{"id":"W4200126321","doi":"10.5121/csit.2021.112302","title":"Representation Learning and Similarity of Legal Judgements using Citation Networks","year":2021,"lang":"en","type":"article","venue":"Natural Language Processing","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Similarity (geometry); Representation (politics); Computer science; Embedding; Citation; Neglect; Information retrieval; Artificial intelligence; Natural language processing; Psychology; Political science; Law; Image (mathematics); World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003959354,0.00006155133,0.0001074376,0.00004117817,0.0004629574,0.0001427497,0.00005827887,0.00007345399,0.00004932848],"category_scores_gemma":[0.001036482,0.00006541674,0.00002685752,0.0004616165,0.0001577876,0.0005469802,0.00004252859,0.0002102035,5.94588e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005068329,"about_ca_system_score_gemma":0.00009590983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001112836,"about_ca_topic_score_gemma":0.0008218486,"domain_scores_codex":[0.9990057,0.0001809019,0.0001844327,0.000179171,0.0002772425,0.0001725543],"domain_scores_gemma":[0.9993885,0.0001007324,0.0001448896,0.00004654412,0.0002823542,0.00003702642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003029142,0.00003753822,0.02406663,0.00007823526,0.00001968157,0.00004109976,0.03729927,0.002820076,0.02600634,0.00193351,0.00001518523,0.9076521],"study_design_scores_gemma":[0.0002768548,0.00003058693,0.003942134,0.0004029327,0.0001051094,0.0000133246,0.1707176,0.7762547,0.04529522,0.0009337504,0.001531961,0.0004957913],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9729587,0.0129697,0.009479209,0.0002071358,0.000278653,0.000104892,6.387392e-7,0.00005845994,0.003942601],"genre_scores_gemma":[0.9948016,0.00003609024,0.004548863,0.00005107926,0.0001738294,0.000001108734,0.000009417555,0.000006956714,0.000371055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9071563,"threshold_uncertainty_score":0.3560741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04307182975669942,"score_gpt":0.4108038783666981,"score_spread":0.3677320486099987,"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."}}