{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:76JNINHR6ILIF6QUYGNNCUIP6W","short_pith_number":"pith:76JNINHR","schema_version":"1.0","canonical_sha256":"ff92d434f1f21682fa14c19ad1510ff5a0010f9d3bb1f389aeb89a9720a69e47","source":{"kind":"arxiv","id":"2402.11006","version":1},"attestation_state":"computed","paper":{"title":"Automated Detection and Analysis of Data Practices Using A Real-World Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"C. Lee Giles, Florian Schaub, Maria Badillo, Mukund Srinath, Pranav Venkit, Shomir Wilson","submitted_at":"2024-02-16T18:51:40Z","abstract_excerpt":"Privacy policies are crucial for informing users about data practices, yet their length and complexity often deter users from reading them. In this paper, we propose an automated approach to identify and visualize data practices within privacy policies at different levels of detail. Leveraging crowd-sourced annotations from the ToS;DR platform, we experiment with various methods to match policy excerpts with predefined data practice descriptions. We further conduct a case study to evaluate our approach on a real-world policy, demonstrating its effectiveness in simplifying complex policies. Exp"},"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":"2402.11006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-16T18:51:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b657533bffc036e0d7efafd72b8379906274c0a745c4a2cd44039f43dc3ad915","abstract_canon_sha256":"4b5bde945c63916d45a4cbb42c48837922d6cb4e3b843b2305e1a146b1ce4753"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:03.430926Z","signature_b64":"p63eKQLm/6O8MDF54LisXBkGK9h894bE9sgjtk8oHV4SLkWDh+Ad6ogbyPf4wRJ5IKzHxCH+9LfN2RVuucxQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff92d434f1f21682fa14c19ad1510ff5a0010f9d3bb1f389aeb89a9720a69e47","last_reissued_at":"2026-07-05T07:46:03.430390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:03.430390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Detection and Analysis of Data Practices Using A Real-World Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"C. Lee Giles, Florian Schaub, Maria Badillo, Mukund Srinath, Pranav Venkit, Shomir Wilson","submitted_at":"2024-02-16T18:51:40Z","abstract_excerpt":"Privacy policies are crucial for informing users about data practices, yet their length and complexity often deter users from reading them. In this paper, we propose an automated approach to identify and visualize data practices within privacy policies at different levels of detail. Leveraging crowd-sourced annotations from the ToS;DR platform, we experiment with various methods to match policy excerpts with predefined data practice descriptions. We further conduct a case study to evaluate our approach on a real-world policy, demonstrating its effectiveness in simplifying complex policies. Exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11006","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/2402.11006/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":"2402.11006","created_at":"2026-07-05T07:46:03.430474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11006v1","created_at":"2026-07-05T07:46:03.430474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11006","created_at":"2026-07-05T07:46:03.430474+00:00"},{"alias_kind":"pith_short_12","alias_value":"76JNINHR6ILI","created_at":"2026-07-05T07:46:03.430474+00:00"},{"alias_kind":"pith_short_16","alias_value":"76JNINHR6ILIF6QU","created_at":"2026-07-05T07:46:03.430474+00:00"},{"alias_kind":"pith_short_8","alias_value":"76JNINHR","created_at":"2026-07-05T07:46:03.430474+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/76JNINHR6ILIF6QUYGNNCUIP6W","json":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W.json","graph_json":"https://pith.science/api/pith-number/76JNINHR6ILIF6QUYGNNCUIP6W/graph.json","events_json":"https://pith.science/api/pith-number/76JNINHR6ILIF6QUYGNNCUIP6W/events.json","paper":"https://pith.science/paper/76JNINHR"},"agent_actions":{"view_html":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W","download_json":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W.json","view_paper":"https://pith.science/paper/76JNINHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11006&json=true","fetch_graph":"https://pith.science/api/pith-number/76JNINHR6ILIF6QUYGNNCUIP6W/graph.json","fetch_events":"https://pith.science/api/pith-number/76JNINHR6ILIF6QUYGNNCUIP6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W/action/storage_attestation","attest_author":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W/action/author_attestation","sign_citation":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W/action/citation_signature","submit_replication":"https://pith.science/pith/76JNINHR6ILIF6QUYGNNCUIP6W/action/replication_record"}},"created_at":"2026-07-05T07:46:03.430474+00:00","updated_at":"2026-07-05T07:46:03.430474+00:00"}