnVoHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bfa75a311a19c62f751710c1297d3dd16045aea3401fed4b99ad051702e5d6f","last_reissued_at":"2026-07-05T08:27:42.354665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:42.354665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Can Infer Psychological Dispositions of Social Media Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Heinrich Peters, Sandra Matz","submitted_at":"2023-09-13T01:27:48Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate increasingly human-like abilities across a wide variety of tasks. In this paper, we investigate whether LLMs like ChatGPT can accurately infer the psychological dispositions of social media users and whether their ability to do so varies across socio-demographic groups. Specifically, we test whether GPT-3.5 and GPT-4 can derive the Big Five personality traits from users' Facebook status updates in a zero-shot learning scenario. Our results show an average correlation of r = .29 (range = [.22, .33]) between LLM-inferred and self-reported trait scores - a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08631","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/2309.08631/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":"2309.08631","created_at":"2026-07-05T08:27:42.354736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08631v2","created_at":"2026-07-05T08:27:42.354736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08631","created_at":"2026-07-05T08:27:42.354736+00:00"},{"alias_kind":"pith_short_12","alias_value":"PP5HLIYRUGOG","created_at":"2026-07-05T08:27:42.354736+00:00"},{"alias_kind":"pith_short_16","alias_value":"PP5HLIYRUGOGF52R","created_at":"2026-07-05T08:27:42.354736+00:00"},{"alias_kind":"pith_short_8","alias_value":"PP5HLIYR","created_at":"2026-07-05T08:27:42.354736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22467","citing_title":"Towards Simulating Social Influence Dynamics with LLM-based Multi-agents","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U","json":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U.json","graph_json":"https://pith.science/api/pith-number/PP5HLIYRUGOGF52ROEGBFF6T3U/graph.json","events_json":"https://pith.science/api/pith-number/PP5HLIYRUGOGF52ROEGBFF6T3U/events.json","paper":"https://pith.science/paper/PP5HLIYR"},"agent_actions":{"view_html":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U","download_json":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U.json","view_paper":"https://pith.science/paper/PP5HLIYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08631&json=true","fetch_graph":"https://pith.science/api/pith-number/PP5HLIYRUGOGF52ROEGBFF6T3U/graph.json","fetch_events":"https://pith.science/api/pith-number/PP5HLIYRUGOGF52ROEGBFF6T3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U/action/storage_attestation","attest_author":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U/action/author_attestation","sign_citation":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U/action/citation_signature","submit_replication":"https://pith.science/pith/PP5HLIYRUGOGF52ROEGBFF6T3U/action/replication_record"}},"created_at":"2026-07-05T08:27:42.354736+00:00","updated_at":"2026-07-05T08:27:42.354736+00:00"}