{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:T7GTML3DG6DY6ZUX5YJ6OK3Q6C","short_pith_number":"pith:T7GTML3D","canonical_record":{"source":{"id":"2504.05019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T12:43:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2303c691ce81374cf76d29cf1ed6207e6fd08ffd351e5f2d7ab825d221d10d67","abstract_canon_sha256":"33ee01ce133a4e0f851a49ec6f5db651cea2906ffb798fe0018e13f6e3a0c0d0"},"schema_version":"1.0"},"canonical_sha256":"9fcd362f6337878f6697ee13e72b70f0943eb7db8f676b472d7c5c9bfdcde82b","source":{"kind":"arxiv","id":"2504.05019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05019","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05019v1","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05019","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"pith_short_12","alias_value":"T7GTML3DG6DY","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"pith_short_16","alias_value":"T7GTML3DG6DY6ZUX","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"pith_short_8","alias_value":"T7GTML3D","created_at":"2026-07-05T10:45:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:T7GTML3DG6DY6ZUX5YJ6OK3Q6C","target":"record","payload":{"canonical_record":{"source":{"id":"2504.05019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T12:43:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2303c691ce81374cf76d29cf1ed6207e6fd08ffd351e5f2d7ab825d221d10d67","abstract_canon_sha256":"33ee01ce133a4e0f851a49ec6f5db651cea2906ffb798fe0018e13f6e3a0c0d0"},"schema_version":"1.0"},"canonical_sha256":"9fcd362f6337878f6697ee13e72b70f0943eb7db8f676b472d7c5c9bfdcde82b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:32.645905Z","signature_b64":"y+JXzb7Ipx0dFtKUp7obL0Lk7aQifg8wglFBl/ek0CT1URJPvHsTpH5cHvMBOOITBH5YNEJ3+ZLK3dA0qpaLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fcd362f6337878f6697ee13e72b70f0943eb7db8f676b472d7c5c9bfdcde82b","last_reissued_at":"2026-07-05T10:45:32.645460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:32.645460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.05019","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:45:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n75fRYFmmeyo56qPYlcs56u5e4gv+vM/olCQMzAa8JemgTWMsrW96fWqRUF7JvojWBscme7NN6kgFhX0dtlEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:55:28.283881Z"},"content_sha256":"7271518c510ed69ceb227bb22c705623599d310e5cc90c6db55b755ef93636d6","schema_version":"1.0","event_id":"sha256:7271518c510ed69ceb227bb22c705623599d310e5cc90c6db55b755ef93636d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:T7GTML3DG6DY6ZUX5YJ6OK3Q6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixture-of-Personas Language Models for Population Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hieu Trung Nguyen, Julian Theodore, Ngoc Bui, Rex Ying, Shantanu Kumar, Viet Anh Nguyen, Weikang Qiu","submitted_at":"2025-04-07T12:43:05Z","abstract_excerpt":"Advances in Large Language Models (LLMs) paved the way for their emerging applications in various domains, such as human behavior simulations, where LLMs could augment human-generated data in social science research and machine learning model training. However, pretrained LLMs often fail to capture the behavioral diversity of target populations due to the inherent variability across individuals and groups. To address this, we propose \\textit{Mixture of Personas} (MoP), a \\textit{probabilistic} prompting method that aligns the LLM responses with the target population. MoP is a contextual mixtur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05019","kind":"arxiv","version":1},"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/2504.05019/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:45:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3yLdWOFFb6zILLt21VeMtmB7IJ7Mn2SqHNnOANAOf0SkTvZed6CHRh770+6yfWRXzL3OsVh6eMEwu0nlnVtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:55:28.284740Z"},"content_sha256":"5ccac645e3334ac8f9d6aaa7bad5107a48a90772eb66170783a03014b19544df","schema_version":"1.0","event_id":"sha256:5ccac645e3334ac8f9d6aaa7bad5107a48a90772eb66170783a03014b19544df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7GTML3DG6DY6ZUX5YJ6OK3Q6C/bundle.json","state_url":"https://pith.science/pith/T7GTML3DG6DY6ZUX5YJ6OK3Q6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7GTML3DG6DY6ZUX5YJ6OK3Q6C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T00:55:28Z","links":{"resolver":"https://pith.science/pith/T7GTML3DG6DY6ZUX5YJ6OK3Q6C","bundle":"https://pith.science/pith/T7GTML3DG6DY6ZUX5YJ6OK3Q6C/bundle.json","state":"https://pith.science/pith/T7GTML3DG6DY6ZUX5YJ6OK3Q6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7GTML3DG6DY6ZUX5YJ6OK3Q6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T7GTML3DG6DY6ZUX5YJ6OK3Q6C","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":"33ee01ce133a4e0f851a49ec6f5db651cea2906ffb798fe0018e13f6e3a0c0d0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T12:43:05Z","title_canon_sha256":"2303c691ce81374cf76d29cf1ed6207e6fd08ffd351e5f2d7ab825d221d10d67"},"schema_version":"1.0","source":{"id":"2504.05019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05019","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05019v1","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05019","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"pith_short_12","alias_value":"T7GTML3DG6DY","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"pith_short_16","alias_value":"T7GTML3DG6DY6ZUX","created_at":"2026-07-05T10:45:32Z"},{"alias_kind":"pith_short_8","alias_value":"T7GTML3D","created_at":"2026-07-05T10:45:32Z"}],"graph_snapshots":[{"event_id":"sha256:5ccac645e3334ac8f9d6aaa7bad5107a48a90772eb66170783a03014b19544df","target":"graph","created_at":"2026-07-05T10:45:32Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.05019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in Large Language Models (LLMs) paved the way for their emerging applications in various domains, such as human behavior simulations, where LLMs could augment human-generated data in social science research and machine learning model training. However, pretrained LLMs often fail to capture the behavioral diversity of target populations due to the inherent variability across individuals and groups. To address this, we propose \\textit{Mixture of Personas} (MoP), a \\textit{probabilistic} prompting method that aligns the LLM responses with the target population. MoP is a contextual mixtur","authors_text":"Hieu Trung Nguyen, Julian Theodore, Ngoc Bui, Rex Ying, Shantanu Kumar, Viet Anh Nguyen, Weikang Qiu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T12:43:05Z","title":"Mixture-of-Personas Language Models for Population Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05019","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7271518c510ed69ceb227bb22c705623599d310e5cc90c6db55b755ef93636d6","target":"record","created_at":"2026-07-05T10:45:32Z","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":"33ee01ce133a4e0f851a49ec6f5db651cea2906ffb798fe0018e13f6e3a0c0d0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T12:43:05Z","title_canon_sha256":"2303c691ce81374cf76d29cf1ed6207e6fd08ffd351e5f2d7ab825d221d10d67"},"schema_version":"1.0","source":{"id":"2504.05019","kind":"arxiv","version":1}},"canonical_sha256":"9fcd362f6337878f6697ee13e72b70f0943eb7db8f676b472d7c5c9bfdcde82b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fcd362f6337878f6697ee13e72b70f0943eb7db8f676b472d7c5c9bfdcde82b","first_computed_at":"2026-07-05T10:45:32.645460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:32.645460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y+JXzb7Ipx0dFtKUp7obL0Lk7aQifg8wglFBl/ek0CT1URJPvHsTpH5cHvMBOOITBH5YNEJ3+ZLK3dA0qpaLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:32.645905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7271518c510ed69ceb227bb22c705623599d310e5cc90c6db55b755ef93636d6","sha256:5ccac645e3334ac8f9d6aaa7bad5107a48a90772eb66170783a03014b19544df"],"state_sha256":"36b292266d6f28729b80457cfa0b17a71b3d953fc868c54af411d7a6b2835b44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zOpWC/myMP3vSwKkl1CRVx3MFs0CINsSuv4VkkY8YQTntTBSXC8s6++OwcmGsMEUAWnGF/a0UrYcIMBVctY1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:55:28.289288Z","bundle_sha256":"051d25669e1185149115556ceb5a3caa208e8f9c368d470b3ea0273bb9fb6598"}}