{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TA5GXZTHPQKVCDAEQGAWO326OR","short_pith_number":"pith:TA5GXZTH","schema_version":"1.0","canonical_sha256":"983a6be6677c15510c048181676f5e7451cda8328371f74e0e27f4c066255fbb","source":{"kind":"arxiv","id":"2507.02966","version":2},"attestation_state":"computed","paper":{"title":"PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alejandro Penna, Alvaro Ortigosa, Aythami Morales, Francisco Jurado, Gonzalo Mancera, Julian Fierrez, Miguel Lopez-Duran, Ruben Tolosana","submitted_at":"2025-06-30T14:42:49Z","abstract_excerpt":"The use of Natural Language Processing (NLP) in highstakes AI-based applications has increased significantly in recent years, especially since the emergence of Large Language Models (LLMs). However, despite their strong performance, LLMs introduce important legal/ ethical concerns, particularly regarding privacy, data protection, and transparency. Due to these concerns, this work explores the use of Named- Entity Recognition (NER) to facilitate the privacy-preserving training (or adaptation) of LLMs. We propose a framework that uses NER technologies to anonymize sensitive information in text d"},"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":"2507.02966","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T14:42:49Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"d25289bf8e914918266e638d2edd42d1a3d3c04c8c08feb078e789cabf0cb4d0","abstract_canon_sha256":"4474d058e1effb293e3b113a5c1ac728690ff4f792e1496d6e9c918e47948524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:11.174568Z","signature_b64":"INeO1oAIR4f9TK7Ojp+NCgNQ00x+/ZI35ENn1/3T9wCqsONE9ZUD+LMq1U0QJsUs6VIpRibOnPyFVhb1kS+PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"983a6be6677c15510c048181676f5e7451cda8328371f74e0e27f4c066255fbb","last_reissued_at":"2026-07-05T11:34:11.174099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:11.174099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alejandro Penna, Alvaro Ortigosa, Aythami Morales, Francisco Jurado, Gonzalo Mancera, Julian Fierrez, Miguel Lopez-Duran, Ruben Tolosana","submitted_at":"2025-06-30T14:42:49Z","abstract_excerpt":"The use of Natural Language Processing (NLP) in highstakes AI-based applications has increased significantly in recent years, especially since the emergence of Large Language Models (LLMs). However, despite their strong performance, LLMs introduce important legal/ ethical concerns, particularly regarding privacy, data protection, and transparency. Due to these concerns, this work explores the use of Named- Entity Recognition (NER) to facilitate the privacy-preserving training (or adaptation) of LLMs. We propose a framework that uses NER technologies to anonymize sensitive information in text d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02966","kind":"arxiv","version":2},"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/2507.02966/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":"2507.02966","created_at":"2026-07-05T11:34:11.174156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02966v2","created_at":"2026-07-05T11:34:11.174156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02966","created_at":"2026-07-05T11:34:11.174156+00:00"},{"alias_kind":"pith_short_12","alias_value":"TA5GXZTHPQKV","created_at":"2026-07-05T11:34:11.174156+00:00"},{"alias_kind":"pith_short_16","alias_value":"TA5GXZTHPQKVCDAE","created_at":"2026-07-05T11:34:11.174156+00:00"},{"alias_kind":"pith_short_8","alias_value":"TA5GXZTH","created_at":"2026-07-05T11:34:11.174156+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/TA5GXZTHPQKVCDAEQGAWO326OR","json":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR.json","graph_json":"https://pith.science/api/pith-number/TA5GXZTHPQKVCDAEQGAWO326OR/graph.json","events_json":"https://pith.science/api/pith-number/TA5GXZTHPQKVCDAEQGAWO326OR/events.json","paper":"https://pith.science/paper/TA5GXZTH"},"agent_actions":{"view_html":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR","download_json":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR.json","view_paper":"https://pith.science/paper/TA5GXZTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02966&json=true","fetch_graph":"https://pith.science/api/pith-number/TA5GXZTHPQKVCDAEQGAWO326OR/graph.json","fetch_events":"https://pith.science/api/pith-number/TA5GXZTHPQKVCDAEQGAWO326OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR/action/storage_attestation","attest_author":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR/action/author_attestation","sign_citation":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR/action/citation_signature","submit_replication":"https://pith.science/pith/TA5GXZTHPQKVCDAEQGAWO326OR/action/replication_record"}},"created_at":"2026-07-05T11:34:11.174156+00:00","updated_at":"2026-07-05T11:34:11.174156+00:00"}