{"as_of":"2026-08-08T16:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:25e2e0e1045dae3da41fcbb2d0ccf315096c040027547e73be4b1b853b1d8d73","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:20:22.584862Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.10582/citation-record","integrity":"/paper/2507.10582/integrity","json":"/paper/2507.10582/citation-record.json","paper":"/paper/2507.10582"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.935608Z","title":null,"venue":null,"work_id":"903c14f3-1207-4c54-876f-0796b8ad1fd3","year":2013},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.456620Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:81440ac52a18c0099e4dbffa6d99656b4c72352f27abe320e4be4f676bcbc0d8","observation_id":"45ff022c-bf0c-40ba-adcb-8ff26b3f360e","resolution":{"observed_at":"2026-08-06T18:20:22.943055Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.917320Z","title":"Efficient es- timation of word representations in vector space","venue":null,"work_id":"37dac655-2790-4b53-af49-7e73d0495cc9","year":2013},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.464540Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:d4ba985d5d7c6252929cf5ef141471d3ebfd3bf37ec0369c2cf514e4a2186ef6","observation_id":"a2306f27-855e-4aa1-99a1-1a242f17be50","resolution":{"observed_at":"2026-08-06T18:20:22.923715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.897306Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"ffc65bb0-ab25-467a-b19f-a6a620700455","year":2019},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.475578Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:130ae78a907edd17af10f125f0c652d9302e3cf86a9025e919e15725034206c8","observation_id":"e56ca477-a5ad-42d8-a014-a58cc0a62b6c","resolution":{"observed_at":"2026-08-06T18:20:22.904163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.875747Z","title":"Sentence-BERT: Sentence embeddings using Siamese BERT-networks","venue":null,"work_id":"4ed10196-8301-4214-b5e2-4be8d6303411","year":2019},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.483744Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:9fe7c5b2e9dfb89b491702b4edcf61924c1fa9729f53b80d3c18df169877e38a","observation_id":"2c9dfdb8-a3ea-4339-a902-d9cb59828b5b","resolution":{"observed_at":"2026-08-06T18:20:22.882049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.855780Z","title":"Natural language processing for social science research: A comprehensive review","venue":null,"work_id":"dc0ff960-e995-4020-9f79-234f96e4e279","year":2025},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.493450Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:c8802b1fc88405cfbc5981cecf88658dddb011d2eb92e5b7aab9d4098ef8d319","observation_id":"f334bd01-9ae6-424d-b8b1-69add7f43bc4","resolution":{"observed_at":"2026-08-06T18:20:22.861013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.499971Z","title":"Dense passage retrieval for open-domain question answering","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.499971Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:d706a99fb15c505ad4af9a8f3ded47f711da5139919b7c6ad7d8bd46eb86feae","observation_id":"6d75dbcb-c538-4712-8d12-179df3a50a6d","resolution":{"observed_at":"2026-08-06T18:20:22.499971Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.05794","last_updated":"2022-03-11T08:35:15Z","snapshot_observed_at":"2026-07-06T12:46:41.057346Z","submitted_at":"2022-03-11T08:35:15Z","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.05794","snapshot_observed_at":"2026-08-06T18:20:22.506799Z","title":"BERTopic: Neural topic modeling with a class- based TF-IDF procedure","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.506799Z"},"links":{"cited_paper":"/paper/2203.05794","citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:971fa7e79d3c25a5837217ee19adcb0b46e5920a89f39191a1a289cbcb26c00f","observation_id":"60b57a8b-bd1b-4393-a421-8ffc7a34391c","resolution":{"observed_at":"2026-08-06T18:20:22.506799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.00053","last_updated":"2020-08-19T19:58:14Z","snapshot_observed_at":"2026-08-07T00:25:43.335186Z","submitted_at":"2020-03-31T18:33:36Z","title":"Information Leakage in Embedding Models","version":2},"cited_work":{"arxiv_id":"2004.00053","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.00053","snapshot_observed_at":"2026-08-06T18:20:22.734278Z","title":"Information Leakage in Embedding Models","venue":"cs.LG","work_id":"c4252981-13ff-4ce3-9477-9bf91f7c1ac0","year":2020},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.514165Z"},"links":{"cited_paper":"/paper/2004.00053","citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:f57973f21321952375c591a13417721d0055684244aa058e59a5c4d2a9d48922","observation_id":"9c492cfd-6552-4212-8ce9-c488ae2400c0","resolution":{"observed_at":"2026-08-06T18:20:22.742845Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03010","last_updated":"2023-05-04T17:31:41Z","snapshot_observed_at":"2026-08-06T21:09:36.639494Z","submitted_at":"2023-05-04T17:31:41Z","title":"Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.03010","snapshot_observed_at":"2026-08-06T18:20:22.524627Z","title":"Sentence embedding leaks more information than you expect: Generative embedding inversion attack to recover the whole sentence, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.524627Z"},"links":{"cited_paper":"/paper/2305.03010","citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:3d0ec1e1ba11801bc3d8b9b0618849701a8ef370e549976ffaef66bb2c69d9ff","observation_id":"57b138e3-b806-41da-9d28-48b44564397f","resolution":{"observed_at":"2026-08-06T18:20:22.524627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06816","last_updated":"2023-10-10T17:39:03Z","snapshot_observed_at":"2026-07-06T16:30:37.867641Z","submitted_at":"2023-10-10T17:39:03Z","title":"Text Embeddings Reveal (Almost) As Much As Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06816","snapshot_observed_at":"2026-08-06T18:20:22.533944Z","title":"Morris, Volodymyr Kuleshov, Vitaly Shmatikov, and Alexander M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.533944Z"},"links":{"cited_paper":"/paper/2310.06816","citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:990e3f09fe93140e50e712b671771e1a349abba204c6a950208a0c49e1e1d3ba","observation_id":"97e7af8e-163e-4a84-8365-5f7367e86ea7","resolution":{"observed_at":"2026-08-06T18:20:22.533944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.822998Z","title":"Does bert pretrained on clinical notes reveal sensitive data? In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) , 2021","venue":null,"work_id":"bac09fe9-3b7e-4bc8-9835-e726f9229539","year":2021},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.542699Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:b0474d7f4a0c07fa97eb09bca54e712d10cf9f418c9c6520bfd82bb4c6982dc5","observation_id":"00783561-9209-4a08-b94b-24244ba980f8","resolution":{"observed_at":"2026-08-06T18:20:22.831415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.798501Z","title":"Stanza: A Python natural language processing toolkit for many human languages","venue":null,"work_id":"ca630098-4068-4fbf-8b36-9cd034bac8d1","year":2020},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.553406Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:065a671c3b7de576858f0aca621e2ee244f22d13a68ba4c4b57fa4a543be56b3","observation_id":"6fbfc2cd-77d1-4f49-83f4-182f9be9cff2","resolution":{"observed_at":"2026-08-06T18:20:22.804940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03281","last_updated":"2023-08-07T03:52:59Z","snapshot_observed_at":"2026-08-04T23:10:23.964516Z","submitted_at":"2023-08-07T03:52:59Z","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03281","snapshot_observed_at":"2026-08-06T18:20:22.565221Z","title":"Towards general text embeddings with multi-stage con- trastive learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.565221Z"},"links":{"cited_paper":"/paper/2308.03281","citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:e6b5abe27ec315ed56359f336ca540c2ca817c4c88fd4432ac19789131fa65a2","observation_id":"dd7d34c4-4b28-4981-ae2b-4f5931f55e8b","resolution":{"observed_at":"2026-08-06T18:20:22.565221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:22.775838Z","title":"Increased risk of death immediately after dis- charge from compulsory care for substance abuse","venue":null,"work_id":"b8d2b855-5a6c-4a37-a170-448e6aac6aad","year":2022},"citing_paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:22.584862Z"},"links":{"citing_paper":"/paper/2507.10582"},"observation_digest":"sha256:c3b7d95958a0a7b591a17a4d5c93dac2b8d5b60958bcf9f54678f4f620d4fe0f","observation_id":"115d0168-e181-4742-91dc-2db8eb98247e","resolution":{"observed_at":"2026-08-06T18:20:22.782997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.10582","last_updated":"2025-07-11T11:58:36Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T18:14:15.978584Z","submitted_at":"2025-07-11T11:58:36Z","title":"Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":1,"verified_fuzzy":7},"total_outbound_references":14},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2507.10582."}