{"id":"W4405854973","doi":"10.1016/j.atech.2024.100764","title":"Optimizing data collection requirements for machine learning models in wild blueberry automation through the application of DALL-E 2","year":2024,"lang":"en","type":"article","venue":"Smart Agricultural Technology","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automation; Computer science; Data collection; Artificial intelligence; Machine learning; Engineering; Mathematics; Statistics; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002800653,0.0001849063,0.0002251879,0.00003994857,0.0002638209,0.00006195392,0.0005843085,0.0002388295,0.00001048147],"category_scores_gemma":[0.00004855357,0.00005743941,0.00007507196,0.001606848,0.0000730887,0.0005855948,0.0002259988,0.0002830137,0.00000734278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006438437,"about_ca_system_score_gemma":0.000009135913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005757402,"about_ca_topic_score_gemma":0.002682051,"domain_scores_codex":[0.9986071,0.00005101837,0.0003913699,0.0004883722,0.0001798059,0.0002823342],"domain_scores_gemma":[0.9994351,0.0001752364,0.000138479,0.0001375047,0.00009371589,0.0000199089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006432786,0.0002254048,0.002854418,0.0001164823,0.0001477066,0.000003563684,0.001177631,0.002440674,0.8511772,0.02660077,0.008222752,0.1069691],"study_design_scores_gemma":[0.001580026,0.001687534,0.05223761,0.0007649309,0.0003996417,0.0003039853,0.01194523,0.5134464,0.0520286,0.06275856,0.300952,0.001895467],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9762829,0.002211434,0.002220374,0.01593209,0.0003537984,0.001545132,0.0000746635,0.0006697839,0.000709841],"genre_scores_gemma":[0.9967598,0.0001426169,0.001438552,0.00003612386,0.0001690582,0.0002235731,0.0009740201,0.000002119881,0.0002541162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7991486,"threshold_uncertainty_score":0.2342311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04896034927497259,"score_gpt":0.2710106054721751,"score_spread":0.2220502561972025,"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."}}