{"id":"W4301430631","doi":"10.26434/chemrxiv-2022-x49mh-v3","title":"ChemSpacE: Interpretable and Interactive Chemical Space Exploration","year":2022,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Chemical space; Interpretability; Computer science; Space (punctuation); Generative model; Generative grammar; Property (philosophy); Artificial intelligence; Task (project management); Process (computing); Black box; Interface (matter); Machine learning; Human–computer interaction; Drug discovery; Bioinformatics; Systems engineering; Engineering; Biology","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001050592,0.0004161161,0.0005253745,0.0001153636,0.0001931531,0.0005507395,0.000860989,0.0002159234,0.005922831],"category_scores_gemma":[0.0006546375,0.0004190343,0.00008679119,0.0001511807,0.0002844879,0.0004724432,0.003944768,0.0009440198,0.000172429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002498615,"about_ca_system_score_gemma":0.0001404532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001589615,"about_ca_topic_score_gemma":0.000003609875,"domain_scores_codex":[0.9972586,0.0002134321,0.0004037503,0.001185931,0.0004996997,0.0004385723],"domain_scores_gemma":[0.9983443,0.0001702309,0.0004606221,0.0007758422,0.00009193805,0.0001570414],"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":[0.00006864641,0.000050882,0.0002655502,0.0002012076,0.000009653,0.000009984652,0.002510687,0.001277025,0.9935783,0.0002828457,0.001580739,0.0001645243],"study_design_scores_gemma":[0.0002861231,0.00005756616,0.0002131016,0.0001937924,0.00004326837,0.00002545382,0.0006300837,0.009996635,0.977701,0.002939619,0.007166951,0.0007464036],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866953,0.0002008294,0.004886352,0.001278582,0.002369794,0.0004248385,0.00001597781,0.0003223313,0.003805922],"genre_scores_gemma":[0.9867502,0.00005279715,0.01071486,0.000167254,0.0002928836,0.0003109771,0.00006902947,0.00005835356,0.00158368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01587725,"threshold_uncertainty_score":0.9998261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01713808449980169,"score_gpt":0.2876839012163843,"score_spread":0.2705458167165826,"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."}}