{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XZE34TW2L3XALPR3JSAECEHYWW","short_pith_number":"pith:XZE34TW2","canonical_record":{"source":{"id":"2311.18140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T23:03:04Z","cross_cats_sorted":[],"title_canon_sha256":"f1095c7b600d212ab00897c4e61fdaf29ca1b9735eedc3feda7c9f35349d56e4","abstract_canon_sha256":"d569acd221f6b7496f7d4f3862cbf4f1c47b9c13c836a0b18dae7a0e9a65d7a6"},"schema_version":"1.0"},"canonical_sha256":"be49be4eda5eee05be3b4c804110f8b59b57bf1dbe054f79ab844a819e710f03","source":{"kind":"arxiv","id":"2311.18140","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18140","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18140v1","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18140","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"XZE34TW2L3XA","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"XZE34TW2L3XALPR3","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"XZE34TW2","created_at":"2026-07-05T07:18:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XZE34TW2L3XALPR3JSAECEHYWW","target":"record","payload":{"canonical_record":{"source":{"id":"2311.18140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T23:03:04Z","cross_cats_sorted":[],"title_canon_sha256":"f1095c7b600d212ab00897c4e61fdaf29ca1b9735eedc3feda7c9f35349d56e4","abstract_canon_sha256":"d569acd221f6b7496f7d4f3862cbf4f1c47b9c13c836a0b18dae7a0e9a65d7a6"},"schema_version":"1.0"},"canonical_sha256":"be49be4eda5eee05be3b4c804110f8b59b57bf1dbe054f79ab844a819e710f03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:37.608476Z","signature_b64":"vKcKKDYkw6jKTITgX/zPNl5WR7tshodCeaPfYJIqZYtbs0mxd3DKo0dqhQa5iQPzUw+4wKkWCkJ/AmB5a22ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be49be4eda5eee05be3b4c804110f8b59b57bf1dbe054f79ab844a819e710f03","last_reissued_at":"2026-07-05T07:18:37.607973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:37.607973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.18140","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":"2026-07-05T07:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kkZzRCpDxhGL2U4IHlayX+IqWty3V/G93jE+iOaUgqNFenfcBva6rr9s3EBEjWVOdRvsnGRgUnsG8JEy8tSWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:39:01.159324Z"},"content_sha256":"085b30f8a27dc1ba8422f1060694b05f028983ba2b8e7e4344052c8aad732465","schema_version":"1.0","event_id":"sha256:085b30f8a27dc1ba8422f1060694b05f028983ba2b8e7e4344052c8aad732465"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XZE34TW2L3XALPR3JSAECEHYWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ROBBIE: Robust Bias Evaluation of Large Generative Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adina Williams, David Esiobu, Eleonora Presani, Eric Michael Smith, Jane Dwivedi-Yu, Jude Fernandes, Megan Ung, Saghar Hosseini, Xiaoqing Tan, Yuchen Zhang","submitted_at":"2023-11-29T23:03:04Z","abstract_excerpt":"As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across multiple text domains and demographic axes, meaning that testing LLMs on more datasets can potentially help us characterize their biases more fully, and better ensure equal and equitable treatment of marginalized demographic groups. In this work, our focus is two-fold:\n  (1) Benchmarking: a comparison of 6 different prompt-based bias and toxicity metrics across 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18140","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/2311.18140/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":"2026-07-05T07:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKACf0Wd2LoVmvql9akRoZBFwTRD8CfSSw/cKTa9VLCwTI5rnERvKPjZ/sA/GTC53PpfbZMOka/55lqEd4PpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:39:01.160232Z"},"content_sha256":"72e1715e1cb4d382b98168dc5de0ffd617eed3fc07e8543c1ed26ebd7fc5612c","schema_version":"1.0","event_id":"sha256:72e1715e1cb4d382b98168dc5de0ffd617eed3fc07e8543c1ed26ebd7fc5612c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZE34TW2L3XALPR3JSAECEHYWW/bundle.json","state_url":"https://pith.science/pith/XZE34TW2L3XALPR3JSAECEHYWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZE34TW2L3XALPR3JSAECEHYWW/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":"2026-08-08T14:39:01Z","links":{"resolver":"https://pith.science/pith/XZE34TW2L3XALPR3JSAECEHYWW","bundle":"https://pith.science/pith/XZE34TW2L3XALPR3JSAECEHYWW/bundle.json","state":"https://pith.science/pith/XZE34TW2L3XALPR3JSAECEHYWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZE34TW2L3XALPR3JSAECEHYWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XZE34TW2L3XALPR3JSAECEHYWW","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":"d569acd221f6b7496f7d4f3862cbf4f1c47b9c13c836a0b18dae7a0e9a65d7a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T23:03:04Z","title_canon_sha256":"f1095c7b600d212ab00897c4e61fdaf29ca1b9735eedc3feda7c9f35349d56e4"},"schema_version":"1.0","source":{"id":"2311.18140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18140","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18140v1","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18140","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"XZE34TW2L3XA","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"XZE34TW2L3XALPR3","created_at":"2026-07-05T07:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"XZE34TW2","created_at":"2026-07-05T07:18:37Z"}],"graph_snapshots":[{"event_id":"sha256:72e1715e1cb4d382b98168dc5de0ffd617eed3fc07e8543c1ed26ebd7fc5612c","target":"graph","created_at":"2026-07-05T07:18:37Z","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/2311.18140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across multiple text domains and demographic axes, meaning that testing LLMs on more datasets can potentially help us characterize their biases more fully, and better ensure equal and equitable treatment of marginalized demographic groups. In this work, our focus is two-fold:\n  (1) Benchmarking: a comparison of 6 different prompt-based bias and toxicity metrics across 1","authors_text":"Adina Williams, David Esiobu, Eleonora Presani, Eric Michael Smith, Jane Dwivedi-Yu, Jude Fernandes, Megan Ung, Saghar Hosseini, Xiaoqing Tan, Yuchen Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T23:03:04Z","title":"ROBBIE: Robust Bias Evaluation of Large Generative Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18140","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":"sha256:085b30f8a27dc1ba8422f1060694b05f028983ba2b8e7e4344052c8aad732465","target":"record","created_at":"2026-07-05T07:18:37Z","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":"d569acd221f6b7496f7d4f3862cbf4f1c47b9c13c836a0b18dae7a0e9a65d7a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T23:03:04Z","title_canon_sha256":"f1095c7b600d212ab00897c4e61fdaf29ca1b9735eedc3feda7c9f35349d56e4"},"schema_version":"1.0","source":{"id":"2311.18140","kind":"arxiv","version":1}},"canonical_sha256":"be49be4eda5eee05be3b4c804110f8b59b57bf1dbe054f79ab844a819e710f03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be49be4eda5eee05be3b4c804110f8b59b57bf1dbe054f79ab844a819e710f03","first_computed_at":"2026-07-05T07:18:37.607973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:37.607973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vKcKKDYkw6jKTITgX/zPNl5WR7tshodCeaPfYJIqZYtbs0mxd3DKo0dqhQa5iQPzUw+4wKkWCkJ/AmB5a22ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:37.608476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:085b30f8a27dc1ba8422f1060694b05f028983ba2b8e7e4344052c8aad732465","sha256:72e1715e1cb4d382b98168dc5de0ffd617eed3fc07e8543c1ed26ebd7fc5612c"],"state_sha256":"eaf85352e16447337b0362a30e2d742e1d9ae7a05aaedc6f03ab080f271c5064"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D8Nct9UrmAnxFyV2jlSz5TI5QTlnkfQjTv6sr2mx8kgPdwh1e1j4IrT26rl3t5os9xly4PuVK7OoKiObziX4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:39:01.171249Z","bundle_sha256":"7e80d7fde69891c4ba7861573117516eb53ea000a5509b60fa664676977555b4"}}