{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B3WJ4ZQRSRKMYT3RCZRUJXAPY3","short_pith_number":"pith:B3WJ4ZQR","schema_version":"1.0","canonical_sha256":"0eec9e66119454cc4f71166344dc0fc6d9962ede742014a7de3327c9de81a0d7","source":{"kind":"arxiv","id":"2505.18695","version":1},"attestation_state":"computed","paper":{"title":"AI for Regulatory Affairs: Balancing Accuracy, Interpretability, and Computational Cost in Medical Device Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aaron Ceross, Jeroen H. M. Bergmann, Yu Han","submitted_at":"2025-05-24T13:41:20Z","abstract_excerpt":"Regulatory affairs, which sits at the intersection of medicine and law, can benefit significantly from AI-enabled automation. Classification task is the initial step in which manufacturers position their products to regulatory authorities, and it plays a critical role in determining market access, regulatory scrutiny, and ultimately, patient safety. In this study, we investigate a broad range of AI models -- including traditional machine learning (ML) algorithms, deep learning architectures, and large language models -- using a regulatory dataset of medical device descriptions. We evaluate eac"},"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":"2505.18695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-24T13:41:20Z","cross_cats_sorted":[],"title_canon_sha256":"e0d5a89e350eb886f8f6d4d3b1e95db4d2ca69cebff690f2c2e514bf43fbcfc0","abstract_canon_sha256":"7431e3d806046741d960ba9b582cb35897c01a509c0a9e51aa349680b90e80b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:18.073421Z","signature_b64":"QG9tSxsi43CcQnzDGrWnm4uBflM/DUp4nnkmd41rSHdjg2bD43nTvaqX0Gug/lpa2CtfHWCAS8Ynwe5LkoXxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eec9e66119454cc4f71166344dc0fc6d9962ede742014a7de3327c9de81a0d7","last_reissued_at":"2026-07-05T11:09:18.072939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:18.072939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI for Regulatory Affairs: Balancing Accuracy, Interpretability, and Computational Cost in Medical Device Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aaron Ceross, Jeroen H. M. Bergmann, Yu Han","submitted_at":"2025-05-24T13:41:20Z","abstract_excerpt":"Regulatory affairs, which sits at the intersection of medicine and law, can benefit significantly from AI-enabled automation. Classification task is the initial step in which manufacturers position their products to regulatory authorities, and it plays a critical role in determining market access, regulatory scrutiny, and ultimately, patient safety. In this study, we investigate a broad range of AI models -- including traditional machine learning (ML) algorithms, deep learning architectures, and large language models -- using a regulatory dataset of medical device descriptions. We evaluate eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18695","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/2505.18695/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":"2505.18695","created_at":"2026-07-05T11:09:18.072994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18695v1","created_at":"2026-07-05T11:09:18.072994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18695","created_at":"2026-07-05T11:09:18.072994+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3WJ4ZQRSRKM","created_at":"2026-07-05T11:09:18.072994+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3WJ4ZQRSRKMYT3R","created_at":"2026-07-05T11:09:18.072994+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3WJ4ZQR","created_at":"2026-07-05T11:09:18.072994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25942","citing_title":"A Multimodal and Explainable Machine Learning Approach to Diagnosing Multi-Class Ejection Fraction from Electrocardiograms","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3","json":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3.json","graph_json":"https://pith.science/api/pith-number/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/graph.json","events_json":"https://pith.science/api/pith-number/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/events.json","paper":"https://pith.science/paper/B3WJ4ZQR"},"agent_actions":{"view_html":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3","download_json":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3.json","view_paper":"https://pith.science/paper/B3WJ4ZQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18695&json=true","fetch_graph":"https://pith.science/api/pith-number/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/graph.json","fetch_events":"https://pith.science/api/pith-number/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/action/storage_attestation","attest_author":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/action/author_attestation","sign_citation":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/action/citation_signature","submit_replication":"https://pith.science/pith/B3WJ4ZQRSRKMYT3RCZRUJXAPY3/action/replication_record"}},"created_at":"2026-07-05T11:09:18.072994+00:00","updated_at":"2026-07-05T11:09:18.072994+00:00"}