{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CZEWUFWFVSOBIKV5EVOFBFOZ6D","short_pith_number":"pith:CZEWUFWF","schema_version":"1.0","canonical_sha256":"16496a16c5ac9c142abd255c5095d9f0c9eb2c181cb2f5c27f2824a423bfa055","source":{"kind":"arxiv","id":"1909.01136","version":5},"attestation_state":"computed","paper":{"title":"Pre-training A Neural Language Model Improves The Sample Efficiency of an Emergency Room Classification Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Binbin Xu, C\\'edric Gil-Jardin\\'e, Emmanuel Lagarde, Eric Tellier, Frantz Thiessard, Marta Avalos","submitted_at":"2019-08-30T17:25:06Z","abstract_excerpt":"To build a French national electronic injury surveillance system based on emergency room visits, we aim to develop a coding system to classify their causes from clinical notes in free-text. Supervised learning techniques have shown good results in this area but require a large amount of expert annotated dataset which is time consuming and costly to obtain. We hypothesize that the Natural Language Processing Transformer model incorporating a generative self-supervised pre-training step can significantly reduce the required number of annotated samples for supervised fine-tuning. In this prelimin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1909.01136","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T17:25:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b2cd20d614aa2f39fa67e81b0fac58d554bd184c70fb76d0b0182e84308a0409","abstract_canon_sha256":"ca34d22b42cc1941015352ec08beb61d10c30ce5ba2606fa5791de8375193712"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:52.321766Z","signature_b64":"erew67VTHIi2PQTwfpRBAVcPAfaiWCT0rwGGn6ZwhGVk3TCmqFceOIjT49RWIyhqe+mBW2IFj38C0UBzOlmGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16496a16c5ac9c142abd255c5095d9f0c9eb2c181cb2f5c27f2824a423bfa055","last_reissued_at":"2026-07-05T02:29:52.321333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:52.321333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training A Neural Language Model Improves The Sample Efficiency of an Emergency Room Classification Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Binbin Xu, C\\'edric Gil-Jardin\\'e, Emmanuel Lagarde, Eric Tellier, Frantz Thiessard, Marta Avalos","submitted_at":"2019-08-30T17:25:06Z","abstract_excerpt":"To build a French national electronic injury surveillance system based on emergency room visits, we aim to develop a coding system to classify their causes from clinical notes in free-text. Supervised learning techniques have shown good results in this area but require a large amount of expert annotated dataset which is time consuming and costly to obtain. We hypothesize that the Natural Language Processing Transformer model incorporating a generative self-supervised pre-training step can significantly reduce the required number of annotated samples for supervised fine-tuning. In this prelimin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01136","kind":"arxiv","version":5},"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/1909.01136/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1909.01136","created_at":"2026-07-05T02:29:52.321396+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01136v5","created_at":"2026-07-05T02:29:52.321396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01136","created_at":"2026-07-05T02:29:52.321396+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZEWUFWFVSOB","created_at":"2026-07-05T02:29:52.321396+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZEWUFWFVSOBIKV5","created_at":"2026-07-05T02:29:52.321396+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZEWUFWF","created_at":"2026-07-05T02:29:52.321396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D","json":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D.json","graph_json":"https://pith.science/api/pith-number/CZEWUFWFVSOBIKV5EVOFBFOZ6D/graph.json","events_json":"https://pith.science/api/pith-number/CZEWUFWFVSOBIKV5EVOFBFOZ6D/events.json","paper":"https://pith.science/paper/CZEWUFWF"},"agent_actions":{"view_html":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D","download_json":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D.json","view_paper":"https://pith.science/paper/CZEWUFWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01136&json=true","fetch_graph":"https://pith.science/api/pith-number/CZEWUFWFVSOBIKV5EVOFBFOZ6D/graph.json","fetch_events":"https://pith.science/api/pith-number/CZEWUFWFVSOBIKV5EVOFBFOZ6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/action/storage_attestation","attest_author":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/action/author_attestation","sign_citation":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/action/citation_signature","submit_replication":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/action/replication_record"}},"created_at":"2026-07-05T02:29:52.321396+00:00","updated_at":"2026-07-05T02:29:52.321396+00:00"}