{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YU6OKLCMU5KSC2UHCQFPW2QYPC","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":"38e0ce6d42453d4b148a2372cf148a2cfcf887ed58514173f8f282231744f47a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T02:28:53Z","title_canon_sha256":"90eac916c07c2b65482a827f7277c91c7f5361f06d4a0f10a7e3fdfc9d5356d2"},"schema_version":"1.0","source":{"id":"2409.05283","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05283","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05283v2","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05283","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_12","alias_value":"YU6OKLCMU5KS","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_16","alias_value":"YU6OKLCMU5KSC2UH","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_8","alias_value":"YU6OKLCM","created_at":"2026-07-05T09:41:41Z"}],"graph_snapshots":[{"event_id":"sha256:0cab4732de4081461ce7a87de96f6f60524f6bfca56aa140da0d3bedd10328f5","target":"graph","created_at":"2026-07-05T09:41:41Z","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/2409.05283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model alignment research often attempts to ensure that models are not only helpful and harmless, but also truthful and unbiased. However, optimizing these objectives simultaneously can obscure how improving one aspect might impact the others. In this work, we focus on analyzing the relationship between two concepts essential in both language model alignment and political science: truthfulness and political bias. We train reward models on various popular truthfulness datasets and subsequently evaluate their political bias. Our findings reveal that optimizing reward models for truthfuln","authors_text":"Cassandra Overney, Deb Roy, Elinor Poole-Dayan, Jad Kabbara, Shrestha Mohanty, Suyash Fulay, William Brannon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T02:28:53Z","title":"On the Relationship between Truth and Political Bias in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05283","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":"sha256:7f21e13c4a6f4d25ea8685bbf5eb722854314c1c88184abc8d33753dbe907431","target":"record","created_at":"2026-07-05T09:41:41Z","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":"38e0ce6d42453d4b148a2372cf148a2cfcf887ed58514173f8f282231744f47a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T02:28:53Z","title_canon_sha256":"90eac916c07c2b65482a827f7277c91c7f5361f06d4a0f10a7e3fdfc9d5356d2"},"schema_version":"1.0","source":{"id":"2409.05283","kind":"arxiv","version":2}},"canonical_sha256":"c53ce52c4ca755216a87140afb6a187892fa1e2ce7f5e2d80c626cb7a713d7db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c53ce52c4ca755216a87140afb6a187892fa1e2ce7f5e2d80c626cb7a713d7db","first_computed_at":"2026-07-05T09:41:41.085889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:41.085889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xHa12t+xk7HfWMbeqF1RL+IujzQNcWSRkI4Yt/G3+OXYZ9Dkq8w6Bc97s1V3WY7khtiuYym7hjlsYyFoV/PeCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:41.086453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05283","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f21e13c4a6f4d25ea8685bbf5eb722854314c1c88184abc8d33753dbe907431","sha256:0cab4732de4081461ce7a87de96f6f60524f6bfca56aa140da0d3bedd10328f5"],"state_sha256":"900870d0e165d2523a2fa02f6cdd122c9e9a675ba1bc437e8aa5225af3dd20bc"}