{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V6DC3VQYNRWKBRZXGNNNEDSUTQ","short_pith_number":"pith:V6DC3VQY","canonical_record":{"source":{"id":"2407.12849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-06T06:58:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a8423668f35023743e0f3389bc2ce4d6d8483a57eeac79f2deb9546a24657f95","abstract_canon_sha256":"959a9783d2b1570aebc3df18b9d200883c16f38d4c38bdf7f5c8d4fe87baf76e"},"schema_version":"1.0"},"canonical_sha256":"af862dd6186c6ca0c737335ad20e549c3e166ef1fd69953745437459e612ea69","source":{"kind":"arxiv","id":"2407.12849","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12849","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12849v1","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12849","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"V6DC3VQYNRWK","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"V6DC3VQYNRWKBRZX","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"V6DC3VQY","created_at":"2026-07-05T08:45:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V6DC3VQYNRWKBRZXGNNNEDSUTQ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-06T06:58:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a8423668f35023743e0f3389bc2ce4d6d8483a57eeac79f2deb9546a24657f95","abstract_canon_sha256":"959a9783d2b1570aebc3df18b9d200883c16f38d4c38bdf7f5c8d4fe87baf76e"},"schema_version":"1.0"},"canonical_sha256":"af862dd6186c6ca0c737335ad20e549c3e166ef1fd69953745437459e612ea69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:12.493756Z","signature_b64":"OngmdnWCjQJOl6NfNNF+sj9gwSlbUOEEMhIPIpPJEEuIDBcdpbXLWsGdFoMEIDX5pD3/PyXkFYjRZAwAdciADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af862dd6186c6ca0c737335ad20e549c3e166ef1fd69953745437459e612ea69","last_reissued_at":"2026-07-05T08:45:12.493358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:12.493358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12849","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T098D4PlnPPsuk7mz/oVkPj4gco49H+3TaP6dJiV2MguhdiembjzoLawYYgzB7S2VXaRPGyIvcdhupLCyzcHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:46:51.492752Z"},"content_sha256":"37fa50d3864789711e240e3ed2e8e7ce9adc2ce5f77972e2ba8b825613e31a19","schema_version":"1.0","event_id":"sha256:37fa50d3864789711e240e3ed2e8e7ce9adc2ce5f77972e2ba8b825613e31a19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V6DC3VQYNRWKBRZXGNNNEDSUTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large language models are good medical coders, if provided with tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Keith Kwan","submitted_at":"2024-07-06T06:58:51Z","abstract_excerpt":"This study presents a novel two-stage Retrieve-Rank system for automated ICD-10-CM medical coding, comparing its performance against a Vanilla Large Language Model (LLM) approach. Evaluating both systems on a dataset of 100 single-term medical conditions, the Retrieve-Rank system achieved 100% accuracy in predicting correct ICD-10-CM codes, significantly outperforming the Vanilla LLM (GPT-3.5-turbo), which achieved only 6% accuracy. Our analysis demonstrates the Retrieve-Rank system's superior precision in handling various medical terms across different specialties. While these results are pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12849","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/2407.12849/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dpFw2bA2g6Nimuzo9iZfTM9Kx0iuW1hZC70v3U4xCAQhiEGVbSHFEPsoc3Rupwz7LYHM1u/+My+LhJI6dR4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:46:51.493291Z"},"content_sha256":"44f458c9bd50f15b188da361a0b85fd2475a583f8fcbcefabe5f3e8fec75a425","schema_version":"1.0","event_id":"sha256:44f458c9bd50f15b188da361a0b85fd2475a583f8fcbcefabe5f3e8fec75a425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6DC3VQYNRWKBRZXGNNNEDSUTQ/bundle.json","state_url":"https://pith.science/pith/V6DC3VQYNRWKBRZXGNNNEDSUTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6DC3VQYNRWKBRZXGNNNEDSUTQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T09:46:51Z","links":{"resolver":"https://pith.science/pith/V6DC3VQYNRWKBRZXGNNNEDSUTQ","bundle":"https://pith.science/pith/V6DC3VQYNRWKBRZXGNNNEDSUTQ/bundle.json","state":"https://pith.science/pith/V6DC3VQYNRWKBRZXGNNNEDSUTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6DC3VQYNRWKBRZXGNNNEDSUTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V6DC3VQYNRWKBRZXGNNNEDSUTQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"959a9783d2b1570aebc3df18b9d200883c16f38d4c38bdf7f5c8d4fe87baf76e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-06T06:58:51Z","title_canon_sha256":"a8423668f35023743e0f3389bc2ce4d6d8483a57eeac79f2deb9546a24657f95"},"schema_version":"1.0","source":{"id":"2407.12849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12849","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12849v1","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12849","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"V6DC3VQYNRWK","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"V6DC3VQYNRWKBRZX","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"V6DC3VQY","created_at":"2026-07-05T08:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:44f458c9bd50f15b188da361a0b85fd2475a583f8fcbcefabe5f3e8fec75a425","target":"graph","created_at":"2026-07-05T08:45:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.12849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study presents a novel two-stage Retrieve-Rank system for automated ICD-10-CM medical coding, comparing its performance against a Vanilla Large Language Model (LLM) approach. Evaluating both systems on a dataset of 100 single-term medical conditions, the Retrieve-Rank system achieved 100% accuracy in predicting correct ICD-10-CM codes, significantly outperforming the Vanilla LLM (GPT-3.5-turbo), which achieved only 6% accuracy. Our analysis demonstrates the Retrieve-Rank system's superior precision in handling various medical terms across different specialties. While these results are pro","authors_text":"Keith Kwan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-06T06:58:51Z","title":"Large language models are good medical coders, if provided with tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12849","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37fa50d3864789711e240e3ed2e8e7ce9adc2ce5f77972e2ba8b825613e31a19","target":"record","created_at":"2026-07-05T08:45:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"959a9783d2b1570aebc3df18b9d200883c16f38d4c38bdf7f5c8d4fe87baf76e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-06T06:58:51Z","title_canon_sha256":"a8423668f35023743e0f3389bc2ce4d6d8483a57eeac79f2deb9546a24657f95"},"schema_version":"1.0","source":{"id":"2407.12849","kind":"arxiv","version":1}},"canonical_sha256":"af862dd6186c6ca0c737335ad20e549c3e166ef1fd69953745437459e612ea69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af862dd6186c6ca0c737335ad20e549c3e166ef1fd69953745437459e612ea69","first_computed_at":"2026-07-05T08:45:12.493358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:12.493358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OngmdnWCjQJOl6NfNNF+sj9gwSlbUOEEMhIPIpPJEEuIDBcdpbXLWsGdFoMEIDX5pD3/PyXkFYjRZAwAdciADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:12.493756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37fa50d3864789711e240e3ed2e8e7ce9adc2ce5f77972e2ba8b825613e31a19","sha256:44f458c9bd50f15b188da361a0b85fd2475a583f8fcbcefabe5f3e8fec75a425"],"state_sha256":"122be0e1a100d63755ec04d569a9409f288c8a430dd5afb4c8d72a302d9a3515"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bBwmHKurGsw3J/EcFqr3gBuwYlk28Pvw6T7oKznYtTOMzLuxH1M1mIbA2sD7lmhIf9+oW0GLiZouv1jQShgyBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:46:51.499616Z","bundle_sha256":"1d2c5e689e4d72480d1dd4b25777f6942531a235689014f14ba8d2f54a2e3274"}}