{"id":"W2101251493","doi":"10.1080/10629360701306050","title":"How can structural similarity analysis help in category formation?§","year":2007,"lang":"en","type":"article","venue":"SAR and QSAR in environmental research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Chemical Industry Council","keywords":"Categorization; Similarity (geometry); Computer science; Ranking (information retrieval); Scope (computer science); Set (abstract data type); Process (computing); Chemical similarity; Mechanism (biology); Information retrieval; Machine learning; Data mining; Structural similarity; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.002534791,0.00009609833,0.0001456463,0.0007434301,0.0001134008,0.0001418971,0.0003709158,0.00005582062,0.0000131535],"category_scores_gemma":[0.00006373888,0.00009342594,0.00004311268,0.001032376,0.0001589738,0.0005668075,0.0004364143,0.0003566645,0.000003585759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003555581,"about_ca_system_score_gemma":0.00002950098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000323906,"about_ca_topic_score_gemma":0.001422015,"domain_scores_codex":[0.9980218,0.0003502415,0.0001946834,0.0003378886,0.0006745634,0.0004208445],"domain_scores_gemma":[0.9991885,0.0004217358,0.00002795566,0.0002495012,0.000008811117,0.000103426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007422174,0.0002153375,0.7160503,0.0000460722,0.0000701041,0.0002120021,0.006548903,0.01771422,0.002942572,0.01093922,0.00004535197,0.2451417],"study_design_scores_gemma":[0.0002552663,0.00003078431,0.8493959,0.000003448924,0.000002896097,0.000005660249,0.0007404377,0.1353655,0.001480387,0.01245561,0.0001564095,0.0001076788],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9609861,0.0002201643,0.03743741,0.0008103558,0.00003053547,0.0001622086,0.000009987306,0.000008022513,0.0003352617],"genre_scores_gemma":[0.9934916,0.0000449584,0.006282569,0.00005285345,0.000018297,0.000003447187,0.0000209213,0.000004349901,0.00008101559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.245034,"threshold_uncertainty_score":0.38098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04607903939175301,"score_gpt":0.3595187392152965,"score_spread":0.3134396998235435,"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."}}