{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7BB4RU3Q5ZOB42ZATJTW3Y5JHR","short_pith_number":"pith:7BB4RU3Q","canonical_record":{"source":{"id":"1901.08746","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-25T05:57:24Z","cross_cats_sorted":[],"title_canon_sha256":"e787614c85b70b4cb1d7c58118162f15d1a2a499ac6683313aac087ee38ff65f","abstract_canon_sha256":"f8686f53d96e7edcca0a7d8c65491a1ffa6bc7897b838e3bc5584e1ca6c59e80"},"schema_version":"1.0"},"canonical_sha256":"f843c8d370ee5c1e6b209a676de3a93c5d0b310b3f408e3234fc3b032ecd22b3","source":{"kind":"arxiv","id":"1901.08746","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08746","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08746v4","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08746","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"7BB4RU3Q5ZOB","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"7BB4RU3Q5ZOB42ZA","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"7BB4RU3Q","created_at":"2026-07-05T00:13:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7BB4RU3Q5ZOB42ZATJTW3Y5JHR","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08746","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-25T05:57:24Z","cross_cats_sorted":[],"title_canon_sha256":"e787614c85b70b4cb1d7c58118162f15d1a2a499ac6683313aac087ee38ff65f","abstract_canon_sha256":"f8686f53d96e7edcca0a7d8c65491a1ffa6bc7897b838e3bc5584e1ca6c59e80"},"schema_version":"1.0"},"canonical_sha256":"f843c8d370ee5c1e6b209a676de3a93c5d0b310b3f408e3234fc3b032ecd22b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:01.274861Z","signature_b64":"sBUjO7EpEuviC37z9iaOaVfIqSykbyEU2h4c2KQ13dmAzXK9tF5vx/hTOqgDsufwRbN/+QU4u4V1GR5z4lMZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f843c8d370ee5c1e6b209a676de3a93c5d0b310b3f408e3234fc3b032ecd22b3","last_reissued_at":"2026-07-05T00:13:01.274352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:01.274352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08746","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rkirz+K3jYfFdlEjt+s6/99DWNkP/JWxsMLKTgJeOGGF5YUBq4Pzm/aoz8bdD269jJwL3f/BuIfF6EGR6zfXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:52:57.070028Z"},"content_sha256":"d9735570c4e74d6384dd6b688710ecd0c03e91a52d58a78896be89f6a2c3ab61","schema_version":"1.0","event_id":"sha256:d9735570c4e74d6384dd6b688710ecd0c03e91a52d58a78896be89f6a2c3ab61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7BB4RU3Q5ZOB42ZATJTW3Y5JHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chan Ho So, Donghyeon Kim, Jaewoo Kang, Jinhyuk Lee, Sungdong Kim, Sunkyu Kim, WonJin Yoon","submitted_at":"2019-01-25T05:57:24Z","abstract_excerpt":"Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows. With the progress in natural language processing (NLP), extracting valuable information from biomedical literature has gained popularity among researchers, and deep learning has boosted the development of effective biomedical text mining models. However, directly applying the advancements in NLP to biomedical text mining often yields unsatisfactory results due to a word distribution shift from general domain corpora to biomedical corpora. In this article, we investigate how the recent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08746","kind":"arxiv","version":4},"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/1901.08746/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":"2026-07-05T00:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AZiWCbpkAgD2nCjeGpu43QVVN/sYI/psFrAr/3goyUJa2UFfov/QQ+S+nxaq/wiVtyJmUvE4iv+Szc0spl7sDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:52:57.070411Z"},"content_sha256":"8fbc3faf746dc91a66b656a481ef97e5e34aac5daac01902a2161980881cf19d","schema_version":"1.0","event_id":"sha256:8fbc3faf746dc91a66b656a481ef97e5e34aac5daac01902a2161980881cf19d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7BB4RU3Q5ZOB42ZATJTW3Y5JHR/bundle.json","state_url":"https://pith.science/pith/7BB4RU3Q5ZOB42ZATJTW3Y5JHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7BB4RU3Q5ZOB42ZATJTW3Y5JHR/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":"2026-08-21T19:52:57Z","links":{"resolver":"https://pith.science/pith/7BB4RU3Q5ZOB42ZATJTW3Y5JHR","bundle":"https://pith.science/pith/7BB4RU3Q5ZOB42ZATJTW3Y5JHR/bundle.json","state":"https://pith.science/pith/7BB4RU3Q5ZOB42ZATJTW3Y5JHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7BB4RU3Q5ZOB42ZATJTW3Y5JHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7BB4RU3Q5ZOB42ZATJTW3Y5JHR","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":"f8686f53d96e7edcca0a7d8c65491a1ffa6bc7897b838e3bc5584e1ca6c59e80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-25T05:57:24Z","title_canon_sha256":"e787614c85b70b4cb1d7c58118162f15d1a2a499ac6683313aac087ee38ff65f"},"schema_version":"1.0","source":{"id":"1901.08746","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08746","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08746v4","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08746","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"7BB4RU3Q5ZOB","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"7BB4RU3Q5ZOB42ZA","created_at":"2026-07-05T00:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"7BB4RU3Q","created_at":"2026-07-05T00:13:01Z"}],"graph_snapshots":[{"event_id":"sha256:8fbc3faf746dc91a66b656a481ef97e5e34aac5daac01902a2161980881cf19d","target":"graph","created_at":"2026-07-05T00:13:01Z","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/1901.08746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows. With the progress in natural language processing (NLP), extracting valuable information from biomedical literature has gained popularity among researchers, and deep learning has boosted the development of effective biomedical text mining models. However, directly applying the advancements in NLP to biomedical text mining often yields unsatisfactory results due to a word distribution shift from general domain corpora to biomedical corpora. In this article, we investigate how the recent","authors_text":"Chan Ho So, Donghyeon Kim, Jaewoo Kang, Jinhyuk Lee, Sungdong Kim, Sunkyu Kim, WonJin Yoon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-25T05:57:24Z","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08746","kind":"arxiv","version":4},"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:d9735570c4e74d6384dd6b688710ecd0c03e91a52d58a78896be89f6a2c3ab61","target":"record","created_at":"2026-07-05T00:13:01Z","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":"f8686f53d96e7edcca0a7d8c65491a1ffa6bc7897b838e3bc5584e1ca6c59e80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-25T05:57:24Z","title_canon_sha256":"e787614c85b70b4cb1d7c58118162f15d1a2a499ac6683313aac087ee38ff65f"},"schema_version":"1.0","source":{"id":"1901.08746","kind":"arxiv","version":4}},"canonical_sha256":"f843c8d370ee5c1e6b209a676de3a93c5d0b310b3f408e3234fc3b032ecd22b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f843c8d370ee5c1e6b209a676de3a93c5d0b310b3f408e3234fc3b032ecd22b3","first_computed_at":"2026-07-05T00:13:01.274352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:01.274352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sBUjO7EpEuviC37z9iaOaVfIqSykbyEU2h4c2KQ13dmAzXK9tF5vx/hTOqgDsufwRbN/+QU4u4V1GR5z4lMZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:01.274861Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08746","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9735570c4e74d6384dd6b688710ecd0c03e91a52d58a78896be89f6a2c3ab61","sha256:8fbc3faf746dc91a66b656a481ef97e5e34aac5daac01902a2161980881cf19d"],"state_sha256":"05bae619b64b011e95abfac2ee89128daba16a436c383c3c1291a5478a1f8a2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aoezn9sVYMHpwEn3b70iE0+3WLZn4tqWYwosAVpP+QgqFRKRYqISG4ZSfJy0wrYOdFqz6EuwV9v1bbSRyVwdAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:52:57.073054Z","bundle_sha256":"e2a961b9eee7be8a667919653a73a66129481576737979041ed9bd0644545caf"}}