{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DXQ3W7DIOPGEWTLOV7W4NCHLQI","short_pith_number":"pith:DXQ3W7DI","schema_version":"1.0","canonical_sha256":"1de1bb7c6873cc4b4d6eafedc688eb8224846292bee39c91b2d43e16ab598982","source":{"kind":"arxiv","id":"2604.18191","version":2},"attestation_state":"computed","paper":{"title":"Implementing CPSLint: A Data Validation and Sanitisation Tool for Industrial Cyber-Physical Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CPSLint is a domain-specific language that expresses industrial CPS data sanitization and validation in just a few lines of code.","cross_cats":[],"primary_cat":"cs.PL","authors_text":"Mari\\\"elle Stoelinga, \\\"Omer Sayilir, Uraz Odyurt, Vadim Zaytsev","submitted_at":"2026-04-20T12:46:13Z","abstract_excerpt":"Raw datasets are often too large and unstructured to work with directly, and require a data preparation phase. The domain of industrial Cyber-Physical Systems (CPSs) is no exception, as raw data typically consists of large time-series data collections that log the system's status at regular time intervals. The processing of such raw data is often carried out using ad hoc, case-specific, one-off Python scripts, often neglecting aspects of readability, reusability, and maintainability. In practice, this can cause professionals such as data scientists to write similar data preparation scripts for"},"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":"2604.18191","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2026-04-20T12:46:13Z","cross_cats_sorted":[],"title_canon_sha256":"b43df190f44c1b6a6160f6debcb237a4d92371e1f646d1e233c9c726ddfccb8a","abstract_canon_sha256":"3513563402ea91f4535f61f2ae616e49a83f610199f459a94ba8e45b9425e7c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:27.890543Z","signature_b64":"a9omOSCLIUZmGHUABjAgrRAd2Hc+03AFaO5UL6kokNtIbzurjslSTmU4GFsG0ymc4/xyt2M48+Gy0QlXKhehBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de1bb7c6873cc4b4d6eafedc688eb8224846292bee39c91b2d43e16ab598982","last_reissued_at":"2026-06-12T01:09:27.890131Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:27.890131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implementing CPSLint: A Data Validation and Sanitisation Tool for Industrial Cyber-Physical Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CPSLint is a domain-specific language that expresses industrial CPS data sanitization and validation in just a few lines of code.","cross_cats":[],"primary_cat":"cs.PL","authors_text":"Mari\\\"elle Stoelinga, \\\"Omer Sayilir, Uraz Odyurt, Vadim Zaytsev","submitted_at":"2026-04-20T12:46:13Z","abstract_excerpt":"Raw datasets are often too large and unstructured to work with directly, and require a data preparation phase. The domain of industrial Cyber-Physical Systems (CPSs) is no exception, as raw data typically consists of large time-series data collections that log the system's status at regular time intervals. The processing of such raw data is often carried out using ad hoc, case-specific, one-off Python scripts, often neglecting aspects of readability, reusability, and maintainability. In practice, this can cause professionals such as data scientists to write similar data preparation scripts for"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce CPSLint, a Domain-Specific Language (DSL) designed to support the data preparation process for industrial CPS. ... In our DSL one can express the data preparation process in just a few lines of code. CPSLint is a publicly available tool applicable for any case involving time-series data collections in need of sanitisation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"We leverage the fact that many raw data collections in the industrial CPS domain require similar actions to render them suitable for data-centric workflows.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CPSLint is a publicly available DSL that lets users express data sanitization for CPS time-series collections in a few lines of code, improving readability and maintainability over custom scripts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CPSLint is a domain-specific language that expresses industrial CPS data sanitization and validation in just a few lines of code.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b1f26f309ffac2d41825e2b75a761110277059d07e0e2764e45a92e45e523a87"},"source":{"id":"2604.18191","kind":"arxiv","version":2},"verdict":{"id":"40ceaa2f-37d4-4d5c-84d3-6910efb6b64d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T03:30:15.057428Z","strongest_claim":"We introduce CPSLint, a Domain-Specific Language (DSL) designed to support the data preparation process for industrial CPS. ... In our DSL one can express the data preparation process in just a few lines of code. CPSLint is a publicly available tool applicable for any case involving time-series data collections in need of sanitisation.","one_line_summary":"CPSLint is a publicly available DSL that lets users express data sanitization for CPS time-series collections in a few lines of code, improving readability and maintainability over custom scripts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"We leverage the fact that many raw data collections in the industrial CPS domain require similar actions to render them suitable for data-centric workflows.","pith_extraction_headline":"CPSLint is a domain-specific language that expresses industrial CPS data sanitization and validation in just a few lines of code."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.18191/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T04:21:15.577126Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8e290f6be16df63b0bd8064039db5248dc149dfd3d706e9fc9e35019ca478d24"},"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":"2604.18191","created_at":"2026-06-12T01:09:27.890190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.18191v2","created_at":"2026-06-12T01:09:27.890190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18191","created_at":"2026-06-12T01:09:27.890190+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXQ3W7DIOPGE","created_at":"2026-06-12T01:09:27.890190+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXQ3W7DIOPGEWTLO","created_at":"2026-06-12T01:09:27.890190+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXQ3W7DI","created_at":"2026-06-12T01:09:27.890190+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/DXQ3W7DIOPGEWTLOV7W4NCHLQI","json":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI.json","graph_json":"https://pith.science/api/pith-number/DXQ3W7DIOPGEWTLOV7W4NCHLQI/graph.json","events_json":"https://pith.science/api/pith-number/DXQ3W7DIOPGEWTLOV7W4NCHLQI/events.json","paper":"https://pith.science/paper/DXQ3W7DI"},"agent_actions":{"view_html":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI","download_json":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI.json","view_paper":"https://pith.science/paper/DXQ3W7DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.18191&json=true","fetch_graph":"https://pith.science/api/pith-number/DXQ3W7DIOPGEWTLOV7W4NCHLQI/graph.json","fetch_events":"https://pith.science/api/pith-number/DXQ3W7DIOPGEWTLOV7W4NCHLQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI/action/storage_attestation","attest_author":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI/action/author_attestation","sign_citation":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI/action/citation_signature","submit_replication":"https://pith.science/pith/DXQ3W7DIOPGEWTLOV7W4NCHLQI/action/replication_record"}},"created_at":"2026-06-12T01:09:27.890190+00:00","updated_at":"2026-06-12T01:09:27.890190+00:00"}