{"id":"W3140174028","doi":"10.1109/wiiatw.2007.4427580","title":"User-Oriented Evaluation Methods for Interactive Web Search Interfaces","year":2007,"lang":"en","type":"article","venue":"2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Human–computer interaction; User interface; World Wide Web; Programming language","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"],"consensus_categories":[],"category_scores_codex":[0.005404069,0.000697776,0.0006726059,0.002099241,0.0003567392,0.0005215639,0.003963784,0.0006546684,0.000395161],"category_scores_gemma":[0.00117394,0.0006234382,0.000251039,0.001130161,0.0004672238,0.0008400939,0.001203749,0.001038285,0.0001385338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000504532,"about_ca_system_score_gemma":0.0003624327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006963439,"about_ca_topic_score_gemma":0.0001490603,"domain_scores_codex":[0.9946191,0.0003271108,0.001494237,0.001584742,0.001002714,0.0009721532],"domain_scores_gemma":[0.9943655,0.001668685,0.0005765791,0.001274576,0.001860982,0.0002537217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001900984,0.0003295993,0.001079063,0.00002705815,0.0003311138,0.00001141165,0.0006493806,0.00009509224,0.001884389,0.1731288,0.00406756,0.8182065],"study_design_scores_gemma":[0.0006011614,0.001671366,0.0002097274,0.0008180329,0.00008206244,0.0001091109,0.005326438,0.2425595,0.4729919,0.05110401,0.2232398,0.001286845],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01965749,0.0008730054,0.9593839,0.004814269,0.005747207,0.001807917,0.00002400949,0.0007228291,0.006969358],"genre_scores_gemma":[0.8975973,0.001691304,0.09818572,0.0006100503,0.0002898751,0.0004049521,0.00004520089,0.00004292617,0.00113274],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8779398,"threshold_uncertainty_score":0.9996217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09433433538937618,"score_gpt":0.4226939083008822,"score_spread":0.328359572911506,"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."}}