{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E777OQ26BTW2SROHTKYXPJGPCM","short_pith_number":"pith:E777OQ26","schema_version":"1.0","canonical_sha256":"27fff7435e0ceda945c79ab177a4cf13184303c628d57d05cc99f6a4c05ee8af","source":{"kind":"arxiv","id":"2605.17755","version":1},"attestation_state":"computed","paper":{"title":"Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anthony Nguyen, Jinghui Liu","submitted_at":"2026-05-18T02:19:29Z","abstract_excerpt":"Clinical coding maps clinical documentation to standardized medical codes, an essential yet time-consuming administrative task that could benefit from automation. Current models on ICD coding are typically optimized for codes from a specific ICD version. However, in reality, ICD systems evolve continuously, and different versions are adopted across time periods and regions. Moreover, ICD coding suffers from the long-tail problem, and rare code performance can be a bottleneck for developing implementable models. We examine whether it is viable to train version-independent models by combining da"},"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":"2605.17755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T02:19:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b0a25276311460807fc4f04b4e0e482a03c8428279e67737bdd1396f82ba8fe","abstract_canon_sha256":"fd34526a5a6df7b650e5a586f9834da1c8ce8ca33f70c648449f073d6092f512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:56.575373Z","signature_b64":"D4I23NcgSUdJKgP/Xdbj0FExd3S7Ih2uVSPrezY2ZD0349XBUy4nrMfqY/az+M8OfniGBhS3+xMckeX/o3PMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27fff7435e0ceda945c79ab177a4cf13184303c628d57d05cc99f6a4c05ee8af","last_reissued_at":"2026-05-20T00:04:56.574587Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:56.574587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anthony Nguyen, Jinghui Liu","submitted_at":"2026-05-18T02:19:29Z","abstract_excerpt":"Clinical coding maps clinical documentation to standardized medical codes, an essential yet time-consuming administrative task that could benefit from automation. Current models on ICD coding are typically optimized for codes from a specific ICD version. However, in reality, ICD systems evolve continuously, and different versions are adopted across time periods and regions. Moreover, ICD coding suffers from the long-tail problem, and rare code performance can be a bottleneck for developing implementable models. We examine whether it is viable to train version-independent models by combining da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17755","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/2605.17755/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":"2605.17755","created_at":"2026-05-20T00:04:56.574708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17755v1","created_at":"2026-05-20T00:04:56.574708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17755","created_at":"2026-05-20T00:04:56.574708+00:00"},{"alias_kind":"pith_short_12","alias_value":"E777OQ26BTW2","created_at":"2026-05-20T00:04:56.574708+00:00"},{"alias_kind":"pith_short_16","alias_value":"E777OQ26BTW2SROH","created_at":"2026-05-20T00:04:56.574708+00:00"},{"alias_kind":"pith_short_8","alias_value":"E777OQ26","created_at":"2026-05-20T00:04:56.574708+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/E777OQ26BTW2SROHTKYXPJGPCM","json":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM.json","graph_json":"https://pith.science/api/pith-number/E777OQ26BTW2SROHTKYXPJGPCM/graph.json","events_json":"https://pith.science/api/pith-number/E777OQ26BTW2SROHTKYXPJGPCM/events.json","paper":"https://pith.science/paper/E777OQ26"},"agent_actions":{"view_html":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM","download_json":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM.json","view_paper":"https://pith.science/paper/E777OQ26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17755&json=true","fetch_graph":"https://pith.science/api/pith-number/E777OQ26BTW2SROHTKYXPJGPCM/graph.json","fetch_events":"https://pith.science/api/pith-number/E777OQ26BTW2SROHTKYXPJGPCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM/action/storage_attestation","attest_author":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM/action/author_attestation","sign_citation":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM/action/citation_signature","submit_replication":"https://pith.science/pith/E777OQ26BTW2SROHTKYXPJGPCM/action/replication_record"}},"created_at":"2026-05-20T00:04:56.574708+00:00","updated_at":"2026-05-20T00:04:56.574708+00:00"}