{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CZEWUFWFVSOBIKV5EVOFBFOZ6D","short_pith_number":"pith:CZEWUFWF","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"},"canonical_sha256":"16496a16c5ac9c142abd255c5095d9f0c9eb2c181cb2f5c27f2824a423bfa055","source":{"kind":"arxiv","id":"1909.01136","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01136","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01136v5","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01136","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"pith_short_12","alias_value":"CZEWUFWFVSOB","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"CZEWUFWFVSOBIKV5","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"CZEWUFWF","created_at":"2026-07-05T02:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CZEWUFWFVSOBIKV5EVOFBFOZ6D","target":"record","payload":{"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"},"canonical_sha256":"16496a16c5ac9c142abd255c5095d9f0c9eb2c181cb2f5c27f2824a423bfa055","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"},"source_kind":"arxiv","source_id":"1909.01136","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:29:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pIAA0wQz8PAXiEBJkJVKbWC0vpqIoOUDgpI8SvBLQUpC3qNHnCRWhN6H2+y4vwZNVkjtEhgsK/sNfgd/Ov1VBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:51:07.978468Z"},"content_sha256":"ec3b830d1f37168718fcf505c0fdf459bc19ab25bfbc39fb1573da8d3ad6dab4","schema_version":"1.0","event_id":"sha256:ec3b830d1f37168718fcf505c0fdf459bc19ab25bfbc39fb1573da8d3ad6dab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CZEWUFWFVSOBIKV5EVOFBFOZ6D","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:29:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nLNTU6zgxxuelT+Nr/J/fe4U896biDkAjBCkF/kBCt8PflVBhBBoFxbXzU37pVBqtumvqZuee+fYEY9N3dTkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:51:07.979365Z"},"content_sha256":"d4347b0af43129d7e6b30212d55a52ecfefcb4724b0f04a7d387de2256c0dfda","schema_version":"1.0","event_id":"sha256:d4347b0af43129d7e6b30212d55a52ecfefcb4724b0f04a7d387de2256c0dfda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/bundle.json","state_url":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/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":"2026-08-15T14:51:07Z","links":{"resolver":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D","bundle":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/bundle.json","state":"https://pith.science/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZEWUFWFVSOBIKV5EVOFBFOZ6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CZEWUFWFVSOBIKV5EVOFBFOZ6D","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":"ca34d22b42cc1941015352ec08beb61d10c30ce5ba2606fa5791de8375193712","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T17:25:06Z","title_canon_sha256":"b2cd20d614aa2f39fa67e81b0fac58d554bd184c70fb76d0b0182e84308a0409"},"schema_version":"1.0","source":{"id":"1909.01136","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01136","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01136v5","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01136","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"pith_short_12","alias_value":"CZEWUFWFVSOB","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"CZEWUFWFVSOBIKV5","created_at":"2026-07-05T02:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"CZEWUFWF","created_at":"2026-07-05T02:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:d4347b0af43129d7e6b30212d55a52ecfefcb4724b0f04a7d387de2256c0dfda","target":"graph","created_at":"2026-07-05T02:29:52Z","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/1909.01136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Binbin Xu, C\\'edric Gil-Jardin\\'e, Emmanuel Lagarde, Eric Tellier, Frantz Thiessard, Marta Avalos","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T17:25:06Z","title":"Pre-training A Neural Language Model Improves The Sample Efficiency of an Emergency Room Classification Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01136","kind":"arxiv","version":5},"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:ec3b830d1f37168718fcf505c0fdf459bc19ab25bfbc39fb1573da8d3ad6dab4","target":"record","created_at":"2026-07-05T02:29:52Z","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":"ca34d22b42cc1941015352ec08beb61d10c30ce5ba2606fa5791de8375193712","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T17:25:06Z","title_canon_sha256":"b2cd20d614aa2f39fa67e81b0fac58d554bd184c70fb76d0b0182e84308a0409"},"schema_version":"1.0","source":{"id":"1909.01136","kind":"arxiv","version":5}},"canonical_sha256":"16496a16c5ac9c142abd255c5095d9f0c9eb2c181cb2f5c27f2824a423bfa055","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16496a16c5ac9c142abd255c5095d9f0c9eb2c181cb2f5c27f2824a423bfa055","first_computed_at":"2026-07-05T02:29:52.321333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:52.321333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erew67VTHIi2PQTwfpRBAVcPAfaiWCT0rwGGn6ZwhGVk3TCmqFceOIjT49RWIyhqe+mBW2IFj38C0UBzOlmGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:52.321766Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01136","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec3b830d1f37168718fcf505c0fdf459bc19ab25bfbc39fb1573da8d3ad6dab4","sha256:d4347b0af43129d7e6b30212d55a52ecfefcb4724b0f04a7d387de2256c0dfda"],"state_sha256":"a7a44721cbd2b3a69ecd7637db5a918dd6587213196904f8e8fb1c8c55ed5adc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jL09+4LmrtfWRzAoczksNumIl23u8XGEl5e1kH7i/txVxP0hYwq3iIruHGBA7RjA8+gOM6G3ZjjIEk2ZOfFWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:51:07.984573Z","bundle_sha256":"220b5a4c89cb9bdb9fb3700a97e495e1006c5268a016882f28f613c41eceb135"}}