{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5RURQ7W6CUSGXL6LE37CNDJFCG","short_pith_number":"pith:5RURQ7W6","canonical_record":{"source":{"id":"2408.10608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T07:40:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30a3ec0b9cba90c9ca17a31bc18a5e525b84b4b8d6039c087765d37e5a40bed3","abstract_canon_sha256":"fbcfc9e1f98bb358bdfd0ae967c61749c1b37b442c0bf4316e221c34722cc5a6"},"schema_version":"1.0"},"canonical_sha256":"ec69187ede15246bafcb26fe268d2511b152ad17185686ef658037a340259520","source":{"kind":"arxiv","id":"2408.10608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10608","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10608v1","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10608","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"pith_short_12","alias_value":"5RURQ7W6CUSG","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"pith_short_16","alias_value":"5RURQ7W6CUSGXL6L","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"pith_short_8","alias_value":"5RURQ7W6","created_at":"2026-07-05T08:57:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5RURQ7W6CUSGXL6LE37CNDJFCG","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T07:40:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30a3ec0b9cba90c9ca17a31bc18a5e525b84b4b8d6039c087765d37e5a40bed3","abstract_canon_sha256":"fbcfc9e1f98bb358bdfd0ae967c61749c1b37b442c0bf4316e221c34722cc5a6"},"schema_version":"1.0"},"canonical_sha256":"ec69187ede15246bafcb26fe268d2511b152ad17185686ef658037a340259520","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:14.533374Z","signature_b64":"cN/jVmjf0G5KsATNpvwxTaHWCqonnvVrsedp16pgUQJsHKC5xiLxzlr2sYYb/lWnqkVN+869wxdvOXoHQ8h4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec69187ede15246bafcb26fe268d2511b152ad17185686ef658037a340259520","last_reissued_at":"2026-07-05T08:57:14.532927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:14.532927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10608","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":"2026-07-05T08:57:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jApu4p6jiEO55pyiuPr01dXhI3S37NyAg53IXMKB0LFS9vY41fG4K5fQVnGuKQkXSp9g5U3ojSGn2bVk8D2XAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:39:02.189277Z"},"content_sha256":"432676a57fc7135a450a3f4b24602dfddb3c5e2376a9959b4f0d6fe95c03841f","schema_version":"1.0","event_id":"sha256:432676a57fc7135a450a3f4b24602dfddb3c5e2376a9959b4f0d6fe95c03841f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5RURQ7W6CUSGXL6LE37CNDJFCG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Promoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"(2) INF Technology (Shanghai) Co., (3) Monash University, (4) Donghua University, (5) Fudan University), Chen Jue (1), Jing Pan (3), Ltd., Wei Chu (2), Xiaoyu Tan (2), Xihe Qiu (1), Yinghui Xu (5), Yongxin Deng (1), Yuan Qi (5) ((1) Shanghai University of Engineering Science, Zhijun Fang (4)","submitted_at":"2024-08-20T07:40:12Z","abstract_excerpt":"Large language models (LLMs) are trained on extensive text corpora, which inevitably include biased information. Although techniques such as Affective Alignment can mitigate some negative impacts of these biases, existing prompt-based attack methods can still extract these biases from the model's weights. Moreover, these biases frequently appear subtly when LLMs are prompted to perform identical tasks across different demographic groups, thereby camouflaging their presence. To address this issue, we have formally defined the implicit bias problem and developed an innovative framework for bias "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10608","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/2408.10608/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":"2026-07-05T08:57:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ls6RvCAZ8hYozI6J2agPFfthqgqnHxqjBXD3QvkmmkeeXQRN79IveGCZFMEP8NJvXOiqA3Fd+KxzRpNtKDFuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:39:02.189824Z"},"content_sha256":"8da2a0c119f43b54b521efa72f3a132569d3891d68e0a7d7f8df0713d780413e","schema_version":"1.0","event_id":"sha256:8da2a0c119f43b54b521efa72f3a132569d3891d68e0a7d7f8df0713d780413e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RURQ7W6CUSGXL6LE37CNDJFCG/bundle.json","state_url":"https://pith.science/pith/5RURQ7W6CUSGXL6LE37CNDJFCG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RURQ7W6CUSGXL6LE37CNDJFCG/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":"2026-08-08T18:39:02Z","links":{"resolver":"https://pith.science/pith/5RURQ7W6CUSGXL6LE37CNDJFCG","bundle":"https://pith.science/pith/5RURQ7W6CUSGXL6LE37CNDJFCG/bundle.json","state":"https://pith.science/pith/5RURQ7W6CUSGXL6LE37CNDJFCG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RURQ7W6CUSGXL6LE37CNDJFCG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5RURQ7W6CUSGXL6LE37CNDJFCG","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":"fbcfc9e1f98bb358bdfd0ae967c61749c1b37b442c0bf4316e221c34722cc5a6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T07:40:12Z","title_canon_sha256":"30a3ec0b9cba90c9ca17a31bc18a5e525b84b4b8d6039c087765d37e5a40bed3"},"schema_version":"1.0","source":{"id":"2408.10608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10608","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10608v1","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10608","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"pith_short_12","alias_value":"5RURQ7W6CUSG","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"pith_short_16","alias_value":"5RURQ7W6CUSGXL6L","created_at":"2026-07-05T08:57:14Z"},{"alias_kind":"pith_short_8","alias_value":"5RURQ7W6","created_at":"2026-07-05T08:57:14Z"}],"graph_snapshots":[{"event_id":"sha256:8da2a0c119f43b54b521efa72f3a132569d3891d68e0a7d7f8df0713d780413e","target":"graph","created_at":"2026-07-05T08:57:14Z","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/2408.10608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are trained on extensive text corpora, which inevitably include biased information. Although techniques such as Affective Alignment can mitigate some negative impacts of these biases, existing prompt-based attack methods can still extract these biases from the model's weights. Moreover, these biases frequently appear subtly when LLMs are prompted to perform identical tasks across different demographic groups, thereby camouflaging their presence. To address this issue, we have formally defined the implicit bias problem and developed an innovative framework for bias ","authors_text":"(2) INF Technology (Shanghai) Co., (3) Monash University, (4) Donghua University, (5) Fudan University), Chen Jue (1), Jing Pan (3), Ltd., Wei Chu (2), Xiaoyu Tan (2), Xihe Qiu (1), Yinghui Xu (5), Yongxin Deng (1), Yuan Qi (5) ((1) Shanghai University of Engineering Science, Zhijun Fang (4)","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T07:40:12Z","title":"Promoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10608","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":"sha256:432676a57fc7135a450a3f4b24602dfddb3c5e2376a9959b4f0d6fe95c03841f","target":"record","created_at":"2026-07-05T08:57:14Z","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":"fbcfc9e1f98bb358bdfd0ae967c61749c1b37b442c0bf4316e221c34722cc5a6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T07:40:12Z","title_canon_sha256":"30a3ec0b9cba90c9ca17a31bc18a5e525b84b4b8d6039c087765d37e5a40bed3"},"schema_version":"1.0","source":{"id":"2408.10608","kind":"arxiv","version":1}},"canonical_sha256":"ec69187ede15246bafcb26fe268d2511b152ad17185686ef658037a340259520","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec69187ede15246bafcb26fe268d2511b152ad17185686ef658037a340259520","first_computed_at":"2026-07-05T08:57:14.532927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:14.532927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cN/jVmjf0G5KsATNpvwxTaHWCqonnvVrsedp16pgUQJsHKC5xiLxzlr2sYYb/lWnqkVN+869wxdvOXoHQ8h4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:14.533374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:432676a57fc7135a450a3f4b24602dfddb3c5e2376a9959b4f0d6fe95c03841f","sha256:8da2a0c119f43b54b521efa72f3a132569d3891d68e0a7d7f8df0713d780413e"],"state_sha256":"00d4e829bdb9fe97b8e4f808f58af805967023c2ee668d8ada98553a104c11b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YH67qdCiDAQKai/ZTueLcqixcsEzVr/XjXy54WuYHaf3KH3arAUYdVw59icnHIAho3XgqfAMH2bS+uThqlQ4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:39:02.195498Z","bundle_sha256":"575c2c7463b57c3c14e24e531053cc236f6f430d091b6f713621058e2db77143"}}