{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SXU6A6LOYZTDK3TTZWSSFIUHLK","short_pith_number":"pith:SXU6A6LO","canonical_record":{"source":{"id":"2506.22232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T13:49:37Z","cross_cats_sorted":[],"title_canon_sha256":"db5c12a53aecf84190291b37c98b73ca5a9b1c102cc00640f19bff77609a6987","abstract_canon_sha256":"3cea0641b223750f74a994a960effe39d8686cdcc09383ca49b97498d629b431"},"schema_version":"1.0"},"canonical_sha256":"95e9e0796ec666356e73cda522a2875a828125f74e5af27bbde843499d7fb21d","source":{"kind":"arxiv","id":"2506.22232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22232","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22232v1","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22232","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"pith_short_12","alias_value":"SXU6A6LOYZTD","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"pith_short_16","alias_value":"SXU6A6LOYZTDK3TT","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"pith_short_8","alias_value":"SXU6A6LO","created_at":"2026-07-05T11:28:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SXU6A6LOYZTDK3TTZWSSFIUHLK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T13:49:37Z","cross_cats_sorted":[],"title_canon_sha256":"db5c12a53aecf84190291b37c98b73ca5a9b1c102cc00640f19bff77609a6987","abstract_canon_sha256":"3cea0641b223750f74a994a960effe39d8686cdcc09383ca49b97498d629b431"},"schema_version":"1.0"},"canonical_sha256":"95e9e0796ec666356e73cda522a2875a828125f74e5af27bbde843499d7fb21d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:24.021594Z","signature_b64":"nS/tBUNsF1I72ehUsZfws/Rg8Itr3F5iikxg2GRZO1J1tIhWHO2jSTgyPiXgZ40upmgLD2BL2dDdtRz4fiQaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95e9e0796ec666356e73cda522a2875a828125f74e5af27bbde843499d7fb21d","last_reissued_at":"2026-07-05T11:28:24.021188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:24.021188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22232","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":"2026-07-05T11:28:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gPuf0hYzGF49EWIY32uCdbtvOYgHC/tXPj8+3TeAsfdq+PZFWug4ZXHEOwxHhCEU8s8VUe2XGCVv4/cZ1OavCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:31:03.674708Z"},"content_sha256":"46533d6707c1023e35d7b5b1479fe5c54a227cb2e02a5dbd3a3909604f9c0157","schema_version":"1.0","event_id":"sha256:46533d6707c1023e35d7b5b1479fe5c54a227cb2e02a5dbd3a3909604f9c0157"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SXU6A6LOYZTDK3TTZWSSFIUHLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging In-Context Learning for Political Bias Testing of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jannis Vamvas, Lena A. J\\\"ager, Patrick Haller, Rico Sennrich","submitted_at":"2025-06-27T13:49:37Z","abstract_excerpt":"A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruction-tuned models to their base versions. Experiments with LLMs of various sizes indicate that instruc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22232","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/2506.22232/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":"2026-07-05T11:28:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEjFHRGnZ/0hJltKKvacg6CQ7QENPByKKRcKBZ0+gVoqifqJTs1BvCJiHBCy1MgnVHYUgn5M51iG9PXhvCeRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:31:03.675566Z"},"content_sha256":"9110ccaaab07c361b40324eb5eca892b46374f6312ff83c288a6324c2fa0ccff","schema_version":"1.0","event_id":"sha256:9110ccaaab07c361b40324eb5eca892b46374f6312ff83c288a6324c2fa0ccff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXU6A6LOYZTDK3TTZWSSFIUHLK/bundle.json","state_url":"https://pith.science/pith/SXU6A6LOYZTDK3TTZWSSFIUHLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXU6A6LOYZTDK3TTZWSSFIUHLK/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":"2026-08-09T14:31:03Z","links":{"resolver":"https://pith.science/pith/SXU6A6LOYZTDK3TTZWSSFIUHLK","bundle":"https://pith.science/pith/SXU6A6LOYZTDK3TTZWSSFIUHLK/bundle.json","state":"https://pith.science/pith/SXU6A6LOYZTDK3TTZWSSFIUHLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXU6A6LOYZTDK3TTZWSSFIUHLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SXU6A6LOYZTDK3TTZWSSFIUHLK","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":"3cea0641b223750f74a994a960effe39d8686cdcc09383ca49b97498d629b431","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T13:49:37Z","title_canon_sha256":"db5c12a53aecf84190291b37c98b73ca5a9b1c102cc00640f19bff77609a6987"},"schema_version":"1.0","source":{"id":"2506.22232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22232","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22232v1","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22232","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"pith_short_12","alias_value":"SXU6A6LOYZTD","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"pith_short_16","alias_value":"SXU6A6LOYZTDK3TT","created_at":"2026-07-05T11:28:24Z"},{"alias_kind":"pith_short_8","alias_value":"SXU6A6LO","created_at":"2026-07-05T11:28:24Z"}],"graph_snapshots":[{"event_id":"sha256:9110ccaaab07c361b40324eb5eca892b46374f6312ff83c288a6324c2fa0ccff","target":"graph","created_at":"2026-07-05T11:28:24Z","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/2506.22232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruction-tuned models to their base versions. Experiments with LLMs of various sizes indicate that instruc","authors_text":"Jannis Vamvas, Lena A. J\\\"ager, Patrick Haller, Rico Sennrich","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T13:49:37Z","title":"Leveraging In-Context Learning for Political Bias Testing of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22232","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":"sha256:46533d6707c1023e35d7b5b1479fe5c54a227cb2e02a5dbd3a3909604f9c0157","target":"record","created_at":"2026-07-05T11:28:24Z","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":"3cea0641b223750f74a994a960effe39d8686cdcc09383ca49b97498d629b431","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T13:49:37Z","title_canon_sha256":"db5c12a53aecf84190291b37c98b73ca5a9b1c102cc00640f19bff77609a6987"},"schema_version":"1.0","source":{"id":"2506.22232","kind":"arxiv","version":1}},"canonical_sha256":"95e9e0796ec666356e73cda522a2875a828125f74e5af27bbde843499d7fb21d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95e9e0796ec666356e73cda522a2875a828125f74e5af27bbde843499d7fb21d","first_computed_at":"2026-07-05T11:28:24.021188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:24.021188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nS/tBUNsF1I72ehUsZfws/Rg8Itr3F5iikxg2GRZO1J1tIhWHO2jSTgyPiXgZ40upmgLD2BL2dDdtRz4fiQaAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:24.021594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46533d6707c1023e35d7b5b1479fe5c54a227cb2e02a5dbd3a3909604f9c0157","sha256:9110ccaaab07c361b40324eb5eca892b46374f6312ff83c288a6324c2fa0ccff"],"state_sha256":"7f5c8bf0ca66a4d18bfdd251636faf30f8dd86c6a8872142db215b160ebf2dc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jU9xBfTAS/aczu5JpzoOICjCHrr4JAEh64SJQOlO3KUEljgDte0NaVHzHdBaNbN5vadluj0yT9vMiwoKiPrDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:31:03.682314Z","bundle_sha256":"5a28d99fe4233ef69d787dd7701353ab17d310c41d8fc870ba4c7df08fde2167"}}