{"id":"W4393365073","doi":"10.26434/chemrxiv-2024-d20px-v2","title":"Beyond Molecular Structure: Critically Assessing Machine Learning for Designing Organic Photovoltaic Materials and Devices","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Division of Materials Research; Office of Naval Research; Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Materials Research Science and Engineering Center, Harvard University; National Science Foundation; Advanced Research Projects Agency; Air Force Office of Scientific Research; University of California, Santa Barbara; Defense Advanced Research Projects Agency; Vector Institute","keywords":"Computer science; Quality (philosophy); Photovoltaic system; Key (lock); Data science; Machine learning; Work (physics); State (computer science); Artificial intelligence; Data mining; Engineering; Electrical 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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002255843,0.0007730688,0.00097638,0.000229573,0.000462793,0.003714995,0.0009245458,0.0005230668,0.001751694],"category_scores_gemma":[0.00194226,0.0007133317,0.0001213732,0.0002152645,0.0003663156,0.0002542456,0.002359049,0.000927194,0.00007129956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273886,"about_ca_system_score_gemma":0.0003217003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009768756,"about_ca_topic_score_gemma":0.00001312114,"domain_scores_codex":[0.9954875,0.0004147231,0.0008631189,0.001780774,0.0005705763,0.0008833772],"domain_scores_gemma":[0.9978973,0.0004574112,0.0004623343,0.0006333495,0.0003119788,0.0002375913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002263157,0.00001457141,0.0002061879,0.002896559,0.00002760185,0.00004394555,0.0002559812,0.0007235437,0.9952592,0.0003779294,0.00004870531,0.0001231078],"study_design_scores_gemma":[0.0002328804,0.00005894785,0.0002018805,0.000660745,0.0002101218,0.00006188436,0.00005315592,0.007601861,0.9592694,0.03070264,0.0001738088,0.0007726825],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977312,0.001964585,0.01612836,0.0003424693,0.002625775,0.0008176611,0.00006420923,0.0005596534,0.0001852443],"genre_scores_gemma":[0.9091861,0.0000220086,0.08945661,0.0003698491,0.0004122149,0.0001184342,0.0001300314,0.000184739,0.0001200596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07332825,"threshold_uncertainty_score":0.9995318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01329208778694779,"score_gpt":0.2859876421197775,"score_spread":0.2726955543328297,"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."}}