{"id":"W4417114405","doi":"10.48550/arxiv.2506.01372","title":"AI Scientists Fail Without Strong Implementation Capability","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Executor; Bottleneck; Workflow; Bridge (graph theory); Position paper; Domain (mathematical analysis); Applications of artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05289633,0.00107397,0.001018615,0.001872604,0.00167255,0.01015056,0.005871709,0.003981476,0.009170684],"category_scores_gemma":[0.1850844,0.001353359,0.001450859,0.002022734,0.008410794,0.02035767,0.007719239,0.008944119,0.009984465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002801145,"about_ca_system_score_gemma":0.01057197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002296102,"about_ca_topic_score_gemma":0.001210896,"domain_scores_codex":[0.9490417,0.02592374,0.003363042,0.004199924,0.0155695,0.001902082],"domain_scores_gemma":[0.7719586,0.1226534,0.007563211,0.06824449,0.0256536,0.003926664],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005808013,0.0004012828,0.006784243,0.002767802,0.000208368,0.000228105,0.002306873,0.01446076,0.01120225,0.5103956,0.0621816,0.3884824],"study_design_scores_gemma":[0.0003130866,0.0004259049,0.002613304,0.001055672,0.0001654534,0.0003675801,0.001132477,0.06529369,0.01756266,0.6106136,0.300292,0.0001645293],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.05110068,0.005375283,0.7263426,0.1098933,0.001737927,0.0007513702,0.00106362,0.02517081,0.07856449],"genre_scores_gemma":[0.3177803,0.003646888,0.6420345,0.01490174,0.0008944225,0.001255092,0.001873074,0.004712612,0.0129014],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9471037,"threshold_uncertainty_score":0.2797459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03447634958603177,"score_gpt":0.3691485353916548,"score_spread":0.334672185805623,"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."}}