{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TDVA2IKRK7BOFRCCWLEDTBQM2H","short_pith_number":"pith:TDVA2IKR","schema_version":"1.0","canonical_sha256":"98ea0d215157c2e2c442b2c839860cd1cedfee3803d2c3684ca07909c73c7cc1","source":{"kind":"arxiv","id":"2508.12158","version":1},"attestation_state":"computed","paper":{"title":"LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Klymenko, Florian Matthes, Stephen Meisenbacher","submitted_at":"2025-08-16T20:49:41Z","abstract_excerpt":"Despite advances in the field of privacy-preserving Natural Language Processing (NLP), a significant challenge remains the accurate evaluation of privacy. As a potential solution, using LLMs as a privacy evaluator presents a promising approach $\\unicode{x2013}$ a strategy inspired by its success in other subfields of NLP. In particular, the so-called $\\textit{LLM-as-a-Judge}$ paradigm has achieved impressive results on a variety of natural language evaluation tasks, demonstrating high agreement rates with human annotators. Recognizing that privacy is both subjective and difficult to define, we"},"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":"2508.12158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-16T20:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"86525d97d6c81a50dc4dabcaa296fa1c32420b975b6d24f2662f93fd8060380e","abstract_canon_sha256":"8ae746c044c175c9e41d6da182dc7a5fb9e689b81361e983a14b7297edf7ccea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:00.994637Z","signature_b64":"E49LMa1CRUbLonWf28qWPbpUMyKBmPhbRdAZkP1K9xrjj9ovYL7yYDFYmQ0Dq3ydfBQLegrV0VsP/3U3h/Q6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ea0d215157c2e2c442b2c839860cd1cedfee3803d2c3684ca07909c73c7cc1","last_reissued_at":"2026-07-05T11:55:00.994258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:00.994258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Klymenko, Florian Matthes, Stephen Meisenbacher","submitted_at":"2025-08-16T20:49:41Z","abstract_excerpt":"Despite advances in the field of privacy-preserving Natural Language Processing (NLP), a significant challenge remains the accurate evaluation of privacy. As a potential solution, using LLMs as a privacy evaluator presents a promising approach $\\unicode{x2013}$ a strategy inspired by its success in other subfields of NLP. In particular, the so-called $\\textit{LLM-as-a-Judge}$ paradigm has achieved impressive results on a variety of natural language evaluation tasks, demonstrating high agreement rates with human annotators. Recognizing that privacy is both subjective and difficult to define, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12158","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/2508.12158/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":"2508.12158","created_at":"2026-07-05T11:55:00.994324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12158v1","created_at":"2026-07-05T11:55:00.994324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12158","created_at":"2026-07-05T11:55:00.994324+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDVA2IKRK7BO","created_at":"2026-07-05T11:55:00.994324+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDVA2IKRK7BOFRCC","created_at":"2026-07-05T11:55:00.994324+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDVA2IKR","created_at":"2026-07-05T11:55:00.994324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20284","citing_title":"Can LLMs Make (Personalized) Access Control Decisions?","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20284","citing_title":"Can LLMs Make (Personalized) Access Control Decisions?","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H","json":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H.json","graph_json":"https://pith.science/api/pith-number/TDVA2IKRK7BOFRCCWLEDTBQM2H/graph.json","events_json":"https://pith.science/api/pith-number/TDVA2IKRK7BOFRCCWLEDTBQM2H/events.json","paper":"https://pith.science/paper/TDVA2IKR"},"agent_actions":{"view_html":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H","download_json":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H.json","view_paper":"https://pith.science/paper/TDVA2IKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12158&json=true","fetch_graph":"https://pith.science/api/pith-number/TDVA2IKRK7BOFRCCWLEDTBQM2H/graph.json","fetch_events":"https://pith.science/api/pith-number/TDVA2IKRK7BOFRCCWLEDTBQM2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H/action/storage_attestation","attest_author":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H/action/author_attestation","sign_citation":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H/action/citation_signature","submit_replication":"https://pith.science/pith/TDVA2IKRK7BOFRCCWLEDTBQM2H/action/replication_record"}},"created_at":"2026-07-05T11:55:00.994324+00:00","updated_at":"2026-07-05T11:55:00.994324+00:00"}