{"id":"W4253479984","doi":"10.5565/ddd.uab.cat/238990","title":"Cadlaws is built from Canadian legal documents. The corpus contains over 16 milions words in each language and it is composed of documents that are legally equivalent in both languages but not the result of a translation. Cadlaws is built upon enactments co-drafted by two jurists to ensure legal equality of each version, to reflect the concepts, terms and institutions of two legal traditions","year":2021,"lang":"en","type":"dataset","venue":"","topic":"Invertebrate Taxonomy and Ecology","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Linguistics; Natural language processing; Legal document; Artificial intelligence; Law; Political science; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001603882,0.00274301,0.001490486,0.01395676,0.004034734,0.003814151,0.00424984,0.002788177,0.04484778],"category_scores_gemma":[0.01223858,0.0007999425,0.001134467,0.01819318,0.00182096,0.002005014,0.002523362,0.00305078,0.04349458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01455952,"about_ca_system_score_gemma":0.03364135,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.818782,"about_ca_topic_score_gemma":0.9138988,"domain_scores_codex":[0.9972703,0.0003134366,0.0002417846,0.0005492799,0.001179182,0.0004459742],"domain_scores_gemma":[0.9930848,0.002008286,0.0003864889,0.0007091404,0.003190739,0.0006205013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004076069,0.00002236567,0.0005730516,0.0008901354,0.00002135061,0.000070679,0.0001343372,0.0001948765,0.0001619283,0.0009948993,0.9927249,0.004170757],"study_design_scores_gemma":[0.0000698857,0.000006081774,0.003897796,0.0003761144,0.00002754196,0.00006086407,0.0002154438,0.0003178962,0.0002877364,0.0004346328,0.9942675,0.0000384011],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0004119968,0.0003349286,0.0001129532,0.0001828108,0.0000450086,0.00002940142,0.9955103,0.0003857808,0.002986772],"genre_scores_gemma":[0.0006427542,0.0001408849,0.0004292889,0.00005664839,0.000006494791,0.00007716056,0.9973595,0.00007564403,0.001211587],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.181218,"threshold_uncertainty_score":0.3645705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04533844632889702,"score_gpt":0.3340671537370178,"score_spread":0.2887287074081208,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}