{"id":"W4403808131","doi":"10.1039/d4dd00252k","title":"Agent-based learning of materials datasets from the scientific literature","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; University of Toronto","keywords":"Data science; Computer science","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009251055,0.0002150968,0.0002380369,0.00008490663,0.0002461605,0.01146226,0.0008570176,0.00006270856,0.0006697204],"category_scores_gemma":[0.0005961875,0.0001340919,0.00008824062,0.0004743897,0.0004980947,0.002392984,0.0003177127,0.0001619728,0.0006854589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002928249,"about_ca_system_score_gemma":0.0001405698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007523411,"about_ca_topic_score_gemma":0.000002974109,"domain_scores_codex":[0.9978206,0.0001698264,0.0004013495,0.0006475684,0.0006223111,0.0003383651],"domain_scores_gemma":[0.9986957,0.0004327044,0.0001385144,0.0006299753,0.00004492444,0.0000581427],"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":[0.00003455239,0.00003235651,0.0004241075,0.0001135548,0.000007207987,0.00003550944,0.0003990974,0.001749454,0.9907095,0.00149811,0.004605393,0.0003911213],"study_design_scores_gemma":[0.0001998581,0.00008745444,0.003151075,0.001145063,0.00003274813,0.00001073561,0.0001115923,0.002306194,0.9387652,0.00192188,0.05185261,0.0004155961],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825808,0.0007193444,0.002160908,0.0002283343,0.003155843,0.0001657519,0.01046184,0.0001664227,0.0003607217],"genre_scores_gemma":[0.9957331,0.00000377271,0.0003515775,0.00008846525,0.0002063738,0.00001265599,0.002678485,0.00002674306,0.0008988733],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05194434,"threshold_uncertainty_score":0.9895639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0100241379096093,"score_gpt":0.2521744097452122,"score_spread":0.2421502718356029,"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."}}