{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3NDD3D2JTXJ4XW4OUE224JR7MO","short_pith_number":"pith:3NDD3D2J","canonical_record":{"source":{"id":"2402.01981","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T01:40:11Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"31c42e50faee083c5d81521a364a3810f1e99963884d46dffaa766857df7aa4e","abstract_canon_sha256":"4461379cdc8fd95a2ab18a6e5c5c15882920bfb81dd4f83d12b33a0e7dcee8f7"},"schema_version":"1.0"},"canonical_sha256":"db463d8f499dd3cbdb8ea135ae263f63b2a027a044f1521d9351f1f1cf073dba","source":{"kind":"arxiv","id":"2402.01981","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01981","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01981v1","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01981","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"3NDD3D2JTXJ4","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_16","alias_value":"3NDD3D2JTXJ4XW4O","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_8","alias_value":"3NDD3D2J","created_at":"2026-07-05T07:41:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3NDD3D2JTXJ4XW4OUE224JR7MO","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01981","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T01:40:11Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"31c42e50faee083c5d81521a364a3810f1e99963884d46dffaa766857df7aa4e","abstract_canon_sha256":"4461379cdc8fd95a2ab18a6e5c5c15882920bfb81dd4f83d12b33a0e7dcee8f7"},"schema_version":"1.0"},"canonical_sha256":"db463d8f499dd3cbdb8ea135ae263f63b2a027a044f1521d9351f1f1cf073dba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:09.152604Z","signature_b64":"v5M/C58drf7lrCOh4oCDWQOllkfMEsl9VHruZKj2VKScmQscB5pWs2oeU46IxhNIMGvS3Sh2AWHe9Jshwc51AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db463d8f499dd3cbdb8ea135ae263f63b2a027a044f1521d9351f1f1cf073dba","last_reissued_at":"2026-07-05T07:41:09.152087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:09.152087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01981","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":"2026-07-05T07:41:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mqStz8GKCCTEivPe60r86IQGAMErQCdlC0AEjDZudNu20jP8tisfX/NgT5F37VUMhBJvlriEnS0BQFSuerR9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:43:05.787795Z"},"content_sha256":"919ec4c97d1bdc06910495eb14a203b41293b2e8f5f67673610d493a40969d23","schema_version":"1.0","event_id":"sha256:919ec4c97d1bdc06910495eb14a203b41293b2e8f5f67673610d493a40969d23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3NDD3D2JTXJ4XW4OUE224JR7MO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Hanieh Deilamsalehy, Isabel O. Gallegos, Joe Barrow, Md Mehrab Tanjim, Ruiyi Zhang, Ryan A. Rossi, Sungchul Kim, Tong Yu","submitted_at":"2024-02-03T01:40:11Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation techniques, most require modifications to the training data, model parameters, or decoding strategy, which may be infeasible without access to a trainable model. In this work, we leverage the zero-shot capabilities of LLMs to reduce stereotyping in a technique we introduce as zero-shot self-debiasing. With two approaches, self-debiasing via explanation and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01981","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/2402.01981/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":"2026-07-05T07:41:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmtNfEx35LVUT71ePtEkaFEX64d458qRIIhMJWThI1tcLHSXSIR58HGD9kaYPrfSPsPI8Xxro6hoK5sRxYDECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:43:05.788361Z"},"content_sha256":"303a284fcf3447a74a745ee0b8761eb92a767470b1bb238829b50f99c772b3c1","schema_version":"1.0","event_id":"sha256:303a284fcf3447a74a745ee0b8761eb92a767470b1bb238829b50f99c772b3c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NDD3D2JTXJ4XW4OUE224JR7MO/bundle.json","state_url":"https://pith.science/pith/3NDD3D2JTXJ4XW4OUE224JR7MO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NDD3D2JTXJ4XW4OUE224JR7MO/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":"2026-08-09T00:43:05Z","links":{"resolver":"https://pith.science/pith/3NDD3D2JTXJ4XW4OUE224JR7MO","bundle":"https://pith.science/pith/3NDD3D2JTXJ4XW4OUE224JR7MO/bundle.json","state":"https://pith.science/pith/3NDD3D2JTXJ4XW4OUE224JR7MO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NDD3D2JTXJ4XW4OUE224JR7MO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3NDD3D2JTXJ4XW4OUE224JR7MO","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":"4461379cdc8fd95a2ab18a6e5c5c15882920bfb81dd4f83d12b33a0e7dcee8f7","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T01:40:11Z","title_canon_sha256":"31c42e50faee083c5d81521a364a3810f1e99963884d46dffaa766857df7aa4e"},"schema_version":"1.0","source":{"id":"2402.01981","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01981","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01981v1","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01981","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"3NDD3D2JTXJ4","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_16","alias_value":"3NDD3D2JTXJ4XW4O","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_8","alias_value":"3NDD3D2J","created_at":"2026-07-05T07:41:09Z"}],"graph_snapshots":[{"event_id":"sha256:303a284fcf3447a74a745ee0b8761eb92a767470b1bb238829b50f99c772b3c1","target":"graph","created_at":"2026-07-05T07:41:09Z","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/2402.01981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation techniques, most require modifications to the training data, model parameters, or decoding strategy, which may be infeasible without access to a trainable model. In this work, we leverage the zero-shot capabilities of LLMs to reduce stereotyping in a technique we introduce as zero-shot self-debiasing. With two approaches, self-debiasing via explanation and s","authors_text":"Franck Dernoncourt, Hanieh Deilamsalehy, Isabel O. Gallegos, Joe Barrow, Md Mehrab Tanjim, Ruiyi Zhang, Ryan A. Rossi, Sungchul Kim, Tong Yu","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T01:40:11Z","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01981","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":"sha256:919ec4c97d1bdc06910495eb14a203b41293b2e8f5f67673610d493a40969d23","target":"record","created_at":"2026-07-05T07:41:09Z","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":"4461379cdc8fd95a2ab18a6e5c5c15882920bfb81dd4f83d12b33a0e7dcee8f7","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T01:40:11Z","title_canon_sha256":"31c42e50faee083c5d81521a364a3810f1e99963884d46dffaa766857df7aa4e"},"schema_version":"1.0","source":{"id":"2402.01981","kind":"arxiv","version":1}},"canonical_sha256":"db463d8f499dd3cbdb8ea135ae263f63b2a027a044f1521d9351f1f1cf073dba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db463d8f499dd3cbdb8ea135ae263f63b2a027a044f1521d9351f1f1cf073dba","first_computed_at":"2026-07-05T07:41:09.152087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:09.152087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v5M/C58drf7lrCOh4oCDWQOllkfMEsl9VHruZKj2VKScmQscB5pWs2oeU46IxhNIMGvS3Sh2AWHe9Jshwc51AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:09.152604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01981","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:919ec4c97d1bdc06910495eb14a203b41293b2e8f5f67673610d493a40969d23","sha256:303a284fcf3447a74a745ee0b8761eb92a767470b1bb238829b50f99c772b3c1"],"state_sha256":"6355e8e32d48a5085c70a369f6713b968984395d60f1986aee504acbd550ede1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KWt7WU78ftD5xuhRsd8XS0viWto1R3TL6SYCQxvlCSCdvJxnKEu4VV6TjxruQxCPwZDh6w5KEeF36R1M8V3aDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:43:05.791877Z","bundle_sha256":"6a1ca4209ce85df30e758137a6a94337b572a247a1afbe96de71704e9cd90f46"}}