{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EUCS7TYU7W5LOAXYXJT42I3GHQ","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":"42b7504e58582ce8dc066be1181da56fd4b362eae32be2310a0799a8aebd9570","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:57:20Z","title_canon_sha256":"f454979ae3c308595bb262166d05f8ad5d4019a92e0389ce809b16c2f18df9a5"},"schema_version":"1.0","source":{"id":"2410.18906","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18906","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18906v2","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18906","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"EUCS7TYU7W5L","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_16","alias_value":"EUCS7TYU7W5LOAXY","created_at":"2026-07-05T09:33:39Z"},{"alias_kind":"pith_short_8","alias_value":"EUCS7TYU","created_at":"2026-07-05T09:33:39Z"}],"graph_snapshots":[{"event_id":"sha256:3539d5ec74f255c317abf2d47f296687922ecfe9fea9783e3ea9f0cecb8c9705","target":"graph","created_at":"2026-07-05T09:33:39Z","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/2410.18906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Auditing Large Language Models (LLMs) to discover their biases and preferences is an emerging challenge in creating Responsible Artificial Intelligence (AI). While various methods have been proposed to elicit the preferences of such models, countermeasures have been taken by LLM trainers, such that LLMs hide, obfuscate or point blank refuse to disclosure their positions on certain subjects. This paper presents PRISM, a flexible, inquiry-based methodology for auditing LLMs - that seeks to illicit such positions indirectly through task-based inquiry prompting rather than direct inquiry of said p","authors_text":"Leif Azzopardi, Yashar Moshfeghi","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:57:20Z","title":"PRISM: A Methodology for Auditing Biases in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18906","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":"sha256:9a13c6abb15d91279d1da7d696a45644e247ebf0bc34dd806de18f936884a01d","target":"record","created_at":"2026-07-05T09:33:39Z","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":"42b7504e58582ce8dc066be1181da56fd4b362eae32be2310a0799a8aebd9570","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T16:57:20Z","title_canon_sha256":"f454979ae3c308595bb262166d05f8ad5d4019a92e0389ce809b16c2f18df9a5"},"schema_version":"1.0","source":{"id":"2410.18906","kind":"arxiv","version":2}},"canonical_sha256":"25052fcf14fdbab702f8ba67cd23663c347cba338224eda58065c3909c6e4d64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25052fcf14fdbab702f8ba67cd23663c347cba338224eda58065c3909c6e4d64","first_computed_at":"2026-07-05T09:33:39.294018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:39.294018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D4gsdty/urIE0jxdaUme9OPN1G1nfydSwHaDtN9stymvtHrCrq3BN2GBgFJQlMKc9wUzrEH4GFms932pPz5jDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:39.294508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18906","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a13c6abb15d91279d1da7d696a45644e247ebf0bc34dd806de18f936884a01d","sha256:3539d5ec74f255c317abf2d47f296687922ecfe9fea9783e3ea9f0cecb8c9705"],"state_sha256":"0e7acbc7d1fb2d8d96a211f3cd27ce5cef147bc5f86d2f63b5f02b98cb625f2e"}