{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:23F4ZDJZWKF3WE6Q446CYMV43H","short_pith_number":"pith:23F4ZDJZ","canonical_record":{"source":{"id":"2502.20897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T09:53:42Z","cross_cats_sorted":[],"title_canon_sha256":"bfd9d858215cc6fe68e57cee8da2bbe8946b5f8d604745d8e7ecf71557eedfca","abstract_canon_sha256":"8f024ee089eda809d9cf5c7f605e7fb3f8be55b948006b58d9e52540cdd17ae6"},"schema_version":"1.0"},"canonical_sha256":"d6cbcc8d39b28bbb13d0e73c2c32bcd9f39e081f5e8dd1c3846201017cbdf694","source":{"kind":"arxiv","id":"2502.20897","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20897","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20897v1","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20897","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"23F4ZDJZWKF3","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"23F4ZDJZWKF3WE6Q","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"23F4ZDJZ","created_at":"2026-07-05T10:21:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:23F4ZDJZWKF3WE6Q446CYMV43H","target":"record","payload":{"canonical_record":{"source":{"id":"2502.20897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T09:53:42Z","cross_cats_sorted":[],"title_canon_sha256":"bfd9d858215cc6fe68e57cee8da2bbe8946b5f8d604745d8e7ecf71557eedfca","abstract_canon_sha256":"8f024ee089eda809d9cf5c7f605e7fb3f8be55b948006b58d9e52540cdd17ae6"},"schema_version":"1.0"},"canonical_sha256":"d6cbcc8d39b28bbb13d0e73c2c32bcd9f39e081f5e8dd1c3846201017cbdf694","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:41.790384Z","signature_b64":"MF9Um8seyERs1qb7L/YUn7bvyWixep6fCToamAv7TePHHmUuNmQHVdRPOFtoaHmlLUR0sa3oTpvwHMC2AeMVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6cbcc8d39b28bbb13d0e73c2c32bcd9f39e081f5e8dd1c3846201017cbdf694","last_reissued_at":"2026-07-05T10:21:41.789745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:41.789745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.20897","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":"2026-07-05T10:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSn+lUnCbFzf2UHPBvSWtMVjCyPRQPKaYqMlA1wCQKEj8UOvQS7SIgnoS+o4tX7rZgi3Cwo+iD3MuRXJGQSwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:13:52.714776Z"},"content_sha256":"45a1e6946ba9637b4a8117ad19b72213532118f12f8e09566eee63c40019ae68","schema_version":"1.0","event_id":"sha256:45a1e6946ba9637b4a8117ad19b72213532118f12f8e09566eee63c40019ae68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:23F4ZDJZWKF3WE6Q446CYMV43H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Jurgens, Dirk Hovy, Jiaxin Pei, Matthias Orlikowski, Paul R\\\"ottger, Philipp Cimiano","submitted_at":"2025-02-28T09:53:42Z","abstract_excerpt":"People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person's sociodemographic characteristics. LLMs have also been used to label data, but recent work has shown that models perform poorly when prompted with sociodemographic attributes, suggesting limited inherent sociodemographic knowledge. Here, we ask whether LLMs can be trained to be accurate sociodemographic models of annotator variation. Using a curated dataset of five tasks with standardized sociodemographics, we show that models do improve in sociodemographic prompti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20897","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/2502.20897/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":"2026-07-05T10:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xlumAFFIaYyEEHnR1Mk+n1CnLfO5prMCXA8r8Nx9ovJAO/XK9Rf4bXIGQDyUY0HOXfnD75PXinwMNV8Ii+q0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:13:52.715140Z"},"content_sha256":"94b0895620f425d5e1a801aeb9b29a5019e1fecd6a82d0404a7b5c637c06905c","schema_version":"1.0","event_id":"sha256:94b0895620f425d5e1a801aeb9b29a5019e1fecd6a82d0404a7b5c637c06905c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23F4ZDJZWKF3WE6Q446CYMV43H/bundle.json","state_url":"https://pith.science/pith/23F4ZDJZWKF3WE6Q446CYMV43H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23F4ZDJZWKF3WE6Q446CYMV43H/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":"2026-08-17T06:13:52Z","links":{"resolver":"https://pith.science/pith/23F4ZDJZWKF3WE6Q446CYMV43H","bundle":"https://pith.science/pith/23F4ZDJZWKF3WE6Q446CYMV43H/bundle.json","state":"https://pith.science/pith/23F4ZDJZWKF3WE6Q446CYMV43H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23F4ZDJZWKF3WE6Q446CYMV43H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:23F4ZDJZWKF3WE6Q446CYMV43H","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":"8f024ee089eda809d9cf5c7f605e7fb3f8be55b948006b58d9e52540cdd17ae6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T09:53:42Z","title_canon_sha256":"bfd9d858215cc6fe68e57cee8da2bbe8946b5f8d604745d8e7ecf71557eedfca"},"schema_version":"1.0","source":{"id":"2502.20897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20897","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20897v1","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20897","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"23F4ZDJZWKF3","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"23F4ZDJZWKF3WE6Q","created_at":"2026-07-05T10:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"23F4ZDJZ","created_at":"2026-07-05T10:21:41Z"}],"graph_snapshots":[{"event_id":"sha256:94b0895620f425d5e1a801aeb9b29a5019e1fecd6a82d0404a7b5c637c06905c","target":"graph","created_at":"2026-07-05T10:21:41Z","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/2502.20897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person's sociodemographic characteristics. LLMs have also been used to label data, but recent work has shown that models perform poorly when prompted with sociodemographic attributes, suggesting limited inherent sociodemographic knowledge. Here, we ask whether LLMs can be trained to be accurate sociodemographic models of annotator variation. Using a curated dataset of five tasks with standardized sociodemographics, we show that models do improve in sociodemographic prompti","authors_text":"David Jurgens, Dirk Hovy, Jiaxin Pei, Matthias Orlikowski, Paul R\\\"ottger, Philipp Cimiano","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T09:53:42Z","title":"Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20897","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":"sha256:45a1e6946ba9637b4a8117ad19b72213532118f12f8e09566eee63c40019ae68","target":"record","created_at":"2026-07-05T10:21:41Z","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":"8f024ee089eda809d9cf5c7f605e7fb3f8be55b948006b58d9e52540cdd17ae6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T09:53:42Z","title_canon_sha256":"bfd9d858215cc6fe68e57cee8da2bbe8946b5f8d604745d8e7ecf71557eedfca"},"schema_version":"1.0","source":{"id":"2502.20897","kind":"arxiv","version":1}},"canonical_sha256":"d6cbcc8d39b28bbb13d0e73c2c32bcd9f39e081f5e8dd1c3846201017cbdf694","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6cbcc8d39b28bbb13d0e73c2c32bcd9f39e081f5e8dd1c3846201017cbdf694","first_computed_at":"2026-07-05T10:21:41.789745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:41.789745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MF9Um8seyERs1qb7L/YUn7bvyWixep6fCToamAv7TePHHmUuNmQHVdRPOFtoaHmlLUR0sa3oTpvwHMC2AeMVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:41.790384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45a1e6946ba9637b4a8117ad19b72213532118f12f8e09566eee63c40019ae68","sha256:94b0895620f425d5e1a801aeb9b29a5019e1fecd6a82d0404a7b5c637c06905c"],"state_sha256":"903fa3ba5f989bcb6fe657ec8505fdeafb4e8778e4e9ed923c2d9401178ab661"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qnjtY6YeVOLfGIkRXfJwHYmMEyXiEHVjW/QEkdNG6aT/TAzfdfKmvlaH6g05Bngg0HnJOPGOFe4VVF5Jz3l3BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:13:52.717795Z","bundle_sha256":"72e77209b6c0bd72637985bee33d1c2e2f2f9f59e53c977616993939bf20e32b"}}