{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C2ZHJHWIVZVN3F2U3BQ4PQMALT","short_pith_number":"pith:C2ZHJHWI","canonical_record":{"source":{"id":"2506.11880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T15:29:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"567fe523fd713a0a4bd1ee75da49f0056e90e182cd97e153fdab5565fe205908","abstract_canon_sha256":"b48afc2bee489f60db153d81ac833ec18e4e034c045a80d20262b3a808c02075"},"schema_version":"1.0"},"canonical_sha256":"16b2749ec8ae6add9754d861c7c1805cc9028c56668c13c41c88c8ad7ebef30a","source":{"kind":"arxiv","id":"2506.11880","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11880","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11880v1","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11880","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"C2ZHJHWIVZVN","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"C2ZHJHWIVZVN3F2U","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"C2ZHJHWI","created_at":"2026-07-05T11:21:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C2ZHJHWIVZVN3F2U3BQ4PQMALT","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T15:29:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"567fe523fd713a0a4bd1ee75da49f0056e90e182cd97e153fdab5565fe205908","abstract_canon_sha256":"b48afc2bee489f60db153d81ac833ec18e4e034c045a80d20262b3a808c02075"},"schema_version":"1.0"},"canonical_sha256":"16b2749ec8ae6add9754d861c7c1805cc9028c56668c13c41c88c8ad7ebef30a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:12.207879Z","signature_b64":"t0RQGxPkl85pRe/SySnK08e4MZyDzK8iWagTsovGeqU8Qi0mbq7Xz3+Bv6qDAkbSjXsztyVamlROGXywzmWDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16b2749ec8ae6add9754d861c7c1805cc9028c56668c13c41c88c8ad7ebef30a","last_reissued_at":"2026-07-05T11:21:12.207454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:12.207454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11880","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":"2026-07-05T11:21:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6WvTMqY1aE8EgA9+72989D86AFed+ngcNAtMz2j5q6vaB37cdpxBKcHc708S0YxYyRspLbZ+jB0AyjIx8PnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:01.719780Z"},"content_sha256":"7731be689421d3e96cba0cae4834dc5562f295c2d9a70dec6504d35c662e8e3a","schema_version":"1.0","event_id":"sha256:7731be689421d3e96cba0cae4834dc5562f295c2d9a70dec6504d35c662e8e3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C2ZHJHWIVZVN3F2U3BQ4PQMALT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Alejandro Pe\\~na, Aythami Morales, Gonzalo Mancera, Julian Fierrez, Miguel Lopez, Ruben Tolosana","submitted_at":"2025-06-13T15:29:43Z","abstract_excerpt":"The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical concerns, such as demographic biases, accountability, or privacy. This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data, using a case study on AI-based automated recruitment. We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11880","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/2506.11880/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":"2026-07-05T11:21:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PJ+0khLueQ1t6XdWeOi+r+e4iVpYwKdkJfV2/SAesjnr2dxsWbkZj46qi1qTJo6ZXy+0M/dFd7icZxe1Qv0BBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:01.720286Z"},"content_sha256":"16a2a8666b8406cfb36aed30f5bb724789d51f831ef43555686272e1a7a0fe55","schema_version":"1.0","event_id":"sha256:16a2a8666b8406cfb36aed30f5bb724789d51f831ef43555686272e1a7a0fe55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2ZHJHWIVZVN3F2U3BQ4PQMALT/bundle.json","state_url":"https://pith.science/pith/C2ZHJHWIVZVN3F2U3BQ4PQMALT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2ZHJHWIVZVN3F2U3BQ4PQMALT/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":"2026-08-09T00:23:01Z","links":{"resolver":"https://pith.science/pith/C2ZHJHWIVZVN3F2U3BQ4PQMALT","bundle":"https://pith.science/pith/C2ZHJHWIVZVN3F2U3BQ4PQMALT/bundle.json","state":"https://pith.science/pith/C2ZHJHWIVZVN3F2U3BQ4PQMALT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2ZHJHWIVZVN3F2U3BQ4PQMALT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C2ZHJHWIVZVN3F2U3BQ4PQMALT","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":"b48afc2bee489f60db153d81ac833ec18e4e034c045a80d20262b3a808c02075","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T15:29:43Z","title_canon_sha256":"567fe523fd713a0a4bd1ee75da49f0056e90e182cd97e153fdab5565fe205908"},"schema_version":"1.0","source":{"id":"2506.11880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11880","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11880v1","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11880","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"C2ZHJHWIVZVN","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"C2ZHJHWIVZVN3F2U","created_at":"2026-07-05T11:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"C2ZHJHWI","created_at":"2026-07-05T11:21:12Z"}],"graph_snapshots":[{"event_id":"sha256:16a2a8666b8406cfb36aed30f5bb724789d51f831ef43555686272e1a7a0fe55","target":"graph","created_at":"2026-07-05T11:21:12Z","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/2506.11880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical concerns, such as demographic biases, accountability, or privacy. This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data, using a case study on AI-based automated recruitment. We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased ","authors_text":"Alejandro Pe\\~na, Aythami Morales, Gonzalo Mancera, Julian Fierrez, Miguel Lopez, Ruben Tolosana","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T15:29:43Z","title":"Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11880","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":"sha256:7731be689421d3e96cba0cae4834dc5562f295c2d9a70dec6504d35c662e8e3a","target":"record","created_at":"2026-07-05T11:21:12Z","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":"b48afc2bee489f60db153d81ac833ec18e4e034c045a80d20262b3a808c02075","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T15:29:43Z","title_canon_sha256":"567fe523fd713a0a4bd1ee75da49f0056e90e182cd97e153fdab5565fe205908"},"schema_version":"1.0","source":{"id":"2506.11880","kind":"arxiv","version":1}},"canonical_sha256":"16b2749ec8ae6add9754d861c7c1805cc9028c56668c13c41c88c8ad7ebef30a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16b2749ec8ae6add9754d861c7c1805cc9028c56668c13c41c88c8ad7ebef30a","first_computed_at":"2026-07-05T11:21:12.207454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:12.207454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t0RQGxPkl85pRe/SySnK08e4MZyDzK8iWagTsovGeqU8Qi0mbq7Xz3+Bv6qDAkbSjXsztyVamlROGXywzmWDDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:12.207879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7731be689421d3e96cba0cae4834dc5562f295c2d9a70dec6504d35c662e8e3a","sha256:16a2a8666b8406cfb36aed30f5bb724789d51f831ef43555686272e1a7a0fe55"],"state_sha256":"ffd86fa0335314e48b89a6ec48fa191633e5ea95f9cabfe9d818ec1b536dd20e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+K6kFwjBEqBY6aONruxGgOW1bTBNHb57i4GU+FcIuM89qkWg3u8yM2813lBBbUsAsBkg4x0SYpvZf3oBRx9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:23:01.725094Z","bundle_sha256":"b6ada2f366a3c931bc307be4fa89ebe4c4f53d5d083b19e57c84becd93ec9011"}}