{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PX7GTLSARM6UNOYCM7YARMMPCI","short_pith_number":"pith:PX7GTLSA","schema_version":"1.0","canonical_sha256":"7dfe69ae408b3d46bb0267f008b18f12187743ab73d0a4d118fdfd554dd60386","source":{"kind":"arxiv","id":"2004.11131","version":2},"attestation_state":"computed","paper":{"title":"Privacy at Scale: Introducing the PrivaSeer Corpus of Web Privacy Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.IR","authors_text":"C. Lee Giles, Mukund Srinath, Shomir Wilson","submitted_at":"2020-04-23T13:21:00Z","abstract_excerpt":"Organisations disclose their privacy practices by posting privacy policies on their website. Even though users often care about their digital privacy, they often don't read privacy policies since they require a significant investment in time and effort. Although natural language processing can help in privacy policy understanding, there has been a lack of large scale privacy policy corpora that could be used to analyse, understand, and simplify privacy policies. Thus, we create PrivaSeer, a corpus of over one million English language website privacy policies, which is significantly larger than"},"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":"2004.11131","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-04-23T13:21:00Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"1af73497e21a12c5eaad2f50038da291efc462c24a0a3b44a02703de9ddd1afb","abstract_canon_sha256":"89a69d2e4e379db129c05b46ad665013e3c24376612457d9e1b718c27db40792"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:18.210282Z","signature_b64":"eRjrpTgG2SLxMZ04POZqs9c9MxPXj6BvFhf8EI93w9ymonzBNLw00pwn5a4LGGFLWk8vSWwHTa3N8wqDne7BAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dfe69ae408b3d46bb0267f008b18f12187743ab73d0a4d118fdfd554dd60386","last_reissued_at":"2026-07-05T08:02:18.209838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:18.209838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy at Scale: Introducing the PrivaSeer Corpus of Web Privacy Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.IR","authors_text":"C. Lee Giles, Mukund Srinath, Shomir Wilson","submitted_at":"2020-04-23T13:21:00Z","abstract_excerpt":"Organisations disclose their privacy practices by posting privacy policies on their website. Even though users often care about their digital privacy, they often don't read privacy policies since they require a significant investment in time and effort. Although natural language processing can help in privacy policy understanding, there has been a lack of large scale privacy policy corpora that could be used to analyse, understand, and simplify privacy policies. Thus, we create PrivaSeer, a corpus of over one million English language website privacy policies, which is significantly larger than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11131","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/2004.11131/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":"2004.11131","created_at":"2026-07-05T08:02:18.209884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.11131v2","created_at":"2026-07-05T08:02:18.209884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11131","created_at":"2026-07-05T08:02:18.209884+00:00"},{"alias_kind":"pith_short_12","alias_value":"PX7GTLSARM6U","created_at":"2026-07-05T08:02:18.209884+00:00"},{"alias_kind":"pith_short_16","alias_value":"PX7GTLSARM6UNOYC","created_at":"2026-07-05T08:02:18.209884+00:00"},{"alias_kind":"pith_short_8","alias_value":"PX7GTLSA","created_at":"2026-07-05T08:02:18.209884+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/PX7GTLSARM6UNOYCM7YARMMPCI","json":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI.json","graph_json":"https://pith.science/api/pith-number/PX7GTLSARM6UNOYCM7YARMMPCI/graph.json","events_json":"https://pith.science/api/pith-number/PX7GTLSARM6UNOYCM7YARMMPCI/events.json","paper":"https://pith.science/paper/PX7GTLSA"},"agent_actions":{"view_html":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI","download_json":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI.json","view_paper":"https://pith.science/paper/PX7GTLSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.11131&json=true","fetch_graph":"https://pith.science/api/pith-number/PX7GTLSARM6UNOYCM7YARMMPCI/graph.json","fetch_events":"https://pith.science/api/pith-number/PX7GTLSARM6UNOYCM7YARMMPCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI/action/storage_attestation","attest_author":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI/action/author_attestation","sign_citation":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI/action/citation_signature","submit_replication":"https://pith.science/pith/PX7GTLSARM6UNOYCM7YARMMPCI/action/replication_record"}},"created_at":"2026-07-05T08:02:18.209884+00:00","updated_at":"2026-07-05T08:02:18.209884+00:00"}