{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5UQZBDOJYWYGW6R5XOXQTBSQUP","short_pith_number":"pith:5UQZBDOJ","canonical_record":{"source":{"id":"2310.12490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T05:49:58Z","cross_cats_sorted":[],"title_canon_sha256":"fb93fff329658de33b9dd968b7a99b49ac7b562e7f0fc99d02b50a31f07f8750","abstract_canon_sha256":"997813f49c4d59a873665635c81dede9d1e3feec5fea2e3a2ed35c37e582b8e7"},"schema_version":"1.0"},"canonical_sha256":"ed21908dc9c5b06b7a3dbbaf098650a3fc0a15dd88a48d71a93ffc92e232c857","source":{"kind":"arxiv","id":"2310.12490","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12490","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12490v1","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12490","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"5UQZBDOJYWYG","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"5UQZBDOJYWYGW6R5","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"5UQZBDOJ","created_at":"2026-07-05T07:02:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5UQZBDOJYWYGW6R5XOXQTBSQUP","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T05:49:58Z","cross_cats_sorted":[],"title_canon_sha256":"fb93fff329658de33b9dd968b7a99b49ac7b562e7f0fc99d02b50a31f07f8750","abstract_canon_sha256":"997813f49c4d59a873665635c81dede9d1e3feec5fea2e3a2ed35c37e582b8e7"},"schema_version":"1.0"},"canonical_sha256":"ed21908dc9c5b06b7a3dbbaf098650a3fc0a15dd88a48d71a93ffc92e232c857","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:38.877518Z","signature_b64":"WJM4AFfd1ASVAIrM3N4Bi9SXWodsHZOG79uaK6Tyy1Sj3HKcadSuiQsqijUbayTTVQ62KrKs6wACE4KBnrp2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed21908dc9c5b06b7a3dbbaf098650a3fc0a15dd88a48d71a93ffc92e232c857","last_reissued_at":"2026-07-05T07:02:38.877023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:38.877023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12490","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":"2026-07-05T07:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eN2MfSKxfN8Weyy/9+tBcLjdPbLzS65z9E+ZjleUIucAjiPV+79pm4XmCYM45ml7mTjfbiMCdrsKXpPStBefBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:44:30.164834Z"},"content_sha256":"13f834fdfb57fc1f9b003485993302bc8677063c8cbefb1712bf647befd83818","schema_version":"1.0","event_id":"sha256:13f834fdfb57fc1f9b003485993302bc8677063c8cbefb1712bf647befd83818"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5UQZBDOJYWYGW6R5XOXQTBSQUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James Caverlee, Maria Teleki, Xiangjue Dong, Zhuoer Wang, Ziwei Zhu","submitted_at":"2023-10-19T05:49:58Z","abstract_excerpt":"Pre-trained Language Models are widely used in many important real-world applications. However, recent studies show that these models can encode social biases from large pre-training corpora and even amplify biases in downstream applications. To address this challenge, we propose Co$^2$PT, an efficient and effective debias-while-prompt tuning method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks. Our experiments conducted on three extrinsic bias benchmarks demonstrate the effectiveness of Co$^2$PT on bias mitigation during the prompt tuning process and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12490","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/2310.12490/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":"2026-07-05T07:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdQAc2Mc8tmp+QXVP5fq4drBi+nH9XrcrI+AX+r+pfpc/o5r0fT/z2u8LBUoxf7aIwa1OAbcSvu/WJGOUyQFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:44:30.165222Z"},"content_sha256":"190144f38695388e6e69c7aff3697c941bca41779630a2d1d1372fb1e3dd2793","schema_version":"1.0","event_id":"sha256:190144f38695388e6e69c7aff3697c941bca41779630a2d1d1372fb1e3dd2793"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UQZBDOJYWYGW6R5XOXQTBSQUP/bundle.json","state_url":"https://pith.science/pith/5UQZBDOJYWYGW6R5XOXQTBSQUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UQZBDOJYWYGW6R5XOXQTBSQUP/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":"2026-08-21T00:44:30Z","links":{"resolver":"https://pith.science/pith/5UQZBDOJYWYGW6R5XOXQTBSQUP","bundle":"https://pith.science/pith/5UQZBDOJYWYGW6R5XOXQTBSQUP/bundle.json","state":"https://pith.science/pith/5UQZBDOJYWYGW6R5XOXQTBSQUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UQZBDOJYWYGW6R5XOXQTBSQUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5UQZBDOJYWYGW6R5XOXQTBSQUP","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":"997813f49c4d59a873665635c81dede9d1e3feec5fea2e3a2ed35c37e582b8e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T05:49:58Z","title_canon_sha256":"fb93fff329658de33b9dd968b7a99b49ac7b562e7f0fc99d02b50a31f07f8750"},"schema_version":"1.0","source":{"id":"2310.12490","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12490","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12490v1","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12490","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"5UQZBDOJYWYG","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"5UQZBDOJYWYGW6R5","created_at":"2026-07-05T07:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"5UQZBDOJ","created_at":"2026-07-05T07:02:38Z"}],"graph_snapshots":[{"event_id":"sha256:190144f38695388e6e69c7aff3697c941bca41779630a2d1d1372fb1e3dd2793","target":"graph","created_at":"2026-07-05T07:02:38Z","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/2310.12490/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Language Models are widely used in many important real-world applications. However, recent studies show that these models can encode social biases from large pre-training corpora and even amplify biases in downstream applications. To address this challenge, we propose Co$^2$PT, an efficient and effective debias-while-prompt tuning method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks. Our experiments conducted on three extrinsic bias benchmarks demonstrate the effectiveness of Co$^2$PT on bias mitigation during the prompt tuning process and i","authors_text":"James Caverlee, Maria Teleki, Xiangjue Dong, Zhuoer Wang, Ziwei Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T05:49:58Z","title":"Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12490","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":"sha256:13f834fdfb57fc1f9b003485993302bc8677063c8cbefb1712bf647befd83818","target":"record","created_at":"2026-07-05T07:02:38Z","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":"997813f49c4d59a873665635c81dede9d1e3feec5fea2e3a2ed35c37e582b8e7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T05:49:58Z","title_canon_sha256":"fb93fff329658de33b9dd968b7a99b49ac7b562e7f0fc99d02b50a31f07f8750"},"schema_version":"1.0","source":{"id":"2310.12490","kind":"arxiv","version":1}},"canonical_sha256":"ed21908dc9c5b06b7a3dbbaf098650a3fc0a15dd88a48d71a93ffc92e232c857","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed21908dc9c5b06b7a3dbbaf098650a3fc0a15dd88a48d71a93ffc92e232c857","first_computed_at":"2026-07-05T07:02:38.877023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:38.877023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WJM4AFfd1ASVAIrM3N4Bi9SXWodsHZOG79uaK6Tyy1Sj3HKcadSuiQsqijUbayTTVQ62KrKs6wACE4KBnrp2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:38.877518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12490","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13f834fdfb57fc1f9b003485993302bc8677063c8cbefb1712bf647befd83818","sha256:190144f38695388e6e69c7aff3697c941bca41779630a2d1d1372fb1e3dd2793"],"state_sha256":"1d0756c5d81bc2ccfc7c441673acbec37690dc7cff1491c865422fa7e80811cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tWK2DXZgjLvNy9xGd53wQck0Fo9s5BycuHWn6zLzZvLipCw2/BKh9mWEcIkeJR35LSb2J8bJ4X0a4AW96ButAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T00:44:30.167453Z","bundle_sha256":"8b31e10144a2c1de6977c469c0bcb3db4fe2a5981fe83172c3662372ccec4786"}}