{"id":"W4415870502","doi":"10.1007/s11036-025-02479-0","title":"Seeds Image – Introduction and Baseline Experiments with the New Labeled Benchmark for Machine Learning Tasks","year":2025,"lang":"en","type":"article","venue":"Mobile Networks and Applications","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Set (abstract data type); Data set; Baseline (sea); Image (mathematics); Artificial neural network; Object (grammar); Pattern recognition (psychology); Deep learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.00280246,0.003123727,0.001304707,0.001964176,0.001120466,0.00173587,0.003185618,0.002650177,0.01051763],"category_scores_gemma":[0.01020635,0.000496407,0.001436082,0.002101567,0.001475189,0.003190424,0.001972372,0.002836678,0.006195846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00173186,"about_ca_system_score_gemma":0.001554441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01466323,"about_ca_topic_score_gemma":0.0195587,"domain_scores_codex":[0.9971774,0.0007609016,0.0002603239,0.000797911,0.0007500711,0.0002533463],"domain_scores_gemma":[0.9948754,0.001458524,0.0002744239,0.00165574,0.001300411,0.0004354567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01008259,0.01118872,0.01192507,0.003980875,0.001283804,0.001019401,0.0004731627,0.08861238,0.03286061,0.008624118,0.3558517,0.4740975],"study_design_scores_gemma":[0.00429872,0.009447999,0.03989535,0.001025965,0.0007479451,0.002985427,0.001832394,0.5499412,0.1010811,0.03960026,0.2486968,0.0004469063],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6761166,0.01400813,0.09703169,0.003862654,0.005451191,0.004538567,0.1029259,0.02815231,0.06791302],"genre_scores_gemma":[0.4448745,0.002834486,0.1980583,0.002213638,0.0008983283,0.002715017,0.3165823,0.003546145,0.02827728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01466323,"threshold_uncertainty_score":0.03518498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004022319303019252,"score_gpt":0.2121795176663746,"score_spread":0.2081571983633553,"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."}}