{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AYCRFTETD36FE5F3X2SISUHKFG","short_pith_number":"pith:AYCRFTET","canonical_record":{"source":{"id":"2502.07068","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"0956f775d4c17878b0b97656c0f249ba94151b60821db6508b8722721d8f62a8","abstract_canon_sha256":"0163c53f73928c1f8465e726430dcf92f4598ed158793f7f1ed66f2580e4bfbd"},"schema_version":"1.0"},"canonical_sha256":"060512cc931efc5274bbbea48950ea29a3b03b7704b59796646c33f0883d27a4","source":{"kind":"arxiv","id":"2502.07068","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07068","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07068v2","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07068","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"AYCRFTETD36F","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"AYCRFTETD36FE5F3","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"AYCRFTET","created_at":"2026-07-05T10:17:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AYCRFTETD36FE5F3X2SISUHKFG","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07068","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"0956f775d4c17878b0b97656c0f249ba94151b60821db6508b8722721d8f62a8","abstract_canon_sha256":"0163c53f73928c1f8465e726430dcf92f4598ed158793f7f1ed66f2580e4bfbd"},"schema_version":"1.0"},"canonical_sha256":"060512cc931efc5274bbbea48950ea29a3b03b7704b59796646c33f0883d27a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:00.017272Z","signature_b64":"sqV5hJlw5O+Txiia/f8OYUxkjzDCqFfjdIwCxOfFoWk54mGCViKe/la6XHJSLVzJtrvAGq2/41Ybx7UjxaG4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"060512cc931efc5274bbbea48950ea29a3b03b7704b59796646c33f0883d27a4","last_reissued_at":"2026-07-05T10:17:00.016792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:00.016792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07068","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8Cgp+0MmvlFtedSX3g67udZGqPVTIMpog7TUuTcOo51nauTH/fIPOvx/ydRAZqjg6LFi0deTKzLqbg9uHZWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:53:55.762242Z"},"content_sha256":"bf1cfda6962c082304765180ce8e7ac6c147f3336b4380c8d625f951f5a62c61","schema_version":"1.0","event_id":"sha256:bf1cfda6962c082304765180ce8e7ac6c147f3336b4380c8d625f951f5a62c61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AYCRFTETD36FE5F3X2SISUHKFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arnav Arora, Daniel Hershcovich, Haijiang Liu, Isabelle Augenstein, Paul R\\\"ottger, Yong Cao","submitted_at":"2025-02-10T21:59:27Z","abstract_excerpt":"Large-scale surveys are essential tools for informing social science research and policy, but running surveys is costly and time-intensive. If we could accurately simulate group-level survey results, this would therefore be very valuable to social science research. Prior work has explored the use of large language models (LLMs) for simulating human behaviors, mostly through prompting. In this paper, we are the first to specialize LLMs for the task of simulating survey response distributions. As a testbed, we use country-level results from two global cultural surveys. We devise a fine-tuning me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07068","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/2502.07068/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":"2026-07-05T10:17:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STcX+3T5xtedobJfvjqZxbmZep27SpChqCERc3aq/5QWwPymyjCbLc9FWBo/dBDqpUpbgRYFTc4jDy2Bti6oDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:53:55.763201Z"},"content_sha256":"6fac9ab0f202e33c1349e8674965eec4fb06c6428e54e5f92864f196f6722f9f","schema_version":"1.0","event_id":"sha256:6fac9ab0f202e33c1349e8674965eec4fb06c6428e54e5f92864f196f6722f9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AYCRFTETD36FE5F3X2SISUHKFG/bundle.json","state_url":"https://pith.science/pith/AYCRFTETD36FE5F3X2SISUHKFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AYCRFTETD36FE5F3X2SISUHKFG/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":"2026-08-08T22:53:55Z","links":{"resolver":"https://pith.science/pith/AYCRFTETD36FE5F3X2SISUHKFG","bundle":"https://pith.science/pith/AYCRFTETD36FE5F3X2SISUHKFG/bundle.json","state":"https://pith.science/pith/AYCRFTETD36FE5F3X2SISUHKFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AYCRFTETD36FE5F3X2SISUHKFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AYCRFTETD36FE5F3X2SISUHKFG","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":"0163c53f73928c1f8465e726430dcf92f4598ed158793f7f1ed66f2580e4bfbd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:59:27Z","title_canon_sha256":"0956f775d4c17878b0b97656c0f249ba94151b60821db6508b8722721d8f62a8"},"schema_version":"1.0","source":{"id":"2502.07068","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07068","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07068v2","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07068","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"AYCRFTETD36F","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"AYCRFTETD36FE5F3","created_at":"2026-07-05T10:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"AYCRFTET","created_at":"2026-07-05T10:17:00Z"}],"graph_snapshots":[{"event_id":"sha256:6fac9ab0f202e33c1349e8674965eec4fb06c6428e54e5f92864f196f6722f9f","target":"graph","created_at":"2026-07-05T10:17:00Z","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/2502.07068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale surveys are essential tools for informing social science research and policy, but running surveys is costly and time-intensive. If we could accurately simulate group-level survey results, this would therefore be very valuable to social science research. Prior work has explored the use of large language models (LLMs) for simulating human behaviors, mostly through prompting. In this paper, we are the first to specialize LLMs for the task of simulating survey response distributions. As a testbed, we use country-level results from two global cultural surveys. We devise a fine-tuning me","authors_text":"Arnav Arora, Daniel Hershcovich, Haijiang Liu, Isabelle Augenstein, Paul R\\\"ottger, Yong Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:59:27Z","title":"Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07068","kind":"arxiv","version":2},"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:bf1cfda6962c082304765180ce8e7ac6c147f3336b4380c8d625f951f5a62c61","target":"record","created_at":"2026-07-05T10:17:00Z","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":"0163c53f73928c1f8465e726430dcf92f4598ed158793f7f1ed66f2580e4bfbd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T21:59:27Z","title_canon_sha256":"0956f775d4c17878b0b97656c0f249ba94151b60821db6508b8722721d8f62a8"},"schema_version":"1.0","source":{"id":"2502.07068","kind":"arxiv","version":2}},"canonical_sha256":"060512cc931efc5274bbbea48950ea29a3b03b7704b59796646c33f0883d27a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"060512cc931efc5274bbbea48950ea29a3b03b7704b59796646c33f0883d27a4","first_computed_at":"2026-07-05T10:17:00.016792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:00.016792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sqV5hJlw5O+Txiia/f8OYUxkjzDCqFfjdIwCxOfFoWk54mGCViKe/la6XHJSLVzJtrvAGq2/41Ybx7UjxaG4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:00.017272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07068","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf1cfda6962c082304765180ce8e7ac6c147f3336b4380c8d625f951f5a62c61","sha256:6fac9ab0f202e33c1349e8674965eec4fb06c6428e54e5f92864f196f6722f9f"],"state_sha256":"56b615959cd014ebf7cb1ae7803ae7c0438b4ae858103c5ee9e4b2d41309ea14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIBbnAl2tXsxId3OxxOidtzp6PeErKuwlB9l4yg2Gsj25rZwcAj0WvJMqQKA3VTBjIYCeQPLWH2+Jy+xZqxVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:53:55.768675Z","bundle_sha256":"510c36709f7a5907e32b098d274b084bb31bb73fc78adae27d5be3787a2b7c63"}}