{"id":"W4414491904","doi":"10.1126/scirobotics.adv7932","title":"Accelerating discovery in natural science laboratories with AI and robotics: Perspectives and challenges","year":2025,"lang":"en","type":"article","venue":"Science Robotics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Structural Genomics Consortium; University of Toronto","funders":"","keywords":"Automation; Natural science; Scientific discovery; Natural (archaeology)","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007273699,0.0001647991,0.0002361142,0.001135662,0.001033612,0.004565468,0.001302461,0.00002494642,0.000001602806],"category_scores_gemma":[0.004541278,0.0001106082,0.00001330047,0.006460554,0.004619723,0.003512235,0.001413887,0.0002007984,0.000002641488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001099435,"about_ca_system_score_gemma":0.000837684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000301265,"about_ca_topic_score_gemma":0.0002399465,"domain_scores_codex":[0.9959994,0.00006017405,0.0003450554,0.001431282,0.001643545,0.0005205394],"domain_scores_gemma":[0.9978213,0.0004645697,0.0001133328,0.0007791311,0.0007028855,0.0001187286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002550517,0.00009655923,0.04298546,0.00003440343,0.000007451154,0.00001621835,0.007341389,0.05555398,0.000884889,0.8217162,0.0001755214,0.07116238],"study_design_scores_gemma":[0.0009305589,0.0001984586,0.4330621,0.0003912098,0.00002294351,0.00002054326,0.1249444,0.4033723,0.0006567549,0.03467286,0.0009901581,0.0007377382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8470898,0.01521179,0.06064846,0.05916322,0.00421779,0.0009025509,0.00001404334,0.0001801558,0.01257215],"genre_scores_gemma":[0.9807307,0.0001943844,0.01846848,0.000173288,0.00002240151,0.000002241377,2.419048e-7,0.00000341016,0.0004049075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7870434,"threshold_uncertainty_score":0.9980891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07094716502420574,"score_gpt":0.3666177420302932,"score_spread":0.2956705770060875,"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."}}