{"id":"W4415389009","doi":"10.1016/j.dib.2025.112203","title":"Plastic Pirates Nova Scotia 2024 dataset - citizen science investigation of anthropogenic litter pollution of aquatic environments","year":2025,"lang":"en","type":"article","venue":"Data in Brief","topic":"Microplastics and Plastic Pollution","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Ocean Frontier Institute; Bundesministerium für Bildung und Forschung; Dalhousie University; Christian-Albrechts-Universität zu Kiel","keywords":"Litter; Citizen science; Nova scotia; Marine debris; Plastic pollution; Pollution; Sampling (signal processing); Aquatic ecosystem","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0007853141,0.0008845393,0.0007143241,0.002050449,0.001020635,0.001189143,0.001289038,0.0007554902,0.009293877],"category_scores_gemma":[0.003349086,0.0004554982,0.0007292402,0.003995171,0.0003802725,0.000428306,0.001797981,0.0006554983,0.00645988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003936088,"about_ca_system_score_gemma":0.005757702,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7112772,"about_ca_topic_score_gemma":0.830802,"domain_scores_codex":[0.9992372,0.000127192,0.00008009424,0.0001838628,0.0002186793,0.0001530409],"domain_scores_gemma":[0.9972851,0.0002548313,0.0002958204,0.0004175634,0.001476522,0.0002701853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00049622,0.00008137758,0.1213701,0.002635464,0.0003298267,0.0004622722,0.0005820891,0.002061679,0.002200627,0.001098458,0.8492572,0.01942463],"study_design_scores_gemma":[0.0001967098,0.00006341057,0.3856966,0.001095507,0.0001162675,0.0001740573,0.001343943,0.001979826,0.001121423,0.0006100657,0.6074901,0.0001120822],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006155583,0.0002032484,0.0003007897,0.0001202294,0.00003317991,0.00005984972,0.9909557,0.0001851461,0.001986383],"genre_scores_gemma":[0.01339358,0.0001454253,0.001542634,0.000124985,0.00001172884,0.0002227552,0.9824724,0.00005783649,0.002028641],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2887228,"threshold_uncertainty_score":0.5808462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0211556543788257,"score_gpt":0.2646593028975489,"score_spread":0.2435036485187232,"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."}}