{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZESMADIX2B6HHZKRTRG3B7HFVF","short_pith_number":"pith:ZESMADIX","canonical_record":{"source":{"id":"2310.11079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c08b767bb235f8bb25439a2516d945b097792223b9886c583cb839908e4be66","abstract_canon_sha256":"1ace5dc97e46ede0f0e90f2a668d6b760d848a8bf42034c8cd07c30a9adad3ec"},"schema_version":"1.0"},"canonical_sha256":"c924c00d17d07c73e5519c4db0fce5a96613a40d0cbe4065411c6d2905730638","source":{"kind":"arxiv","id":"2310.11079","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11079","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11079v1","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11079","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZESMADIX2B6H","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZESMADIX2B6HHZKR","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZESMADIX","created_at":"2026-07-05T07:01:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZESMADIX2B6HHZKRTRG3B7HFVF","target":"record","payload":{"canonical_record":{"source":{"id":"2310.11079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c08b767bb235f8bb25439a2516d945b097792223b9886c583cb839908e4be66","abstract_canon_sha256":"1ace5dc97e46ede0f0e90f2a668d6b760d848a8bf42034c8cd07c30a9adad3ec"},"schema_version":"1.0"},"canonical_sha256":"c924c00d17d07c73e5519c4db0fce5a96613a40d0cbe4065411c6d2905730638","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:50.053184Z","signature_b64":"8+0y1lHHyEF9jq+BM2ai/lSJ992TjQwKHQxP4jq12IUOxFZiJ0Qn4E1h4g+r2EuT1MjvpEu/BnE7MoS0A0LyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c924c00d17d07c73e5519c4db0fce5a96613a40d0cbe4065411c6d2905730638","last_reissued_at":"2026-07-05T07:01:50.052707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:50.052707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.11079","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":"2026-07-05T07:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+/M3lN2V90Zw40oK8EAA12HfruGfe2kIejjG1NF5ztgE2faSXF6TvlRRB458hXX9WUXnqZ6A5182VJSNswuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:15:54.976009Z"},"content_sha256":"5e3c04c2b1398b7453ad5eb50263c5ba6dbdfeceb84c649eacd9417161123235","schema_version":"1.0","event_id":"sha256:5e3c04c2b1398b7453ad5eb50263c5ba6dbdfeceb84c649eacd9417161123235"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZESMADIX2B6HHZKRTRG3B7HFVF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng-Chu Cheng, Hsuan Su, Hua Farn, Hung-yi Lee, Saurav Sahay, Shachi H Kumar, Shang-Tse Chen","submitted_at":"2023-10-17T08:56:04Z","abstract_excerpt":"Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots encode the potential biases while retaining disparities that can harm humans during interactions. The traditional biases investigation methods often rely on human-written test cases. However, these test cases are usually expensive and limited. In this work, we propose a first-of-its-kind method that automatically generates test cases to detect LLMs' potential gender bias. We apply our method to three well-known LLMs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11079","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/2310.11079/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":"2026-07-05T07:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CI7apZOHUrqYWAtSTH5BpL38delnEokrFZOHsilmrCOyr8gtLyj1kUIfEFVJnQL6cyQg8WWaYmbbG61CuCYgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:15:54.976394Z"},"content_sha256":"a8867a99aeade339c1d9cd16b178f60d52d4e73b46db926e7d9a0d8718e4b34d","schema_version":"1.0","event_id":"sha256:a8867a99aeade339c1d9cd16b178f60d52d4e73b46db926e7d9a0d8718e4b34d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZESMADIX2B6HHZKRTRG3B7HFVF/bundle.json","state_url":"https://pith.science/pith/ZESMADIX2B6HHZKRTRG3B7HFVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZESMADIX2B6HHZKRTRG3B7HFVF/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":"2026-07-07T12:15:54Z","links":{"resolver":"https://pith.science/pith/ZESMADIX2B6HHZKRTRG3B7HFVF","bundle":"https://pith.science/pith/ZESMADIX2B6HHZKRTRG3B7HFVF/bundle.json","state":"https://pith.science/pith/ZESMADIX2B6HHZKRTRG3B7HFVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZESMADIX2B6HHZKRTRG3B7HFVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZESMADIX2B6HHZKRTRG3B7HFVF","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":"1ace5dc97e46ede0f0e90f2a668d6b760d848a8bf42034c8cd07c30a9adad3ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","title_canon_sha256":"7c08b767bb235f8bb25439a2516d945b097792223b9886c583cb839908e4be66"},"schema_version":"1.0","source":{"id":"2310.11079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11079","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11079v1","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11079","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZESMADIX2B6H","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZESMADIX2B6HHZKR","created_at":"2026-07-05T07:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZESMADIX","created_at":"2026-07-05T07:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:a8867a99aeade339c1d9cd16b178f60d52d4e73b46db926e7d9a0d8718e4b34d","target":"graph","created_at":"2026-07-05T07:01:50Z","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/2310.11079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots encode the potential biases while retaining disparities that can harm humans during interactions. The traditional biases investigation methods often rely on human-written test cases. However, these test cases are usually expensive and limited. In this work, we propose a first-of-its-kind method that automatically generates test cases to detect LLMs' potential gender bias. We apply our method to three well-known LLMs ","authors_text":"Cheng-Chu Cheng, Hsuan Su, Hua Farn, Hung-yi Lee, Saurav Sahay, Shachi H Kumar, Shang-Tse Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11079","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":"sha256:5e3c04c2b1398b7453ad5eb50263c5ba6dbdfeceb84c649eacd9417161123235","target":"record","created_at":"2026-07-05T07:01:50Z","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":"1ace5dc97e46ede0f0e90f2a668d6b760d848a8bf42034c8cd07c30a9adad3ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T08:56:04Z","title_canon_sha256":"7c08b767bb235f8bb25439a2516d945b097792223b9886c583cb839908e4be66"},"schema_version":"1.0","source":{"id":"2310.11079","kind":"arxiv","version":1}},"canonical_sha256":"c924c00d17d07c73e5519c4db0fce5a96613a40d0cbe4065411c6d2905730638","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c924c00d17d07c73e5519c4db0fce5a96613a40d0cbe4065411c6d2905730638","first_computed_at":"2026-07-05T07:01:50.052707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:50.052707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+0y1lHHyEF9jq+BM2ai/lSJ992TjQwKHQxP4jq12IUOxFZiJ0Qn4E1h4g+r2EuT1MjvpEu/BnE7MoS0A0LyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:50.053184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e3c04c2b1398b7453ad5eb50263c5ba6dbdfeceb84c649eacd9417161123235","sha256:a8867a99aeade339c1d9cd16b178f60d52d4e73b46db926e7d9a0d8718e4b34d"],"state_sha256":"a73077dc39d9cb0722232ee2bfdebe19bb76fe173c8528343b58f774a38b30a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uw64XaWStmdtnHYA062R21HDMjUimcRXmYpDIfZxE8FGaOpWLadFGxT+n8TF9ItwxGCYKifVLPb8SHqj5XCGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:15:54.978307Z","bundle_sha256":"e993a0526f4c2172db00544082171fe179270668e7a20b2b5cc536c50fa192f0"}}