{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:C6SVEUZQ444MKQQYPEY7A4IJ72","short_pith_number":"pith:C6SVEUZQ","canonical_record":{"source":{"id":"2104.06709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T09:12:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10f31dc0683cfedbf422259f53c21b52facf05903d5a1c12af1f7373826d5858","abstract_canon_sha256":"e4b80a72ed30d1daa98cfd7756fd5968be7f29b4f49dd7876e1247bb9c6110ee"},"schema_version":"1.0"},"canonical_sha256":"17a5525330e738c542187931f07109fe8f56b1bb7bfa516ad20eb9a792f1e89b","source":{"kind":"arxiv","id":"2104.06709","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06709","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06709v1","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06709","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_12","alias_value":"C6SVEUZQ444M","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"C6SVEUZQ444MKQQY","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"C6SVEUZQ","created_at":"2026-07-05T02:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:C6SVEUZQ444MKQQYPEY7A4IJ72","target":"record","payload":{"canonical_record":{"source":{"id":"2104.06709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T09:12:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10f31dc0683cfedbf422259f53c21b52facf05903d5a1c12af1f7373826d5858","abstract_canon_sha256":"e4b80a72ed30d1daa98cfd7756fd5968be7f29b4f49dd7876e1247bb9c6110ee"},"schema_version":"1.0"},"canonical_sha256":"17a5525330e738c542187931f07109fe8f56b1bb7bfa516ad20eb9a792f1e89b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:08.627014Z","signature_b64":"5SsIwVcoVawgUt3YDaW9rSix2HgIHZux3ws3xnxj6d6MQ7DmjGu3PnIqe1wI7xAhN/g2SIWttR7OtHZd7onwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17a5525330e738c542187931f07109fe8f56b1bb7bfa516ad20eb9a792f1e89b","last_reissued_at":"2026-07-05T02:32:08.626622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:08.626622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.06709","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":"2026-07-05T02:32:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76+OAWRUMU85OLeTxlBeYFtkJ1Bv57t4xyJ2XTpHPR4HMtOPOhk9GKOjNm7Io+D4vW8aVlmyEg32u3zAEerdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:58:52.524018Z"},"content_sha256":"da4ea781d4928e05afd4403532af1355b86d799238b700d4b4f9d2651423e191","schema_version":"1.0","event_id":"sha256:da4ea781d4928e05afd4403532af1355b86d799238b700d4b4f9d2651423e191"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:C6SVEUZQ444MKQQYPEY7A4IJ72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards BERT-based Automatic ICD Coding: Limitations and Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Damian Pascual, Roger Wattenhofer, Sandro Luck","submitted_at":"2021-04-14T09:12:53Z","abstract_excerpt":"Automatic ICD coding is the task of assigning codes from the International Classification of Diseases (ICD) to medical notes. These codes describe the state of the patient and have multiple applications, e.g., computer-assisted diagnosis or epidemiological studies. ICD coding is a challenging task due to the complexity and length of medical notes. Unlike the general trend in language processing, no transformer model has been reported to reach high performance on this task. Here, we investigate in detail ICD coding using PubMedBERT, a state-of-the-art transformer model for biomedical language u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06709","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/2104.06709/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":"2026-07-05T02:32:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RW71K4EEzrAbHh69dNwOvbDtl5xgxWQMX+a+zS6C8XUMS7KtKyctN15eCGWJUfixHEpCudY5arEGrm6mfPFvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:58:52.524695Z"},"content_sha256":"3704391b77093f31f4533d6d747304730e4ee636ebc68eabd84aa35e440d742e","schema_version":"1.0","event_id":"sha256:3704391b77093f31f4533d6d747304730e4ee636ebc68eabd84aa35e440d742e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C6SVEUZQ444MKQQYPEY7A4IJ72/bundle.json","state_url":"https://pith.science/pith/C6SVEUZQ444MKQQYPEY7A4IJ72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C6SVEUZQ444MKQQYPEY7A4IJ72/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":"2026-08-21T10:58:52Z","links":{"resolver":"https://pith.science/pith/C6SVEUZQ444MKQQYPEY7A4IJ72","bundle":"https://pith.science/pith/C6SVEUZQ444MKQQYPEY7A4IJ72/bundle.json","state":"https://pith.science/pith/C6SVEUZQ444MKQQYPEY7A4IJ72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C6SVEUZQ444MKQQYPEY7A4IJ72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:C6SVEUZQ444MKQQYPEY7A4IJ72","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":"e4b80a72ed30d1daa98cfd7756fd5968be7f29b4f49dd7876e1247bb9c6110ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T09:12:53Z","title_canon_sha256":"10f31dc0683cfedbf422259f53c21b52facf05903d5a1c12af1f7373826d5858"},"schema_version":"1.0","source":{"id":"2104.06709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06709","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06709v1","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06709","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_12","alias_value":"C6SVEUZQ444M","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"C6SVEUZQ444MKQQY","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"C6SVEUZQ","created_at":"2026-07-05T02:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:3704391b77093f31f4533d6d747304730e4ee636ebc68eabd84aa35e440d742e","target":"graph","created_at":"2026-07-05T02:32:08Z","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/2104.06709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic ICD coding is the task of assigning codes from the International Classification of Diseases (ICD) to medical notes. These codes describe the state of the patient and have multiple applications, e.g., computer-assisted diagnosis or epidemiological studies. ICD coding is a challenging task due to the complexity and length of medical notes. Unlike the general trend in language processing, no transformer model has been reported to reach high performance on this task. Here, we investigate in detail ICD coding using PubMedBERT, a state-of-the-art transformer model for biomedical language u","authors_text":"Damian Pascual, Roger Wattenhofer, Sandro Luck","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T09:12:53Z","title":"Towards BERT-based Automatic ICD Coding: Limitations and Opportunities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06709","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:da4ea781d4928e05afd4403532af1355b86d799238b700d4b4f9d2651423e191","target":"record","created_at":"2026-07-05T02:32:08Z","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":"e4b80a72ed30d1daa98cfd7756fd5968be7f29b4f49dd7876e1247bb9c6110ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T09:12:53Z","title_canon_sha256":"10f31dc0683cfedbf422259f53c21b52facf05903d5a1c12af1f7373826d5858"},"schema_version":"1.0","source":{"id":"2104.06709","kind":"arxiv","version":1}},"canonical_sha256":"17a5525330e738c542187931f07109fe8f56b1bb7bfa516ad20eb9a792f1e89b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17a5525330e738c542187931f07109fe8f56b1bb7bfa516ad20eb9a792f1e89b","first_computed_at":"2026-07-05T02:32:08.626622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:08.626622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5SsIwVcoVawgUt3YDaW9rSix2HgIHZux3ws3xnxj6d6MQ7DmjGu3PnIqe1wI7xAhN/g2SIWttR7OtHZd7onwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:08.627014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da4ea781d4928e05afd4403532af1355b86d799238b700d4b4f9d2651423e191","sha256:3704391b77093f31f4533d6d747304730e4ee636ebc68eabd84aa35e440d742e"],"state_sha256":"48b3a88aebcf763a872ae21345d32b979ebc5902b316f75a824f254d9650217f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQb+/WCvznkRZKsUbMXEedcUtX1E+iVRMoPQuhkulOPXVVmYc+55Pq1Cr49g3nHLDe4DWRX5YPYwqcieh7HjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:58:52.530785Z","bundle_sha256":"9e3c8e78fea659c9ea4be6bfd2b845e201fb2ab1e2bd74a80b0425190607b634"}}