{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J3PCFLAZLQDDFDGLXHTUO4JVJ3","short_pith_number":"pith:J3PCFLAZ","canonical_record":{"source":{"id":"2307.10522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-20T01:48:51Z","cross_cats_sorted":[],"title_canon_sha256":"e23712967e0867857f3c46dbdaafe5deaf9d238c057e4556255ebc78570bd81e","abstract_canon_sha256":"e968813ddef4a270485b19e4fe56cb3bba33c17fdb0dc2fb87949dd34bd243a3"},"schema_version":"1.0"},"canonical_sha256":"4ede22ac195c06328ccbb9e74771354ec154cf12ec22eb6d0e58796fedc7f84c","source":{"kind":"arxiv","id":"2307.10522","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10522","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10522v1","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10522","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"pith_short_12","alias_value":"J3PCFLAZLQDD","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"pith_short_16","alias_value":"J3PCFLAZLQDDFDGL","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"pith_short_8","alias_value":"J3PCFLAZ","created_at":"2026-07-05T06:33:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J3PCFLAZLQDDFDGLXHTUO4JVJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2307.10522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-20T01:48:51Z","cross_cats_sorted":[],"title_canon_sha256":"e23712967e0867857f3c46dbdaafe5deaf9d238c057e4556255ebc78570bd81e","abstract_canon_sha256":"e968813ddef4a270485b19e4fe56cb3bba33c17fdb0dc2fb87949dd34bd243a3"},"schema_version":"1.0"},"canonical_sha256":"4ede22ac195c06328ccbb9e74771354ec154cf12ec22eb6d0e58796fedc7f84c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:47.826178Z","signature_b64":"R2oV/R4EMC+o1bIZQ4Nl9dtL4LtO1fsWNcf+dBdoebTHLUGuNWXQ44jGdf/p0KBs7sok7Ta/Cyluqw/l+gyZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ede22ac195c06328ccbb9e74771354ec154cf12ec22eb6d0e58796fedc7f84c","last_reissued_at":"2026-07-05T06:33:47.825692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:47.825692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.10522","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":"2026-07-05T06:33:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RWfgdFATukM1jv6NycTp7wU0CCEcI4u2ebZwXIc4amD0sZum8Y772EARihbv++NMyjcQe9H7z5g2C6p+htSOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:37:59.566122Z"},"content_sha256":"6c3b5c99adcedc29561bc948ec32e995719a00a48cc41a1a49ed19547cce1022","schema_version":"1.0","event_id":"sha256:6c3b5c99adcedc29561bc948ec32e995719a00a48cc41a1a49ed19547cce1022"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J3PCFLAZLQDDFDGLXHTUO4JVJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hamed Khanpour, Hamid Palangi, Radames Cruz Moreno, Somayeh Ghanbarzadeh, Yan Huang","submitted_at":"2023-07-20T01:48:51Z","abstract_excerpt":"Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for debiasing, which are resource-intensive and costly. Furthermore, these methods hurt the PLMs' performance on downstream tasks. In this study, we propose Gender-tuning, which debiases the PLMs through fine-tuning on downstream tasks' datasets. For this aim, Gender-tuning integrates Masked Language Modeling (MLM) training objectives into fine-tuning's training proces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10522","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/2307.10522/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":"2026-07-05T06:33:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"115UNr44lKmBMWtSCgZBQYcoyzAaojjyVQ9gl7rEnyFF3dM6j2jOs0fa8K3tlqHYADTatjUatki69pfumpwKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:37:59.566500Z"},"content_sha256":"6dac55f2d56d1d361098761fe41d584d705ece120afbb1abec770f95c9554840","schema_version":"1.0","event_id":"sha256:6dac55f2d56d1d361098761fe41d584d705ece120afbb1abec770f95c9554840"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3PCFLAZLQDDFDGLXHTUO4JVJ3/bundle.json","state_url":"https://pith.science/pith/J3PCFLAZLQDDFDGLXHTUO4JVJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3PCFLAZLQDDFDGLXHTUO4JVJ3/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":"2026-07-11T15:37:59Z","links":{"resolver":"https://pith.science/pith/J3PCFLAZLQDDFDGLXHTUO4JVJ3","bundle":"https://pith.science/pith/J3PCFLAZLQDDFDGLXHTUO4JVJ3/bundle.json","state":"https://pith.science/pith/J3PCFLAZLQDDFDGLXHTUO4JVJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3PCFLAZLQDDFDGLXHTUO4JVJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J3PCFLAZLQDDFDGLXHTUO4JVJ3","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":"e968813ddef4a270485b19e4fe56cb3bba33c17fdb0dc2fb87949dd34bd243a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-20T01:48:51Z","title_canon_sha256":"e23712967e0867857f3c46dbdaafe5deaf9d238c057e4556255ebc78570bd81e"},"schema_version":"1.0","source":{"id":"2307.10522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10522","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10522v1","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10522","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"pith_short_12","alias_value":"J3PCFLAZLQDD","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"pith_short_16","alias_value":"J3PCFLAZLQDDFDGL","created_at":"2026-07-05T06:33:47Z"},{"alias_kind":"pith_short_8","alias_value":"J3PCFLAZ","created_at":"2026-07-05T06:33:47Z"}],"graph_snapshots":[{"event_id":"sha256:6dac55f2d56d1d361098761fe41d584d705ece120afbb1abec770f95c9554840","target":"graph","created_at":"2026-07-05T06:33:47Z","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/2307.10522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for debiasing, which are resource-intensive and costly. Furthermore, these methods hurt the PLMs' performance on downstream tasks. In this study, we propose Gender-tuning, which debiases the PLMs through fine-tuning on downstream tasks' datasets. For this aim, Gender-tuning integrates Masked Language Modeling (MLM) training objectives into fine-tuning's training proces","authors_text":"Hamed Khanpour, Hamid Palangi, Radames Cruz Moreno, Somayeh Ghanbarzadeh, Yan Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-20T01:48:51Z","title":"Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10522","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":"sha256:6c3b5c99adcedc29561bc948ec32e995719a00a48cc41a1a49ed19547cce1022","target":"record","created_at":"2026-07-05T06:33:47Z","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":"e968813ddef4a270485b19e4fe56cb3bba33c17fdb0dc2fb87949dd34bd243a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-20T01:48:51Z","title_canon_sha256":"e23712967e0867857f3c46dbdaafe5deaf9d238c057e4556255ebc78570bd81e"},"schema_version":"1.0","source":{"id":"2307.10522","kind":"arxiv","version":1}},"canonical_sha256":"4ede22ac195c06328ccbb9e74771354ec154cf12ec22eb6d0e58796fedc7f84c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ede22ac195c06328ccbb9e74771354ec154cf12ec22eb6d0e58796fedc7f84c","first_computed_at":"2026-07-05T06:33:47.825692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:47.825692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R2oV/R4EMC+o1bIZQ4Nl9dtL4LtO1fsWNcf+dBdoebTHLUGuNWXQ44jGdf/p0KBs7sok7Ta/Cyluqw/l+gyZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:47.826178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.10522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c3b5c99adcedc29561bc948ec32e995719a00a48cc41a1a49ed19547cce1022","sha256:6dac55f2d56d1d361098761fe41d584d705ece120afbb1abec770f95c9554840"],"state_sha256":"3f35fefa15bdc4fb057b7c1ec1e99ed495e3afef051dda5183d2f74e037b73f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UfiJiafgQV+Bb6FL8Gxb0VwLWatmLr+nheUy3V67pjIqbDF0agPW3ddQGski1kkBE0+ysXner4CTADlbOnDSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T15:37:59.568590Z","bundle_sha256":"9b0b498d5efc347c6ce1aec1df7298a3b0c1c242ff447e1d5cbacca9f092bcc1"}}