{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3IWKEWILI67LU2O46G3YAVB2OM","short_pith_number":"pith:3IWKEWIL","canonical_record":{"source":{"id":"2304.00958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T13:25:53Z","cross_cats_sorted":[],"title_canon_sha256":"ad8d65d0e83d9559f5a9bc51f98c86cb46f6ac52617e97c61dbda7948c4390c9","abstract_canon_sha256":"ebb722a814c945d1fab56b969a5b80de80a202cd4c5f62101ab87c0d8c9d85ae"},"schema_version":"1.0"},"canonical_sha256":"da2ca2590b47beba69dcf1b780543a731f4073436b026e915eb68f62cd4f00e4","source":{"kind":"arxiv","id":"2304.00958","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00958","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00958v2","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00958","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"3IWKEWILI67L","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"3IWKEWILI67LU2O4","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"3IWKEWIL","created_at":"2026-07-05T06:07:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3IWKEWILI67LU2O46G3YAVB2OM","target":"record","payload":{"canonical_record":{"source":{"id":"2304.00958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T13:25:53Z","cross_cats_sorted":[],"title_canon_sha256":"ad8d65d0e83d9559f5a9bc51f98c86cb46f6ac52617e97c61dbda7948c4390c9","abstract_canon_sha256":"ebb722a814c945d1fab56b969a5b80de80a202cd4c5f62101ab87c0d8c9d85ae"},"schema_version":"1.0"},"canonical_sha256":"da2ca2590b47beba69dcf1b780543a731f4073436b026e915eb68f62cd4f00e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:10.038389Z","signature_b64":"gSVMGNuzv/hFA+6J2yBgvElXwjuVV3nACqNtSmXqijKlT4iHfF8VUHrpcLvd2cj0hcfx4fFaz91O+FxozaawBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da2ca2590b47beba69dcf1b780543a731f4073436b026e915eb68f62cd4f00e4","last_reissued_at":"2026-07-05T06:07:10.037909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:10.037909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.00958","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:07:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlbmvO2rO9u4wTIm6UmSjPkdYEE3/tYc4xZXVSqMrRZpn0C3FeadzbN/yT0Be6iM54ARs8aP1VSVshDXIwktDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:47:02.402454Z"},"content_sha256":"eee553b0110df6dd888761f816491ec4721849866e1dc7b54060110594ec892e","schema_version":"1.0","event_id":"sha256:eee553b0110df6dd888761f816491ec4721849866e1dc7b54060110594ec892e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3IWKEWILI67LU2O46G3YAVB2OM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrien Bazoge, B\\'eatrice Daille, Emmanuel Morin, Mickael Rouvier, Pierre-Antoine Gourraud, Richard Dufour, Yanis Labrak","submitted_at":"2023-04-03T13:25:53Z","abstract_excerpt":"In recent years, pre-trained language models (PLMs) achieve the best performance on a wide range of natural language processing (NLP) tasks. While the first models were trained on general domain data, specialized ones have emerged to more effectively treat specific domains. In this paper, we propose an original study of PLMs in the medical domain on French language. We compare, for the first time, the performance of PLMs trained on both public data from the web and private data from healthcare establishments. We also evaluate different learning strategies on a set of biomedical tasks. In parti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00958","kind":"arxiv","version":2},"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/2304.00958/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":"2026-07-05T06:07:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WiMVSo55SiNQHqt0gc/HJxxH7V9KhDwRtk/iIxSyusZ8AmeY2s3VSj3WcZYU9fG0AzdouIpHbAybEGwxOYyzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:47:02.403020Z"},"content_sha256":"a2365064cd56170d15651529271e846c7a249b769e274df416b28a18d456c9d1","schema_version":"1.0","event_id":"sha256:a2365064cd56170d15651529271e846c7a249b769e274df416b28a18d456c9d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IWKEWILI67LU2O46G3YAVB2OM/bundle.json","state_url":"https://pith.science/pith/3IWKEWILI67LU2O46G3YAVB2OM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IWKEWILI67LU2O46G3YAVB2OM/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":"2026-08-23T14:47:02Z","links":{"resolver":"https://pith.science/pith/3IWKEWILI67LU2O46G3YAVB2OM","bundle":"https://pith.science/pith/3IWKEWILI67LU2O46G3YAVB2OM/bundle.json","state":"https://pith.science/pith/3IWKEWILI67LU2O46G3YAVB2OM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IWKEWILI67LU2O46G3YAVB2OM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3IWKEWILI67LU2O46G3YAVB2OM","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":"ebb722a814c945d1fab56b969a5b80de80a202cd4c5f62101ab87c0d8c9d85ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T13:25:53Z","title_canon_sha256":"ad8d65d0e83d9559f5a9bc51f98c86cb46f6ac52617e97c61dbda7948c4390c9"},"schema_version":"1.0","source":{"id":"2304.00958","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00958","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00958v2","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00958","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"3IWKEWILI67L","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"3IWKEWILI67LU2O4","created_at":"2026-07-05T06:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"3IWKEWIL","created_at":"2026-07-05T06:07:10Z"}],"graph_snapshots":[{"event_id":"sha256:a2365064cd56170d15651529271e846c7a249b769e274df416b28a18d456c9d1","target":"graph","created_at":"2026-07-05T06:07:10Z","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/2304.00958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, pre-trained language models (PLMs) achieve the best performance on a wide range of natural language processing (NLP) tasks. While the first models were trained on general domain data, specialized ones have emerged to more effectively treat specific domains. In this paper, we propose an original study of PLMs in the medical domain on French language. We compare, for the first time, the performance of PLMs trained on both public data from the web and private data from healthcare establishments. We also evaluate different learning strategies on a set of biomedical tasks. In parti","authors_text":"Adrien Bazoge, B\\'eatrice Daille, Emmanuel Morin, Mickael Rouvier, Pierre-Antoine Gourraud, Richard Dufour, Yanis Labrak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T13:25:53Z","title":"DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00958","kind":"arxiv","version":2},"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:eee553b0110df6dd888761f816491ec4721849866e1dc7b54060110594ec892e","target":"record","created_at":"2026-07-05T06:07:10Z","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":"ebb722a814c945d1fab56b969a5b80de80a202cd4c5f62101ab87c0d8c9d85ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T13:25:53Z","title_canon_sha256":"ad8d65d0e83d9559f5a9bc51f98c86cb46f6ac52617e97c61dbda7948c4390c9"},"schema_version":"1.0","source":{"id":"2304.00958","kind":"arxiv","version":2}},"canonical_sha256":"da2ca2590b47beba69dcf1b780543a731f4073436b026e915eb68f62cd4f00e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da2ca2590b47beba69dcf1b780543a731f4073436b026e915eb68f62cd4f00e4","first_computed_at":"2026-07-05T06:07:10.037909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:10.037909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gSVMGNuzv/hFA+6J2yBgvElXwjuVV3nACqNtSmXqijKlT4iHfF8VUHrpcLvd2cj0hcfx4fFaz91O+FxozaawBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:10.038389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00958","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eee553b0110df6dd888761f816491ec4721849866e1dc7b54060110594ec892e","sha256:a2365064cd56170d15651529271e846c7a249b769e274df416b28a18d456c9d1"],"state_sha256":"7e165f9f88694bf5bfa81d726e89dccdd7e7afaf4e3d12abafec6b7df82c702c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+nBz2iU/A/bmg8583wyXw4NLbpGObgRe709Wc/i/0SnkVjp/9fnDS6aXpxYpsgLIk227uNOvVOuELK4J9+jDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T14:47:02.406420Z","bundle_sha256":"0fbbe9c67926816f83c9fa780da9afe45f95ea26fb8fc1eb69b636d43f1e97bd"}}