{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PMAYFHGEPLWFC6EQJLXU2ZWUNN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"489002cd66a880d72a014c44cab034d05e839490cc4931db8e179fa9ee2f3c24","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-11-26T09:54:13Z","title_canon_sha256":"285601870dff531262a9c646809629608737031eb1bb01063c1ccfc47efeefdb"},"schema_version":"1.0","source":{"id":"1811.10256","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10256","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10256v2","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10256","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"PMAYFHGEPLWF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PMAYFHGEPLWFC6EQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PMAYFHGE","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:16e6a643abc86fd401e7a237161a7cc070eb38fa87db8a988a6ed7eb35955da5","target":"graph","created_at":"2026-05-17T23:54:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We address the problem of how to \"obfuscate\" texts by removing stylistic clues which can identify authorship, whilst preserving (as much as possible) the content of the text. In this paper we combine ideas from \"generalised differential privacy\" and machine learning techniques for text processing to model privacy for text documents. We define a privacy mechanism that operates at the level of text documents represented as \"bags-of-words\" - these representations are typical in machine learning and contain sufficient information to carry out many kinds of classification tasks including topic iden","authors_text":"Annabelle McIver, Mark Dras, Natasha Fernandes","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-11-26T09:54:13Z","title":"Generalised Differential Privacy for Text Document Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10256","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a3834d676c28a52c77e3ef586c5ebb6db41766e493ec9ac87f3fe148316f7a6f","target":"record","created_at":"2026-05-17T23:54:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"489002cd66a880d72a014c44cab034d05e839490cc4931db8e179fa9ee2f3c24","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-11-26T09:54:13Z","title_canon_sha256":"285601870dff531262a9c646809629608737031eb1bb01063c1ccfc47efeefdb"},"schema_version":"1.0","source":{"id":"1811.10256","kind":"arxiv","version":2}},"canonical_sha256":"7b01829cc47aec5178904aef4d66d46b62b87aaaf58b729b7b86c76d3d98fdf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b01829cc47aec5178904aef4d66d46b62b87aaaf58b729b7b86c76d3d98fdf2","first_computed_at":"2026-05-17T23:54:47.985755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:47.985755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EYXIetHymv+NrbnAZWrKSqTRJM84139pUIUUK5VLp4Eap4C1B6qyanbsUfruN1AI7x5l1yWKFilnJFzJqQ1EBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:47.986262Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10256","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3834d676c28a52c77e3ef586c5ebb6db41766e493ec9ac87f3fe148316f7a6f","sha256:16e6a643abc86fd401e7a237161a7cc070eb38fa87db8a988a6ed7eb35955da5"],"state_sha256":"652d7b449bb951f6ad0943abb70939805f954f1e92d331a58a886183220a776b"}