{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:43E5TO2W5PXX3GJRRZMO7TM6KN","short_pith_number":"pith:43E5TO2W","schema_version":"1.0","canonical_sha256":"e6c9d9bb56ebef7d99318e58efcd9e5345878d3d2ec8634316cc4f03cf43c5d2","source":{"kind":"arxiv","id":"2606.19881","version":1},"attestation_state":"computed","paper":{"title":"REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ajita Dash, Anubha Agrawal, Bharadwaj Y M G, Guneesh Vats, Praison Selvaraj, Ranga Prasad Chenna, Shikha Singhal, Vidhan Jhawar","submitted_at":"2026-06-18T07:38:15Z","abstract_excerpt":"Benchmark infrastructure for personally identifiable information (PII) detection remains limited: existing corpora cover few entity types, use ad hoc generation conditions, and do not show which surface conditions cause detector failures. We present REDACT, a systematically controlled multilingual PII benchmark with 13,427 records, 324,078 entity annotations, 51 entity types, 4,127 surface-form patterns, and 25 languages across 9 scripts. A strength-2 covering-array sampler controls nine generation axes: domain, format, difficulty, length, density, code-switching, language, adjacency, and co-o"},"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":"2606.19881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T07:38:15Z","cross_cats_sorted":[],"title_canon_sha256":"31086b14e34edde69709818fc8f308c32034bf7493b8a5a9a329ef847e3bdd69","abstract_canon_sha256":"c7a9eadd7a99885c1bf09e2f6994883ab83a06fc7bff0ff597623728deedbf24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:37.693739Z","signature_b64":"kAzHfAnqaD1L23zTwwqESaYVa3ArG8TH5CQvDmB8KX5csCd2tDj7ULa1D1IoGhwxYLLitLu9txobtDX7gINbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6c9d9bb56ebef7d99318e58efcd9e5345878d3d2ec8634316cc4f03cf43c5d2","last_reissued_at":"2026-06-19T16:12:37.693391Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:37.693391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ajita Dash, Anubha Agrawal, Bharadwaj Y M G, Guneesh Vats, Praison Selvaraj, Ranga Prasad Chenna, Shikha Singhal, Vidhan Jhawar","submitted_at":"2026-06-18T07:38:15Z","abstract_excerpt":"Benchmark infrastructure for personally identifiable information (PII) detection remains limited: existing corpora cover few entity types, use ad hoc generation conditions, and do not show which surface conditions cause detector failures. We present REDACT, a systematically controlled multilingual PII benchmark with 13,427 records, 324,078 entity annotations, 51 entity types, 4,127 surface-form patterns, and 25 languages across 9 scripts. A strength-2 covering-array sampler controls nine generation axes: domain, format, difficulty, length, density, code-switching, language, adjacency, and co-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19881","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/2606.19881/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":"2606.19881","created_at":"2026-06-19T16:12:37.693453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19881v1","created_at":"2026-06-19T16:12:37.693453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19881","created_at":"2026-06-19T16:12:37.693453+00:00"},{"alias_kind":"pith_short_12","alias_value":"43E5TO2W5PXX","created_at":"2026-06-19T16:12:37.693453+00:00"},{"alias_kind":"pith_short_16","alias_value":"43E5TO2W5PXX3GJR","created_at":"2026-06-19T16:12:37.693453+00:00"},{"alias_kind":"pith_short_8","alias_value":"43E5TO2W","created_at":"2026-06-19T16:12:37.693453+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/43E5TO2W5PXX3GJRRZMO7TM6KN","json":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN.json","graph_json":"https://pith.science/api/pith-number/43E5TO2W5PXX3GJRRZMO7TM6KN/graph.json","events_json":"https://pith.science/api/pith-number/43E5TO2W5PXX3GJRRZMO7TM6KN/events.json","paper":"https://pith.science/paper/43E5TO2W"},"agent_actions":{"view_html":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN","download_json":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN.json","view_paper":"https://pith.science/paper/43E5TO2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19881&json=true","fetch_graph":"https://pith.science/api/pith-number/43E5TO2W5PXX3GJRRZMO7TM6KN/graph.json","fetch_events":"https://pith.science/api/pith-number/43E5TO2W5PXX3GJRRZMO7TM6KN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN/action/storage_attestation","attest_author":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN/action/author_attestation","sign_citation":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN/action/citation_signature","submit_replication":"https://pith.science/pith/43E5TO2W5PXX3GJRRZMO7TM6KN/action/replication_record"}},"created_at":"2026-06-19T16:12:37.693453+00:00","updated_at":"2026-06-19T16:12:37.693453+00:00"}