{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JBQ3KIEL7XOC4LSHGR7ZRNIHUI","short_pith_number":"pith:JBQ3KIEL","schema_version":"1.0","canonical_sha256":"4861b5208bfddc2e2e47347f98b507a22fb5e020f244c29a7d077cd51c4e04cd","source":{"kind":"arxiv","id":"2304.13998","version":1},"attestation_state":"computed","paper":{"title":"Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhinav Kashyap, Chih-Jen Lin, Jie-Jyun Liu, Shao-Syuan Huang, Stefan Winkler, Thanh-Tung Nguyen, Viktor Schlegel","submitted_at":"2023-04-27T07:36:14Z","abstract_excerpt":"Clinical notes are assigned ICD codes - sets of codes for diagnoses and procedures. In the recent years, predictive machine learning models have been built for automatic ICD coding. However, there is a lack of widely accepted benchmarks for automated ICD coding models based on large-scale public EHR data.\n  This paper proposes a public benchmark suite for ICD-10 coding using a large EHR dataset derived from MIMIC-IV, the most recent public EHR dataset. We implement and compare several popular methods for ICD coding prediction tasks to standardize data preprocessing and establish a comprehensiv"},"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":"2304.13998","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-04-27T07:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"565917b4fe6315f9052e5ccf201b054478695fa4825c4168f3b40c80211eb195","abstract_canon_sha256":"6d19b8942fe96f194dcd9cecf18e30e62c6a4df71a99e86cdf5b7deec43739a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:59.466935Z","signature_b64":"4jn0gpijnkUOQQh6SBvaGNJanYn51xJ0cx2BoFAIWwfN/TvVJIRnFB1wqMyAUk6Q38nTcgjWhi66LNy8XJq9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4861b5208bfddc2e2e47347f98b507a22fb5e020f244c29a7d077cd51c4e04cd","last_reissued_at":"2026-07-05T06:04:59.466609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:59.466609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abhinav Kashyap, Chih-Jen Lin, Jie-Jyun Liu, Shao-Syuan Huang, Stefan Winkler, Thanh-Tung Nguyen, Viktor Schlegel","submitted_at":"2023-04-27T07:36:14Z","abstract_excerpt":"Clinical notes are assigned ICD codes - sets of codes for diagnoses and procedures. In the recent years, predictive machine learning models have been built for automatic ICD coding. However, there is a lack of widely accepted benchmarks for automated ICD coding models based on large-scale public EHR data.\n  This paper proposes a public benchmark suite for ICD-10 coding using a large EHR dataset derived from MIMIC-IV, the most recent public EHR dataset. We implement and compare several popular methods for ICD coding prediction tasks to standardize data preprocessing and establish a comprehensiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13998","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/2304.13998/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":"2304.13998","created_at":"2026-07-05T06:04:59.466663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13998v1","created_at":"2026-07-05T06:04:59.466663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13998","created_at":"2026-07-05T06:04:59.466663+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBQ3KIEL7XOC","created_at":"2026-07-05T06:04:59.466663+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBQ3KIEL7XOC4LSH","created_at":"2026-07-05T06:04:59.466663+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBQ3KIEL","created_at":"2026-07-05T06:04:59.466663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.03122","citing_title":"Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI","json":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI.json","graph_json":"https://pith.science/api/pith-number/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/graph.json","events_json":"https://pith.science/api/pith-number/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/events.json","paper":"https://pith.science/paper/JBQ3KIEL"},"agent_actions":{"view_html":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI","download_json":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI.json","view_paper":"https://pith.science/paper/JBQ3KIEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13998&json=true","fetch_graph":"https://pith.science/api/pith-number/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/graph.json","fetch_events":"https://pith.science/api/pith-number/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/action/storage_attestation","attest_author":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/action/author_attestation","sign_citation":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/action/citation_signature","submit_replication":"https://pith.science/pith/JBQ3KIEL7XOC4LSHGR7ZRNIHUI/action/replication_record"}},"created_at":"2026-07-05T06:04:59.466663+00:00","updated_at":"2026-07-05T06:04:59.466663+00:00"}