{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:27AI2Z5CKTZY5BQPGGRRMPGRT2","short_pith_number":"pith:27AI2Z5C","schema_version":"1.0","canonical_sha256":"d7c08d67a254f38e860f31a3163cd19e9ecfd8dfde82f26ecc2fad975a48721c","source":{"kind":"arxiv","id":"2406.12548","version":3},"attestation_state":"computed","paper":{"title":"P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Zhou, Junfeng Tian, Liang He, Qin Chen, Yuhao Dan","submitted_at":"2024-06-18T12:25:13Z","abstract_excerpt":"Personalized large language models (LLMs) have attracted great attention in many applications, such as emotional support and role-playing. However, existing works primarily focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making, hampering the development of more anthropomorphic and psychologically-grounded AI systems. In this paper, we explore the modeling of Big Five personality traits, which is the most widely used trait theory in psychology, and propose P-React, a mixture of experts (MoE)-based personali"},"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":"2406.12548","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T12:25:13Z","cross_cats_sorted":[],"title_canon_sha256":"27cb09c3af2b44c9a1980f2f54cb8bf40b3ee2eb73b6c6ae0613bac38ab599bc","abstract_canon_sha256":"0e32c0e0603ffc1114a1a2666f62b9bf4299a0e055d001fc51d9d65cf900f7aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:21.001204Z","signature_b64":"gKRCA7qC1txFQ1YeDW185jJVrxdQri10zMt7WY+8kWAErHmO8iDyRd3DIc0QJXn6OedZAtyM62pP5MR/PolsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7c08d67a254f38e860f31a3163cd19e9ecfd8dfde82f26ecc2fad975a48721c","last_reissued_at":"2026-07-05T11:42:21.000768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:21.000768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Zhou, Junfeng Tian, Liang He, Qin Chen, Yuhao Dan","submitted_at":"2024-06-18T12:25:13Z","abstract_excerpt":"Personalized large language models (LLMs) have attracted great attention in many applications, such as emotional support and role-playing. However, existing works primarily focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making, hampering the development of more anthropomorphic and psychologically-grounded AI systems. In this paper, we explore the modeling of Big Five personality traits, which is the most widely used trait theory in psychology, and propose P-React, a mixture of experts (MoE)-based personali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12548","kind":"arxiv","version":3},"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/2406.12548/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":"2406.12548","created_at":"2026-07-05T11:42:21.000821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12548v3","created_at":"2026-07-05T11:42:21.000821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12548","created_at":"2026-07-05T11:42:21.000821+00:00"},{"alias_kind":"pith_short_12","alias_value":"27AI2Z5CKTZY","created_at":"2026-07-05T11:42:21.000821+00:00"},{"alias_kind":"pith_short_16","alias_value":"27AI2Z5CKTZY5BQP","created_at":"2026-07-05T11:42:21.000821+00:00"},{"alias_kind":"pith_short_8","alias_value":"27AI2Z5C","created_at":"2026-07-05T11:42:21.000821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04794","citing_title":"Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2","json":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2.json","graph_json":"https://pith.science/api/pith-number/27AI2Z5CKTZY5BQPGGRRMPGRT2/graph.json","events_json":"https://pith.science/api/pith-number/27AI2Z5CKTZY5BQPGGRRMPGRT2/events.json","paper":"https://pith.science/paper/27AI2Z5C"},"agent_actions":{"view_html":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2","download_json":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2.json","view_paper":"https://pith.science/paper/27AI2Z5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12548&json=true","fetch_graph":"https://pith.science/api/pith-number/27AI2Z5CKTZY5BQPGGRRMPGRT2/graph.json","fetch_events":"https://pith.science/api/pith-number/27AI2Z5CKTZY5BQPGGRRMPGRT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2/action/storage_attestation","attest_author":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2/action/author_attestation","sign_citation":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2/action/citation_signature","submit_replication":"https://pith.science/pith/27AI2Z5CKTZY5BQPGGRRMPGRT2/action/replication_record"}},"created_at":"2026-07-05T11:42:21.000821+00:00","updated_at":"2026-07-05T11:42:21.000821+00:00"}