{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:C6NZ2POVD6R6RKNNCSEDAIT3MS","short_pith_number":"pith:C6NZ2POV","schema_version":"1.0","canonical_sha256":"179b9d3dd51fa3e8a9ad148830227b64abaace4469f3a59b4f810e8e8d8742b2","source":{"kind":"arxiv","id":"2006.07332","version":1},"attestation_state":"computed","paper":{"title":"Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Richard JB Dobson, Thomas Searle, Zina Ibrahim","submitted_at":"2020-06-12T17:15:44Z","abstract_excerpt":"Clinical coding is currently a labour-intensive, error-prone, but critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new state of the art results. A popular dataset used in this task is MIMIC-III, a large intensive care database that includes clinical free text notes and associated codes. We argue for the reconsideration of the validity MIMIC-III's assigned codes that"},"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":"2006.07332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T17:15:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bfb7343969db194680aa62cc3f36ff442a92cd79a459783af8e493a75d88887c","abstract_canon_sha256":"97910c91acf233c15b164ced848c1836780c8c55357645c5e3ab4c84e29cbca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:22.441026Z","signature_b64":"4M2gOpIwC0DkvG70GvykL2wm4Djkq9n5g7qSQOCwFHIyuh4HfJaSexc2bfNWk0VLboNAruJklhAGKWqIsDusBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"179b9d3dd51fa3e8a9ad148830227b64abaace4469f3a59b4f810e8e8d8742b2","last_reissued_at":"2026-07-05T05:45:22.440631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:22.440631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Richard JB Dobson, Thomas Searle, Zina Ibrahim","submitted_at":"2020-06-12T17:15:44Z","abstract_excerpt":"Clinical coding is currently a labour-intensive, error-prone, but critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new state of the art results. A popular dataset used in this task is MIMIC-III, a large intensive care database that includes clinical free text notes and associated codes. We argue for the reconsideration of the validity MIMIC-III's assigned codes that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07332","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/2006.07332/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":"2006.07332","created_at":"2026-07-05T05:45:22.440683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07332v1","created_at":"2026-07-05T05:45:22.440683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07332","created_at":"2026-07-05T05:45:22.440683+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6NZ2POVD6R6","created_at":"2026-07-05T05:45:22.440683+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6NZ2POVD6R6RKNN","created_at":"2026-07-05T05:45:22.440683+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6NZ2POV","created_at":"2026-07-05T05:45:22.440683+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/C6NZ2POVD6R6RKNNCSEDAIT3MS","json":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS.json","graph_json":"https://pith.science/api/pith-number/C6NZ2POVD6R6RKNNCSEDAIT3MS/graph.json","events_json":"https://pith.science/api/pith-number/C6NZ2POVD6R6RKNNCSEDAIT3MS/events.json","paper":"https://pith.science/paper/C6NZ2POV"},"agent_actions":{"view_html":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS","download_json":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS.json","view_paper":"https://pith.science/paper/C6NZ2POV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07332&json=true","fetch_graph":"https://pith.science/api/pith-number/C6NZ2POVD6R6RKNNCSEDAIT3MS/graph.json","fetch_events":"https://pith.science/api/pith-number/C6NZ2POVD6R6RKNNCSEDAIT3MS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS/action/storage_attestation","attest_author":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS/action/author_attestation","sign_citation":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS/action/citation_signature","submit_replication":"https://pith.science/pith/C6NZ2POVD6R6RKNNCSEDAIT3MS/action/replication_record"}},"created_at":"2026-07-05T05:45:22.440683+00:00","updated_at":"2026-07-05T05:45:22.440683+00:00"}