{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TRWVOJE4MKPNDZ732S3WWXMNUV","short_pith_number":"pith:TRWVOJE4","canonical_record":{"source":{"id":"2406.10130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"bbf28ed7988d5f719212eb30535c5730c28db74ea6423e5955eeabe9c6d40106","abstract_canon_sha256":"197ad8778e34e306fb56afd7fda4acaa10170a8ae3ea847e4af90f93dba1fe2f"},"schema_version":"1.0"},"canonical_sha256":"9c6d57249c629ed1e7fbd4b76b5d8da542e38908215eca4376cd1a97a76f4c83","source":{"kind":"arxiv","id":"2406.10130","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10130","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10130v1","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10130","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"pith_short_12","alias_value":"TRWVOJE4MKPN","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"TRWVOJE4MKPNDZ73","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"TRWVOJE4","created_at":"2026-07-05T08:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TRWVOJE4MKPNDZ732S3WWXMNUV","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"bbf28ed7988d5f719212eb30535c5730c28db74ea6423e5955eeabe9c6d40106","abstract_canon_sha256":"197ad8778e34e306fb56afd7fda4acaa10170a8ae3ea847e4af90f93dba1fe2f"},"schema_version":"1.0"},"canonical_sha256":"9c6d57249c629ed1e7fbd4b76b5d8da542e38908215eca4376cd1a97a76f4c83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:05.840127Z","signature_b64":"PJLvcUb5abfpNygQh2bujitYWtUuBSlV3vJzjuWsHWp0AasvbG9SBD1hAfUs8MLg9GhrHmdIjmQNV6r4D7K2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c6d57249c629ed1e7fbd4b76b5d8da542e38908215eca4376cd1a97a76f4c83","last_reissued_at":"2026-07-05T08:32:05.839626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:05.839626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10130","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":"2026-07-05T08:32:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FTBIZiECno52tBxQQooG/t3Zu73al7j0D5BOPafoCnAVT87f41SFc/7hc3TmBMaaIMC6LYil9lw6c5xvOSCIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:45:10.177353Z"},"content_sha256":"b751c18b61dc9baabe8297a3a237e4f792af06e4dbe248c28a9a2fa25ebdc026","schema_version":"1.0","event_id":"sha256:b751c18b61dc9baabe8297a3a237e4f792af06e4dbe248c28a9a2fa25ebdc026"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TRWVOJE4MKPNDZ732S3WWXMNUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daoguang Zan, Min-Yen Kan, Pin-Yu Chen, Tsung-Yi Ho, Xiaokang Chen, Yan Liu, Yu Liu","submitted_at":"2024-06-14T15:41:06Z","abstract_excerpt":"Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem mainly focused on using black-box methods such as probing to detect and quantify social biases in PLMs by observing model outputs. As a result, previous debiasing methods mainly finetune or even pre-train language models on newly constructed anti-stereotypical datasets, which are high-cost. In this work, we try to unveil the mystery of social bias inside language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10130","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/2406.10130/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":"2026-07-05T08:32:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIYmLNjOr9uYJOfiH1jL0p34NAUOReBErNr4IHemD1Ww39z696x1yUzcHFmHsE3NzPsnxBk6SvREIZudiz3qAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:45:10.177840Z"},"content_sha256":"33acd2132d079fbf3e2ce6d28a7c34312489e5f3e4036fb7349eb4de0fdee18e","schema_version":"1.0","event_id":"sha256:33acd2132d079fbf3e2ce6d28a7c34312489e5f3e4036fb7349eb4de0fdee18e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRWVOJE4MKPNDZ732S3WWXMNUV/bundle.json","state_url":"https://pith.science/pith/TRWVOJE4MKPNDZ732S3WWXMNUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRWVOJE4MKPNDZ732S3WWXMNUV/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":"2026-08-04T15:45:10Z","links":{"resolver":"https://pith.science/pith/TRWVOJE4MKPNDZ732S3WWXMNUV","bundle":"https://pith.science/pith/TRWVOJE4MKPNDZ732S3WWXMNUV/bundle.json","state":"https://pith.science/pith/TRWVOJE4MKPNDZ732S3WWXMNUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRWVOJE4MKPNDZ732S3WWXMNUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TRWVOJE4MKPNDZ732S3WWXMNUV","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":"197ad8778e34e306fb56afd7fda4acaa10170a8ae3ea847e4af90f93dba1fe2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:41:06Z","title_canon_sha256":"bbf28ed7988d5f719212eb30535c5730c28db74ea6423e5955eeabe9c6d40106"},"schema_version":"1.0","source":{"id":"2406.10130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10130","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10130v1","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10130","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"pith_short_12","alias_value":"TRWVOJE4MKPN","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"TRWVOJE4MKPNDZ73","created_at":"2026-07-05T08:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"TRWVOJE4","created_at":"2026-07-05T08:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:33acd2132d079fbf3e2ce6d28a7c34312489e5f3e4036fb7349eb4de0fdee18e","target":"graph","created_at":"2026-07-05T08:32:05Z","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/2406.10130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem mainly focused on using black-box methods such as probing to detect and quantify social biases in PLMs by observing model outputs. As a result, previous debiasing methods mainly finetune or even pre-train language models on newly constructed anti-stereotypical datasets, which are high-cost. In this work, we try to unveil the mystery of social bias inside language","authors_text":"Daoguang Zan, Min-Yen Kan, Pin-Yu Chen, Tsung-Yi Ho, Xiaokang Chen, Yan Liu, Yu Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:41:06Z","title":"The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10130","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:b751c18b61dc9baabe8297a3a237e4f792af06e4dbe248c28a9a2fa25ebdc026","target":"record","created_at":"2026-07-05T08:32:05Z","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":"197ad8778e34e306fb56afd7fda4acaa10170a8ae3ea847e4af90f93dba1fe2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:41:06Z","title_canon_sha256":"bbf28ed7988d5f719212eb30535c5730c28db74ea6423e5955eeabe9c6d40106"},"schema_version":"1.0","source":{"id":"2406.10130","kind":"arxiv","version":1}},"canonical_sha256":"9c6d57249c629ed1e7fbd4b76b5d8da542e38908215eca4376cd1a97a76f4c83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c6d57249c629ed1e7fbd4b76b5d8da542e38908215eca4376cd1a97a76f4c83","first_computed_at":"2026-07-05T08:32:05.839626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:05.839626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PJLvcUb5abfpNygQh2bujitYWtUuBSlV3vJzjuWsHWp0AasvbG9SBD1hAfUs8MLg9GhrHmdIjmQNV6r4D7K2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:05.840127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b751c18b61dc9baabe8297a3a237e4f792af06e4dbe248c28a9a2fa25ebdc026","sha256:33acd2132d079fbf3e2ce6d28a7c34312489e5f3e4036fb7349eb4de0fdee18e"],"state_sha256":"9a453fc584e1462011b5cb8a40f5848b06cec56cd14748f710c29f9701e51b79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGn6nw/CbGLvJeJ3LgIhI7ttpQ2A+qyL3mpTM8VUQ4eVVnv+SOB7wZwXE7PwNwnHFXqknCT54cnp74TgkN/QBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:45:10.181657Z","bundle_sha256":"9b1a6c394056e73dee90509cad437a08ff9e4e00b231e213575092afcc20f3b4"}}