{"id":"W4393182994","doi":"10.2139/ssrn.4772622","title":"Label Efficient Plant Damage Estimation Using Pixel-Level Contrastive Learning","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Estimation; Pixel; Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Economics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005637065,0.0007471243,0.0008580838,0.001216044,0.0003054246,0.00114472,0.001200358,0.001763057,0.002093892],"category_scores_gemma":[0.001311758,0.000367734,0.0006953643,0.0007692189,0.0005882467,0.001266642,0.001202731,0.001120421,0.001824067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006982457,"about_ca_system_score_gemma":0.000539816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002078594,"about_ca_topic_score_gemma":0.005187914,"domain_scores_codex":[0.99962,0.0000370398,0.0000110524,0.0001533279,0.0001176111,0.00006092881],"domain_scores_gemma":[0.9992229,0.000203883,0.0001118525,0.0002026439,0.0002189562,0.00003980641],"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":[0.0004935176,0.0003064576,0.006475922,0.0002970006,0.0001110779,0.0001276727,0.00009720149,0.1434878,0.1990968,0.004862691,0.004273196,0.6403707],"study_design_scores_gemma":[0.000009060332,0.00007335527,0.003311711,0.00001610524,0.00002956022,0.000103801,0.0000170327,0.9499518,0.0394852,0.005423678,0.001563076,0.00001556403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05333646,0.0003059094,0.9420729,0.0001630291,0.00005679591,0.00004749184,0.0003415995,0.001728524,0.001947232],"genre_scores_gemma":[0.5476615,0.0004058638,0.4396329,0.0002548969,0.0001314412,0.0001151022,0.001588835,0.0004155256,0.009793928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002093892,"threshold_uncertainty_score":0.007004738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02658014721521727,"score_gpt":0.2448379070398146,"score_spread":0.2182577598245974,"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."}}