{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VZ5CUBEF54J26PBFRXLCJDDSEL","short_pith_number":"pith:VZ5CUBEF","schema_version":"1.0","canonical_sha256":"ae7a2a0485ef13af3c258dd6248c7222e965a0046d4a199f5d8256df1ee8b66b","source":{"kind":"arxiv","id":"2507.10582","version":1},"attestation_state":"computed","paper":{"title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.CL","authors_text":"Anders Ledberg, Anna Thal\\'en","submitted_at":"2025-07-11T11:58:36Z","abstract_excerpt":"Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence of sensitive, personally identifiable information, and significant heterogeneity in structure and language. We present a modular toolchain that prepares such text data for embedding-based analysis, relying entirely on open-weight models that run on local hardware, requiring only a workstation-level GPU and supporting privacy-sensitive research.\n  The toolcha"},"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":"2507.10582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T11:58:36Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"48eb03207e930e42016cbd8d77ac84e537789b10f9dd40111c483b527aa2cfea","abstract_canon_sha256":"cbee4a9534cb0eb5d428111aa3d187f06ba93375e734d85b1af9f7a48a739026"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:56.935847Z","signature_b64":"HZw6sV/A4Hfh+CCgdn4FpSEquNw1FiGY6tocp6HeOZ7xxAByJe2BOb1Sex8CLXdOugw9ZO3jGiWyyYI9/l5tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae7a2a0485ef13af3c258dd6248c7222e965a0046d4a199f5d8256df1ee8b66b","last_reissued_at":"2026-07-05T11:36:56.935426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:56.935426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.CL","authors_text":"Anders Ledberg, Anna Thal\\'en","submitted_at":"2025-07-11T11:58:36Z","abstract_excerpt":"Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence of sensitive, personally identifiable information, and significant heterogeneity in structure and language. We present a modular toolchain that prepares such text data for embedding-based analysis, relying entirely on open-weight models that run on local hardware, requiring only a workstation-level GPU and supporting privacy-sensitive research.\n  The toolcha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10582","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/2507.10582/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":"2507.10582","created_at":"2026-07-05T11:36:56.935512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10582v1","created_at":"2026-07-05T11:36:56.935512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10582","created_at":"2026-07-05T11:36:56.935512+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZ5CUBEF54J2","created_at":"2026-07-05T11:36:56.935512+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZ5CUBEF54J26PBF","created_at":"2026-07-05T11:36:56.935512+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZ5CUBEF","created_at":"2026-07-05T11:36:56.935512+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/VZ5CUBEF54J26PBFRXLCJDDSEL","json":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL.json","graph_json":"https://pith.science/api/pith-number/VZ5CUBEF54J26PBFRXLCJDDSEL/graph.json","events_json":"https://pith.science/api/pith-number/VZ5CUBEF54J26PBFRXLCJDDSEL/events.json","paper":"https://pith.science/paper/VZ5CUBEF"},"agent_actions":{"view_html":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL","download_json":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL.json","view_paper":"https://pith.science/paper/VZ5CUBEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10582&json=true","fetch_graph":"https://pith.science/api/pith-number/VZ5CUBEF54J26PBFRXLCJDDSEL/graph.json","fetch_events":"https://pith.science/api/pith-number/VZ5CUBEF54J26PBFRXLCJDDSEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL/action/storage_attestation","attest_author":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL/action/author_attestation","sign_citation":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL/action/citation_signature","submit_replication":"https://pith.science/pith/VZ5CUBEF54J26PBFRXLCJDDSEL/action/replication_record"}},"created_at":"2026-07-05T11:36:56.935512+00:00","updated_at":"2026-07-05T11:36:56.935512+00:00"}