{"id":"W4393442459","doi":"10.5281/zenodo.4016857","title":"A Comparison of Natural Language Understanding Services for Software Bots","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Software; Natural (archaeology); Software engineering; Programming language; History; Archaeology","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002638424,0.0002250953,0.0003354658,0.000288234,0.001175874,0.000976534,0.003434474,0.000125275,0.00099908],"category_scores_gemma":[0.0004058598,0.0002427157,0.0001112589,0.0006300632,0.00007499657,0.0004871986,0.002666176,0.0005232533,0.002216778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002399574,"about_ca_system_score_gemma":0.000009467665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005069027,"about_ca_topic_score_gemma":0.000006814958,"domain_scores_codex":[0.9980097,0.0001919446,0.0004125217,0.0005713069,0.0004780687,0.0003364125],"domain_scores_gemma":[0.9981185,0.0001480318,0.0004054299,0.0007302832,0.0004544292,0.000143376],"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":[0.00003471571,0.00008835,4.576777e-7,0.0007124858,0.00007346216,0.000006910955,0.00184535,0.00002226042,0.0001404522,0.0004525474,0.9924013,0.004221715],"study_design_scores_gemma":[0.0002980028,0.0002236299,0.000008465831,0.0002003842,0.00003610771,0.00002970293,0.001546142,0.004002344,0.0001261284,0.0001023265,0.9931973,0.000229486],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00004805077,0.0002269596,0.124277,0.0007851204,0.0005250141,0.0007056327,0.8721015,0.0008048458,0.0005259638],"genre_scores_gemma":[0.01184844,0.00002608489,0.002865473,0.0002997495,0.0001939994,1.248694e-7,0.9841028,0.0005954325,0.00006782583],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1214115,"threshold_uncertainty_score":0.9999142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0710544871344522,"score_gpt":0.3242120747320547,"score_spread":0.2531575875976025,"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."}}