{"id":"W4234247114","doi":"10.2139/ssrn.3338718","title":"Sense and Similarity: Automating Legal Text Comparison","year":2019,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sense (electronics); Similarity (geometry); Computer science; Natural language processing; Information retrieval; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003170718,0.0001123242,0.0001941848,0.00006863583,0.0007870406,0.0002521116,0.0001267262,0.000108786,0.0001992724],"category_scores_gemma":[0.0002352079,0.0001085089,0.00006494913,0.0001856128,0.0002077184,0.0004496622,0.00004343971,0.001477431,0.0002110328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006087538,"about_ca_system_score_gemma":0.00150864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001796444,"about_ca_topic_score_gemma":0.01587832,"domain_scores_codex":[0.9969923,0.0002423742,0.0003068636,0.0001858332,0.0004152186,0.001857334],"domain_scores_gemma":[0.999322,0.0001817119,0.0001669574,0.0001121863,0.00009367079,0.0001234819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000207189,0.000041421,0.01420406,0.000004019508,0.00004224296,0.000008711003,0.006331164,0.00009185234,0.0004015605,0.9354368,0.0001562168,0.04326117],"study_design_scores_gemma":[0.0005131548,0.0007172772,0.0012888,0.0001049005,0.00008121779,0.0007976732,0.1953972,0.01141609,0.000879514,0.5802875,0.2076091,0.0009075831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9642792,0.000785208,0.001803896,0.002489748,0.0004476723,0.0001705637,6.256471e-7,0.00008066194,0.02994246],"genre_scores_gemma":[0.9954231,0.0004782081,0.0001748055,0.0001638688,0.0004030089,0.000001099272,4.317015e-7,0.00001415587,0.003341316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3551494,"threshold_uncertainty_score":0.8860475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01921546106449809,"score_gpt":0.334922178260661,"score_spread":0.3157067171961629,"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."}}