{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SA2M4VFBYY3QF755ZCQ5YAKZP4","short_pith_number":"pith:SA2M4VFB","canonical_record":{"source":{"id":"2505.23996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T20:45:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"53e546d43f3f022de5be974b87698a172b7d8cac4276086fe450327cf836f7ac","abstract_canon_sha256":"9cef2bc7cee4dabf47658c602b0ad6f313a490e0597c0f125ff5d2f3bdd1f561"},"schema_version":"1.0"},"canonical_sha256":"9034ce54a1c63702ffbdc8a1dc01597f33f35d0705d3d321ae433d6910a7df77","source":{"kind":"arxiv","id":"2505.23996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23996","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23996v1","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23996","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"pith_short_12","alias_value":"SA2M4VFBYY3Q","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"pith_short_16","alias_value":"SA2M4VFBYY3QF755","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"pith_short_8","alias_value":"SA2M4VFB","created_at":"2026-07-05T11:12:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SA2M4VFBYY3QF755ZCQ5YAKZP4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T20:45:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"53e546d43f3f022de5be974b87698a172b7d8cac4276086fe450327cf836f7ac","abstract_canon_sha256":"9cef2bc7cee4dabf47658c602b0ad6f313a490e0597c0f125ff5d2f3bdd1f561"},"schema_version":"1.0"},"canonical_sha256":"9034ce54a1c63702ffbdc8a1dc01597f33f35d0705d3d321ae433d6910a7df77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:39.820313Z","signature_b64":"DDDmCBc+wTTe9pdBTgCDB7CFvBgEyf8T7AjDufSgzAlgv1VhAfA5CB+MMIAF0ANWRSjMKytmtPSiDFnR91VMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9034ce54a1c63702ffbdc8a1dc01597f33f35d0705d3d321ae433d6910a7df77","last_reissued_at":"2026-07-05T11:12:39.819720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:39.819720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23996","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":"2026-07-05T11:12:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zxcdojFQiDZGpARKpBGNE2bhDomCsudM8SMgLqc5zyRxiRGdcJF9I4R7p8rHQfBZD+6jr8t3VKSQD58JiFQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:17:02.768147Z"},"content_sha256":"dbc35367911a25e7fdb5d762bcdd9c5e71927e974b2d16a67d0da056175ce7bd","schema_version":"1.0","event_id":"sha256:dbc35367911a25e7fdb5d762bcdd9c5e71927e974b2d16a67d0da056175ce7bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SA2M4VFBYY3QF755ZCQ5YAKZP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Golinski, Barry-John Theobald, Falaah Arif Khan, Luca Zappella, Natalie Mackraz, Nicholas Apostoloff, Nivedha Sivakumar, Rin Metcalf Susa, Yinong Oliver Wang","submitted_at":"2025-05-29T20:45:18Z","abstract_excerpt":"The recent rapid adoption of large language models (LLMs) highlights the critical need for benchmarking their fairness. Conventional fairness metrics, which focus on discrete accuracy-based evaluations (i.e., prediction correctness), fail to capture the implicit impact of model uncertainty (e.g., higher model confidence about one group over another despite similar accuracy). To address this limitation, we propose an uncertainty-aware fairness metric, UCerF, to enable a fine-grained evaluation of model fairness that is more reflective of the internal bias in model decisions compared to conventi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23996","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/2505.23996/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":"2026-07-05T11:12:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lYba93acXeUeNVLZ7IOjAphnvdI5Nls2qlxz/D6JRHoHzqeqZZbaR409LlOIqq17RpbqK15zUjT4ZJOlq4PbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:17:02.768698Z"},"content_sha256":"7fca37a400db2bd7bc70ca21d627f1fe341125584b3eb7aacba817acdcfa6d21","schema_version":"1.0","event_id":"sha256:7fca37a400db2bd7bc70ca21d627f1fe341125584b3eb7aacba817acdcfa6d21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SA2M4VFBYY3QF755ZCQ5YAKZP4/bundle.json","state_url":"https://pith.science/pith/SA2M4VFBYY3QF755ZCQ5YAKZP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SA2M4VFBYY3QF755ZCQ5YAKZP4/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":"2026-08-08T01:17:02Z","links":{"resolver":"https://pith.science/pith/SA2M4VFBYY3QF755ZCQ5YAKZP4","bundle":"https://pith.science/pith/SA2M4VFBYY3QF755ZCQ5YAKZP4/bundle.json","state":"https://pith.science/pith/SA2M4VFBYY3QF755ZCQ5YAKZP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SA2M4VFBYY3QF755ZCQ5YAKZP4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SA2M4VFBYY3QF755ZCQ5YAKZP4","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":"9cef2bc7cee4dabf47658c602b0ad6f313a490e0597c0f125ff5d2f3bdd1f561","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T20:45:18Z","title_canon_sha256":"53e546d43f3f022de5be974b87698a172b7d8cac4276086fe450327cf836f7ac"},"schema_version":"1.0","source":{"id":"2505.23996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23996","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23996v1","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23996","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"pith_short_12","alias_value":"SA2M4VFBYY3Q","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"pith_short_16","alias_value":"SA2M4VFBYY3QF755","created_at":"2026-07-05T11:12:39Z"},{"alias_kind":"pith_short_8","alias_value":"SA2M4VFB","created_at":"2026-07-05T11:12:39Z"}],"graph_snapshots":[{"event_id":"sha256:7fca37a400db2bd7bc70ca21d627f1fe341125584b3eb7aacba817acdcfa6d21","target":"graph","created_at":"2026-07-05T11:12:39Z","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/2505.23996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent rapid adoption of large language models (LLMs) highlights the critical need for benchmarking their fairness. Conventional fairness metrics, which focus on discrete accuracy-based evaluations (i.e., prediction correctness), fail to capture the implicit impact of model uncertainty (e.g., higher model confidence about one group over another despite similar accuracy). To address this limitation, we propose an uncertainty-aware fairness metric, UCerF, to enable a fine-grained evaluation of model fairness that is more reflective of the internal bias in model decisions compared to conventi","authors_text":"Adam Golinski, Barry-John Theobald, Falaah Arif Khan, Luca Zappella, Natalie Mackraz, Nicholas Apostoloff, Nivedha Sivakumar, Rin Metcalf Susa, Yinong Oliver Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T20:45:18Z","title":"Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23996","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:dbc35367911a25e7fdb5d762bcdd9c5e71927e974b2d16a67d0da056175ce7bd","target":"record","created_at":"2026-07-05T11:12:39Z","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":"9cef2bc7cee4dabf47658c602b0ad6f313a490e0597c0f125ff5d2f3bdd1f561","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T20:45:18Z","title_canon_sha256":"53e546d43f3f022de5be974b87698a172b7d8cac4276086fe450327cf836f7ac"},"schema_version":"1.0","source":{"id":"2505.23996","kind":"arxiv","version":1}},"canonical_sha256":"9034ce54a1c63702ffbdc8a1dc01597f33f35d0705d3d321ae433d6910a7df77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9034ce54a1c63702ffbdc8a1dc01597f33f35d0705d3d321ae433d6910a7df77","first_computed_at":"2026-07-05T11:12:39.819720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:39.819720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DDDmCBc+wTTe9pdBTgCDB7CFvBgEyf8T7AjDufSgzAlgv1VhAfA5CB+MMIAF0ANWRSjMKytmtPSiDFnR91VMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:39.820313Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbc35367911a25e7fdb5d762bcdd9c5e71927e974b2d16a67d0da056175ce7bd","sha256:7fca37a400db2bd7bc70ca21d627f1fe341125584b3eb7aacba817acdcfa6d21"],"state_sha256":"18b70696624824bf29982b1d42d9eb82dc8445cc076a2a60e828423d6e24ee67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfbewLwcnKgBaEDqh71F3QggPSSSJ83OOm/HL7k13bkaB+MQ7rfQt+5O+efQ422+tPZ4bGt+r8rdZnD/PyW8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:17:02.772188Z","bundle_sha256":"281fe533fecdedd89742c41aaf36d3589a5448e2cb43aa9c7c14b779f1ff97f8"}}