{"id":"W4308297793","doi":"10.1016/j.joi.2022.101344","title":"Detecting emerging technologies and their evolution using deep learning and weak signal analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Innovation Diffusion and Forecasting","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"","keywords":"Emerging technologies; Prosperity; Computer science; Data science; Field (mathematics); Identification (biology); Emerging markets; Domain (mathematical analysis); Risk analysis (engineering); Management science; Artificial intelligence; Business; Engineering; Political science; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005930937,0.00009910073,0.0002974665,0.006650744,0.0009387701,0.0002403844,0.0002416024,0.00005016886,0.00009188963],"category_scores_gemma":[0.008182838,0.00007066798,0.0001136166,0.01262571,0.00005884217,0.0005296748,0.0004072672,0.0005974965,4.183141e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001310949,"about_ca_system_score_gemma":0.00005175743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006483559,"about_ca_topic_score_gemma":0.000003430961,"domain_scores_codex":[0.9977144,0.00008478769,0.0009610798,0.0001279178,0.0009315129,0.0001803048],"domain_scores_gemma":[0.9967723,0.0009725893,0.001505815,0.00008189143,0.0006247219,0.00004266522],"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":[0.00002400362,0.00001048678,0.1638108,0.000003111984,0.00007825355,0.00000394933,0.0009805617,0.02349165,0.001421632,0.0003219697,0.00001250353,0.8098411],"study_design_scores_gemma":[0.0004091769,0.0002535004,0.01309305,0.00001031672,0.00008198345,0.0004332488,0.1617035,0.815938,0.0003394486,0.002783739,0.004783438,0.0001705767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8011331,0.0007728072,0.1974352,0.00006890304,0.0001178021,0.00002994034,9.476346e-7,0.00001866387,0.0004226834],"genre_scores_gemma":[0.9946579,0.00003587163,0.005202374,0.00002340722,0.00002679591,4.765734e-7,2.857891e-7,0.000004652689,0.00004827767],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8096705,"threshold_uncertainty_score":0.9796212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06226207505265736,"score_gpt":0.3336898294886794,"score_spread":0.2714277544360221,"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."}}