{"id":"W6925962417","doi":"10.21227/107d-hk82","title":"CLEAR: A Dataset for Compositional Language and Elementary Acoustic Reasoning","year":2019,"lang":"en","type":"dataset","venue":"IEEE DataPort","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Task (project management); Acoustic model; Code (set theory); Order (exchange); Scheme (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":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008517641,0.0002639038,0.0004184992,0.0001990084,0.0001821411,0.0003221355,0.001675201,0.0001604945,0.0001237772],"category_scores_gemma":[0.0001348105,0.0002526735,0.00009169747,0.000219075,0.00008963853,0.0004741987,0.0007350749,0.0004015149,0.0001990857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006196558,"about_ca_system_score_gemma":0.0002111538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004389118,"about_ca_topic_score_gemma":0.00009530596,"domain_scores_codex":[0.9975773,0.00008055634,0.0003673637,0.0009235884,0.0006293982,0.0004217826],"domain_scores_gemma":[0.9972495,0.0004838007,0.0001617505,0.001868821,0.00007631424,0.0001597997],"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":[0.00002209739,0.00005863049,0.0000253324,0.0002922851,0.000109176,0.00005721027,0.00001231153,0.00002863656,0.00006444514,0.00000874826,0.9984444,0.0008767134],"study_design_scores_gemma":[0.0003293009,0.000124372,0.00005384192,0.00009367941,0.0001070102,0.00005169809,0.00002172068,0.005331181,0.00003918623,0.00003367946,0.9934984,0.0003159377],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001196973,0.000162377,0.03693001,0.0001287041,0.000255962,0.0004227776,0.9619477,0.00003069637,0.000002121991],"genre_scores_gemma":[0.00006158745,0.0001459712,0.007184009,0.0005745209,0.0002295612,0.0000576714,0.9916957,0.00001195342,0.00003901266],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02974806,"threshold_uncertainty_score":0.9999925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02590827152566443,"score_gpt":0.3388993667689945,"score_spread":0.3129910952433301,"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."}}