{"id":"W2908935617","doi":"10.1371/journal.pone.0212103","title":"Automating the search for a patent’s prior art with a full text similarity search","year":2019,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Intellectual Property and Patents","field":"Business, Management and Accounting","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Berlin Center for Machine Learning; Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Novelty; Process (computing); Similarity (geometry); Information retrieval; Quality (philosophy); Invention; Domain (mathematical analysis); Symbol (formal); Patent application; Feature (linguistics); Nearest neighbor search; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001740957,0.0008673829,0.001264808,0.01721855,0.001018337,0.002621393,0.001220114,0.001682591,0.008461379],"category_scores_gemma":[0.0110289,0.0002672932,0.001317582,0.007011434,0.0005153455,0.004010337,0.001495113,0.0006052052,0.003513565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008009643,"about_ca_system_score_gemma":0.002371425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003422407,"about_ca_topic_score_gemma":0.004146421,"domain_scores_codex":[0.9974636,0.0005132825,0.0004359054,0.0005271357,0.0009065103,0.000153499],"domain_scores_gemma":[0.9922735,0.004635588,0.0008948969,0.000643075,0.001353059,0.0001998212],"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":[0.0005657111,0.0006474199,0.006832661,0.002267157,0.000250186,0.001549442,0.0006134491,0.005198944,0.06823605,0.008165619,0.02048476,0.8851888],"study_design_scores_gemma":[0.0005186673,0.002875539,0.06703106,0.0008112674,0.001286882,0.01273742,0.003581467,0.4995766,0.1965273,0.04561292,0.1689623,0.0004787035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.342126,0.01008382,0.5897115,0.001756557,0.0004517106,0.001856122,0.01278899,0.0151078,0.02611746],"genre_scores_gemma":[0.4478703,0.002225467,0.5284774,0.0002518097,0.0002973496,0.0003536732,0.01484965,0.0003853423,0.005289004],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01721855,"threshold_uncertainty_score":0.02830613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2542441161148024,"score_gpt":0.2361494102552961,"score_spread":0.01809470585950632,"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."}}