{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X27ATVDDTU3PPVWMC7E4PZCPFT","short_pith_number":"pith:X27ATVDD","schema_version":"1.0","canonical_sha256":"bebe09d4639d36f7d6cc17c9c7e44f2cd4a516d8e60b0389a03db905063b6715","source":{"kind":"arxiv","id":"2505.16931","version":1},"attestation_state":"computed","paper":{"title":"PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Digory Smith, Matthew Zent, Simon Woodhead","submitted_at":"2025-05-22T17:22:28Z","abstract_excerpt":"Personally identifiable information (PII) anonymization is a high-stakes task that poses a barrier to many open-science data sharing initiatives. While PII identification has made large strides in recent years, in practice, error thresholds and the recall/precision trade-off still limit the uptake of these anonymization pipelines. We present PIIvot, a lighter-weight framework for PII anonymization that leverages knowledge of the data context to simplify the PII detection problem. To demonstrate its effectiveness, we also contribute QATD-2k, the largest open-source real-world tutoring dataset 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":"2505.16931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T17:22:28Z","cross_cats_sorted":[],"title_canon_sha256":"d7d3e7d5fc2de90dd7b424d985006351a58cd8e82027a588600b1f4cc89fc8fc","abstract_canon_sha256":"39e9c2215910ae79934c93dbd00a53a2bd594f8a4ad92bc189e227a8f3309bef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:43.490738Z","signature_b64":"erjYMK4LJ/ceCd1tAFw5pWdQrdu2Ag9GHu5vZMHqY5wU4Qg1bEaWDIWBvobAcAaZZ5Lxo0jMAk1K3CGBEYhQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bebe09d4639d36f7d6cc17c9c7e44f2cd4a516d8e60b0389a03db905063b6715","last_reissued_at":"2026-07-05T11:07:43.490064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:43.490064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Digory Smith, Matthew Zent, Simon Woodhead","submitted_at":"2025-05-22T17:22:28Z","abstract_excerpt":"Personally identifiable information (PII) anonymization is a high-stakes task that poses a barrier to many open-science data sharing initiatives. While PII identification has made large strides in recent years, in practice, error thresholds and the recall/precision trade-off still limit the uptake of these anonymization pipelines. We present PIIvot, a lighter-weight framework for PII anonymization that leverages knowledge of the data context to simplify the PII detection problem. To demonstrate its effectiveness, we also contribute QATD-2k, the largest open-source real-world tutoring dataset o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16931","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/2505.16931/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":"2505.16931","created_at":"2026-07-05T11:07:43.490140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16931v1","created_at":"2026-07-05T11:07:43.490140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16931","created_at":"2026-07-05T11:07:43.490140+00:00"},{"alias_kind":"pith_short_12","alias_value":"X27ATVDDTU3P","created_at":"2026-07-05T11:07:43.490140+00:00"},{"alias_kind":"pith_short_16","alias_value":"X27ATVDDTU3PPVWM","created_at":"2026-07-05T11:07:43.490140+00:00"},{"alias_kind":"pith_short_8","alias_value":"X27ATVDD","created_at":"2026-07-05T11:07:43.490140+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/X27ATVDDTU3PPVWMC7E4PZCPFT","json":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT.json","graph_json":"https://pith.science/api/pith-number/X27ATVDDTU3PPVWMC7E4PZCPFT/graph.json","events_json":"https://pith.science/api/pith-number/X27ATVDDTU3PPVWMC7E4PZCPFT/events.json","paper":"https://pith.science/paper/X27ATVDD"},"agent_actions":{"view_html":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT","download_json":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT.json","view_paper":"https://pith.science/paper/X27ATVDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16931&json=true","fetch_graph":"https://pith.science/api/pith-number/X27ATVDDTU3PPVWMC7E4PZCPFT/graph.json","fetch_events":"https://pith.science/api/pith-number/X27ATVDDTU3PPVWMC7E4PZCPFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT/action/storage_attestation","attest_author":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT/action/author_attestation","sign_citation":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT/action/citation_signature","submit_replication":"https://pith.science/pith/X27ATVDDTU3PPVWMC7E4PZCPFT/action/replication_record"}},"created_at":"2026-07-05T11:07:43.490140+00:00","updated_at":"2026-07-05T11:07:43.490140+00:00"}