{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NAXP2YOKZM66FYJPC52J6UIAXL","short_pith_number":"pith:NAXP2YOK","schema_version":"1.0","canonical_sha256":"682efd61cacb3de2e12f17749f5100bacf8be224e4ae9e3b904679c1bc2de3e0","source":{"kind":"arxiv","id":"2505.03529","version":2},"attestation_state":"computed","paper":{"title":"SKALD: Scalable K-Anonymisation for Large Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CR","math.IT"],"primary_cat":"cs.IT","authors_text":"Amogh Dharmavaram, Anshoo Tandon, Kailash Reddy, Novoneel Chakraborty","submitted_at":"2025-05-06T13:38:53Z","abstract_excerpt":"Data privacy and anonymisation are critical concerns in today's data-driven society, particularly when handling personal and sensitive user data. Regulatory frameworks worldwide recommend privacy-preserving protocols such as k-anonymisation to de-identify releases of tabular data. Available hardware resources provide an upper bound on the maximum size of dataset that can be processed at a time. Large datasets with sizes exceeding this upper bound must be broken up into smaller data chunks for processing. In these cases, standard k-anonymisation tools such as ARX can only operate on a per-chunk"},"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":"2505.03529","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IT","submitted_at":"2025-05-06T13:38:53Z","cross_cats_sorted":["cs.CR","math.IT"],"title_canon_sha256":"77a614d6ca0f4fc7cb6e649658e0d1b0a2d38f233b51d7227a6ce22aaa360a8e","abstract_canon_sha256":"0467bc74add186191b4bfda3357470c27e8fe46e0d3925d92d8d5fe4cb5b0f79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:59.270253Z","signature_b64":"p1w8/0JRIxAEga7RKLJ3+EtLeWRDp4tcZbs5PiEfuYiyBI0DTnUyhwy1iI3oYgAZMnChm+n8h51jFm4basWeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682efd61cacb3de2e12f17749f5100bacf8be224e4ae9e3b904679c1bc2de3e0","last_reissued_at":"2026-07-05T11:29:59.269851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:59.269851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SKALD: Scalable K-Anonymisation for Large Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CR","math.IT"],"primary_cat":"cs.IT","authors_text":"Amogh Dharmavaram, Anshoo Tandon, Kailash Reddy, Novoneel Chakraborty","submitted_at":"2025-05-06T13:38:53Z","abstract_excerpt":"Data privacy and anonymisation are critical concerns in today's data-driven society, particularly when handling personal and sensitive user data. Regulatory frameworks worldwide recommend privacy-preserving protocols such as k-anonymisation to de-identify releases of tabular data. Available hardware resources provide an upper bound on the maximum size of dataset that can be processed at a time. Large datasets with sizes exceeding this upper bound must be broken up into smaller data chunks for processing. In these cases, standard k-anonymisation tools such as ARX can only operate on a per-chunk"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03529","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/2505.03529/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":"2505.03529","created_at":"2026-07-05T11:29:59.269904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03529v2","created_at":"2026-07-05T11:29:59.269904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03529","created_at":"2026-07-05T11:29:59.269904+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAXP2YOKZM66","created_at":"2026-07-05T11:29:59.269904+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAXP2YOKZM66FYJP","created_at":"2026-07-05T11:29:59.269904+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAXP2YOK","created_at":"2026-07-05T11:29:59.269904+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/NAXP2YOKZM66FYJPC52J6UIAXL","json":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL.json","graph_json":"https://pith.science/api/pith-number/NAXP2YOKZM66FYJPC52J6UIAXL/graph.json","events_json":"https://pith.science/api/pith-number/NAXP2YOKZM66FYJPC52J6UIAXL/events.json","paper":"https://pith.science/paper/NAXP2YOK"},"agent_actions":{"view_html":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL","download_json":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL.json","view_paper":"https://pith.science/paper/NAXP2YOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03529&json=true","fetch_graph":"https://pith.science/api/pith-number/NAXP2YOKZM66FYJPC52J6UIAXL/graph.json","fetch_events":"https://pith.science/api/pith-number/NAXP2YOKZM66FYJPC52J6UIAXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL/action/storage_attestation","attest_author":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL/action/author_attestation","sign_citation":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL/action/citation_signature","submit_replication":"https://pith.science/pith/NAXP2YOKZM66FYJPC52J6UIAXL/action/replication_record"}},"created_at":"2026-07-05T11:29:59.269904+00:00","updated_at":"2026-07-05T11:29:59.269904+00:00"}