{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JM4VMCX4X4QUYHSVWOE2VPY4W7","short_pith_number":"pith:JM4VMCX4","canonical_record":{"source":{"id":"2005.12833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-22T05:07:17Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"feb96153252518882566cfe6c51664442c578d883de57f307da249f169b761e9","abstract_canon_sha256":"b934370c6b9d8ecc51ee5802b612da8ea3aff5adaaf4f7a8fd6c95191a77c948"},"schema_version":"1.0"},"canonical_sha256":"4b39560afcbf214c1e55b389aabf1cb7f43cbc62c535ab5672ba19b9bf7636e7","source":{"kind":"arxiv","id":"2005.12833","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.12833","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2005.12833v1","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.12833","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"JM4VMCX4X4QU","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"JM4VMCX4X4QUYHSV","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"JM4VMCX4","created_at":"2026-07-05T01:05:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JM4VMCX4X4QUYHSVWOE2VPY4W7","target":"record","payload":{"canonical_record":{"source":{"id":"2005.12833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-22T05:07:17Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"feb96153252518882566cfe6c51664442c578d883de57f307da249f169b761e9","abstract_canon_sha256":"b934370c6b9d8ecc51ee5802b612da8ea3aff5adaaf4f7a8fd6c95191a77c948"},"schema_version":"1.0"},"canonical_sha256":"4b39560afcbf214c1e55b389aabf1cb7f43cbc62c535ab5672ba19b9bf7636e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:58.048586Z","signature_b64":"nlRKNzbjnaFhbQfyD+VX+XmTkkopW9COELvbXkTAvOek5yr34MR4X9gxjbLAr64pUAKxW3K6qCs1GSnkxb7kBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b39560afcbf214c1e55b389aabf1cb7f43cbc62c535ab5672ba19b9bf7636e7","last_reissued_at":"2026-07-05T01:05:58.048019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:58.048019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.12833","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":"2026-07-05T01:05:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z9guAvnArAEUZUjxFRtifuhPU9ggOXreizfEKjDsm46jxqCQd4JImUbZpQq/tDW4pgORIr4GcMnwJfcnB1YJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:57:36.149209Z"},"content_sha256":"4897c34beda535961570ecec6779f0fb1cffee8776ee276b2aabc1154532f287","schema_version":"1.0","event_id":"sha256:4897c34beda535961570ecec6779f0fb1cffee8776ee276b2aabc1154532f287"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JM4VMCX4X4QUYHSVWOE2VPY4W7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Cui Tao, Degui Zhi, Laila Rasmy, Yang Xiang, Ziqian Xie","submitted_at":"2020-05-22T05:07:17Z","abstract_excerpt":"Deep learning (DL) based predictive models from electronic health records (EHR) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required to achieve high accuracy, hindering the adoption of DL-based models in scenarios with limited training data size. Recently, bidirectional encoder representations from transformers (BERT) and related models have achieved tremendous successes in the natural language processing domain. The pre-training of BERT on a very large training corpus generates contextualized embeddings that can boost the performance of mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.12833","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/2005.12833/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":"2026-07-05T01:05:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+2JTLkHZX4LReKkqKBOayz3SGdFmII7HvxvqnC60m5/VudAU4mago0OIW7q/qwoWvwY7iaqE/nxPBnYRRTeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:57:36.150349Z"},"content_sha256":"9853c98eeba8af3a4f072ac5ec12c011bc1be0ffbc3ff471a6843d92a8113330","schema_version":"1.0","event_id":"sha256:9853c98eeba8af3a4f072ac5ec12c011bc1be0ffbc3ff471a6843d92a8113330"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JM4VMCX4X4QUYHSVWOE2VPY4W7/bundle.json","state_url":"https://pith.science/pith/JM4VMCX4X4QUYHSVWOE2VPY4W7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JM4VMCX4X4QUYHSVWOE2VPY4W7/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":"2026-08-09T20:57:36Z","links":{"resolver":"https://pith.science/pith/JM4VMCX4X4QUYHSVWOE2VPY4W7","bundle":"https://pith.science/pith/JM4VMCX4X4QUYHSVWOE2VPY4W7/bundle.json","state":"https://pith.science/pith/JM4VMCX4X4QUYHSVWOE2VPY4W7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JM4VMCX4X4QUYHSVWOE2VPY4W7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JM4VMCX4X4QUYHSVWOE2VPY4W7","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":"b934370c6b9d8ecc51ee5802b612da8ea3aff5adaaf4f7a8fd6c95191a77c948","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-22T05:07:17Z","title_canon_sha256":"feb96153252518882566cfe6c51664442c578d883de57f307da249f169b761e9"},"schema_version":"1.0","source":{"id":"2005.12833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.12833","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2005.12833v1","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.12833","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"JM4VMCX4X4QU","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"JM4VMCX4X4QUYHSV","created_at":"2026-07-05T01:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"JM4VMCX4","created_at":"2026-07-05T01:05:58Z"}],"graph_snapshots":[{"event_id":"sha256:9853c98eeba8af3a4f072ac5ec12c011bc1be0ffbc3ff471a6843d92a8113330","target":"graph","created_at":"2026-07-05T01:05:58Z","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/2005.12833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning (DL) based predictive models from electronic health records (EHR) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required to achieve high accuracy, hindering the adoption of DL-based models in scenarios with limited training data size. Recently, bidirectional encoder representations from transformers (BERT) and related models have achieved tremendous successes in the natural language processing domain. The pre-training of BERT on a very large training corpus generates contextualized embeddings that can boost the performance of mo","authors_text":"Cui Tao, Degui Zhi, Laila Rasmy, Yang Xiang, Ziqian Xie","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-22T05:07:17Z","title":"Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.12833","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":"sha256:4897c34beda535961570ecec6779f0fb1cffee8776ee276b2aabc1154532f287","target":"record","created_at":"2026-07-05T01:05:58Z","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":"b934370c6b9d8ecc51ee5802b612da8ea3aff5adaaf4f7a8fd6c95191a77c948","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-22T05:07:17Z","title_canon_sha256":"feb96153252518882566cfe6c51664442c578d883de57f307da249f169b761e9"},"schema_version":"1.0","source":{"id":"2005.12833","kind":"arxiv","version":1}},"canonical_sha256":"4b39560afcbf214c1e55b389aabf1cb7f43cbc62c535ab5672ba19b9bf7636e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b39560afcbf214c1e55b389aabf1cb7f43cbc62c535ab5672ba19b9bf7636e7","first_computed_at":"2026-07-05T01:05:58.048019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:58.048019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nlRKNzbjnaFhbQfyD+VX+XmTkkopW9COELvbXkTAvOek5yr34MR4X9gxjbLAr64pUAKxW3K6qCs1GSnkxb7kBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:58.048586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.12833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4897c34beda535961570ecec6779f0fb1cffee8776ee276b2aabc1154532f287","sha256:9853c98eeba8af3a4f072ac5ec12c011bc1be0ffbc3ff471a6843d92a8113330"],"state_sha256":"ff4161a4460b2e1e779d1bc797cb5978a6a3222f0917bd5173e90412287ef1a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7OI2xT+PusfffhncaUA885m1nny6zkSKUxWCKGygVV2ZF2Xmrr6MyG2NHtap4qwJ81K4dFq1wjb8j2lab2jgDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:57:36.156595Z","bundle_sha256":"a27c73877bdeb4237a539472d7b5a072340db474e40662e03b25be84ed63b94b"}}