{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JRUOOICKGY7WBOBV3N7RWN5BEE","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":"c98605ed5f0ee96e2c35740c3a38433f417befeed0106c145cc8be974ffc3cc2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:00:49Z","title_canon_sha256":"ced2245ba416b918cc48549c5cef7295b070c3fd3a5bf2cc13ea8f62a25a5b81"},"schema_version":"1.0","source":{"id":"2402.16786","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16786","created_at":"2026-07-05T08:27:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16786v2","created_at":"2026-07-05T08:27:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16786","created_at":"2026-07-05T08:27:46Z"},{"alias_kind":"pith_short_12","alias_value":"JRUOOICKGY7W","created_at":"2026-07-05T08:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"JRUOOICKGY7WBOBV","created_at":"2026-07-05T08:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"JRUOOICK","created_at":"2026-07-05T08:27:46Z"}],"graph_snapshots":[{"event_id":"sha256:aae3b51bafe820857e9c02300f63d229a74ed4d63e2688468ebc888b1db0f714","target":"graph","created_at":"2026-07-05T08:27:46Z","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/2402.16786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much recent work seeks to evaluate values and opinions in large language models (LLMs) using multiple-choice surveys and questionnaires. Most of this work is motivated by concerns around real-world LLM applications. For example, politically-biased LLMs may subtly influence society when they are used by millions of people. Such real-world concerns, however, stand in stark contrast to the artificiality of current evaluations: real users do not typically ask LLMs survey questions. Motivated by this discrepancy, we challenge the prevailing constrained evaluation paradigm for values and opinions in","authors_text":"Dirk Hovy, Hannah Rose Kirk, Hinrich Sch\\\"utze, Musashi Hinck, Paul R\\\"ottger, Valentina Pyatkin, Valentin Hofmann","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:00:49Z","title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16786","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":"sha256:1d5a9a0ad75d266fe46ca45e9eeede5c2923df6bc1b9d8b841ebafa4d040c28c","target":"record","created_at":"2026-07-05T08:27:46Z","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":"c98605ed5f0ee96e2c35740c3a38433f417befeed0106c145cc8be974ffc3cc2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T18:00:49Z","title_canon_sha256":"ced2245ba416b918cc48549c5cef7295b070c3fd3a5bf2cc13ea8f62a25a5b81"},"schema_version":"1.0","source":{"id":"2402.16786","kind":"arxiv","version":2}},"canonical_sha256":"4c68e7204a363f60b835db7f1b37a12124cd96b97b4702cd1e819545f03f7a89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c68e7204a363f60b835db7f1b37a12124cd96b97b4702cd1e819545f03f7a89","first_computed_at":"2026-07-05T08:27:46.721190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:46.721190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"30NE1cnEcWkJZKJ9OMAViLF4utVmEt/5lRGC4Q12z0YeB/vsAt49mFOF5800cOidAXX9wdyavazbFKB1W28UDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:46.721795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16786","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d5a9a0ad75d266fe46ca45e9eeede5c2923df6bc1b9d8b841ebafa4d040c28c","sha256:aae3b51bafe820857e9c02300f63d229a74ed4d63e2688468ebc888b1db0f714"],"state_sha256":"a770caf5624b805c7b25a3adca148dc393a68000ca58dc77809e78f542fa2643"}