{"id":"W4245139197","doi":"10.26434/chemrxiv.11930004.v3","title":"Computer Vision for Recognition of Materials and Vessels in Chemistry Lab Settings and the Vector-LabPics Dataset","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Task (project management); Segmentation; Market segmentation; Support vector machine; Machine learning; Pattern recognition (psychology); Computer vision; Engineering","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":[0.00114059,0.004740021,0.001766265,0.003381724,0.0009195117,0.001951949,0.004587965,0.0035795,0.01269665],"category_scores_gemma":[0.002266799,0.000816302,0.002200691,0.003963631,0.0007789035,0.001995172,0.001943228,0.002785795,0.02200333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002285285,"about_ca_system_score_gemma":0.001894664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02105522,"about_ca_topic_score_gemma":0.03414436,"domain_scores_codex":[0.9981295,0.0002158624,0.0001429135,0.0006215476,0.0005669491,0.0003231615],"domain_scores_gemma":[0.9990258,0.0001370018,0.00009158006,0.0003556424,0.0002397555,0.0001502174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007273356,0.0009052188,0.003585262,0.001787071,0.0002185168,0.0004135134,0.00007170499,0.007601259,0.007368075,0.001543014,0.9114743,0.06430469],"study_design_scores_gemma":[0.001089873,0.0007846605,0.0351886,0.0004491367,0.0001941052,0.001531968,0.0004393823,0.1116754,0.03175386,0.00750824,0.809096,0.0002888465],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0256789,0.002316357,0.007369683,0.0008590983,0.0004833131,0.0007305699,0.9301728,0.02241558,0.009973782],"genre_scores_gemma":[0.01104296,0.0002719835,0.008674405,0.0001425359,0.00003208952,0.0002676425,0.9778811,0.0002468282,0.001440568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02105522,"threshold_uncertainty_score":0.04247451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02524905302689847,"score_gpt":0.2500276979038329,"score_spread":0.2247786448769345,"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."}}