{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CJEGRICZY52T4MQV7HOLIFR53R","short_pith_number":"pith:CJEGRICZ","schema_version":"1.0","canonical_sha256":"124868a059c7753e3215f9dcb4163ddc7874fbcabf6a9fdaaca2fb94f4ddeb7a","source":{"kind":"arxiv","id":"2607.28319","version":1},"attestation_state":"computed","paper":{"title":"Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alfonso Ure\\~na L\\'opez, Eugenio Mart\\'inez C\\'amara, Pere Martra","submitted_at":"2026-07-30T14:54:33Z","abstract_excerpt":"This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical validation of this method, this work focuses on causal bias localization. Using minimally contrastive prompt pairs and inference-time activation capture, the method identifies neurons that react differentially when processing demographic attributes in GLU architectures, evaluating the signal at the down_proj input. Empirical evaluation was conducted on models of up to 3 billion parame"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.28319","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T14:54:33Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"9e5991f17b9bc6e881745e84560e72e1117517aad133feddabb79ea2201adf77","abstract_canon_sha256":"303fc48d0b46a0673ef2148621d57d51ab9f6ec75b0f53f5003b8356e88ab9cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"124868a059c7753e3215f9dcb4163ddc7874fbcabf6a9fdaaca2fb94f4ddeb7a","last_reissued_at":"2026-07-31T01:37:13.756269Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:13.756269Z"},"graph_snapshot":{"paper":{"title":"Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alfonso Ure\\~na L\\'opez, Eugenio Mart\\'inez C\\'amara, Pere Martra","submitted_at":"2026-07-30T14:54:33Z","abstract_excerpt":"This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical validation of this method, this work focuses on causal bias localization. Using minimally contrastive prompt pairs and inference-time activation capture, the method identifies neurons that react differentially when processing demographic attributes in GLU architectures, evaluating the signal at the down_proj input. Empirical evaluation was conducted on models of up to 3 billion parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28319","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/2607.28319/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.28319","created_at":"2026-07-31T01:37:13.759789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28319v1","created_at":"2026-07-31T01:37:13.759789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28319","created_at":"2026-07-31T01:37:13.759789+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJEGRICZY52T","created_at":"2026-07-31T01:37:13.759789+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJEGRICZY52T4MQV","created_at":"2026-07-31T01:37:13.759789+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJEGRICZ","created_at":"2026-07-31T01:37:13.759789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R","json":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R.json","graph_json":"https://pith.science/api/pith-number/CJEGRICZY52T4MQV7HOLIFR53R/graph.json","events_json":"https://pith.science/api/pith-number/CJEGRICZY52T4MQV7HOLIFR53R/events.json","paper":"https://pith.science/paper/CJEGRICZ"},"agent_actions":{"view_html":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R","download_json":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R.json","view_paper":"https://pith.science/paper/CJEGRICZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28319&json=true","fetch_graph":"https://pith.science/api/pith-number/CJEGRICZY52T4MQV7HOLIFR53R/graph.json","fetch_events":"https://pith.science/api/pith-number/CJEGRICZY52T4MQV7HOLIFR53R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R/action/storage_attestation","attest_author":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R/action/author_attestation","sign_citation":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R/action/citation_signature","submit_replication":"https://pith.science/pith/CJEGRICZY52T4MQV7HOLIFR53R/action/replication_record"}},"created_at":"2026-07-31T01:37:13.759789+00:00","updated_at":"2026-07-31T01:37:13.759789+00:00"}