{"id":"W4396893084","doi":"10.26434/chemrxiv-2024-zs5xp","title":"Metis - A Python-Based User Interface to Collect Expert Feedback for GenerativeChemistry Models","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Chemistry and Chemical Engineering","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Horizon 2020","keywords":"Python (programming language); Generative grammar; Computer science; Metis; User interface; Programming language; Interface (matter); Human–computer interaction; Toolbox; World Wide Web; Software engineering; Artificial intelligence; Operating system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001248793,0.0004800807,0.000398849,0.00002357756,0.00005983059,0.0001121378,0.0005866595,0.0004276054,0.001026644],"category_scores_gemma":[0.00007684914,0.0004879623,0.0002875409,0.0002154046,0.00008215492,0.00003654135,0.001274233,0.0005677357,0.0001238941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006350582,"about_ca_system_score_gemma":0.00005854327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003211805,"about_ca_topic_score_gemma":0.000002953901,"domain_scores_codex":[0.997963,0.000007163199,0.0003176529,0.00102941,0.000255969,0.0004268582],"domain_scores_gemma":[0.9989332,0.00008482303,0.00005875659,0.0006212619,0.00001901092,0.0002829298],"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":[0.00003258132,0.0000441466,0.000002626384,0.0003584689,0.00004119548,0.000004123207,0.0002248005,0.1796633,0.7716908,0.000005678517,0.04770632,0.0002258972],"study_design_scores_gemma":[0.0001981084,0.00001119909,7.527481e-7,0.0002289108,0.00003131699,0.000002058204,0.00002312565,0.1168753,0.8684854,0.0008863236,0.01274376,0.000513809],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8363789,0.001061666,0.1367135,0.001946892,0.0007006999,0.001293128,0.0001180223,0.0006009544,0.0211863],"genre_scores_gemma":[0.965037,0.00001595506,0.02274416,0.000350018,0.000323091,0.001074699,0.00008175115,0.0001211653,0.01025218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1286581,"threshold_uncertainty_score":0.9998866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02064793834236246,"score_gpt":0.2578491133890943,"score_spread":0.2372011750467318,"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."}}