{"id":"W4306317650","doi":"10.1145/3511808.3557719","title":"Unsupervised Question Clarity Prediction through Retrieved Item Coherency","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","topic":"Topic Modeling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ambiguity; Computer science; CLARITY; Generalization; Context (archaeology); Artificial intelligence; Ask price; Graph; Machine learning; Similarity (geometry); Open domain; Information retrieval; Question answering; Natural language processing; Theoretical computer science; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0008409054,0.0001993689,0.0001655787,0.0002257036,0.0003829642,0.000323064,0.003182815,0.00006100644,0.0002043219],"category_scores_gemma":[0.0002883866,0.0001798949,0.0001080494,0.0005781449,0.00004642124,0.002267861,0.002475221,0.0003770019,0.00009512067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004596117,"about_ca_system_score_gemma":0.00006241342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002041821,"about_ca_topic_score_gemma":0.000004506362,"domain_scores_codex":[0.9976978,0.00003717297,0.0007053541,0.0003065259,0.001038139,0.0002149969],"domain_scores_gemma":[0.9979649,0.00004090291,0.0005404445,0.0004892189,0.0009183922,0.00004615227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005085386,0.0001331579,0.001798873,0.0001190955,0.00006541405,7.240862e-8,0.003544211,0.0003387169,0.000162937,0.9781524,0.005141106,0.01049315],"study_design_scores_gemma":[0.003286628,0.0003033066,0.02376362,0.0005887077,0.00008697571,0.00002589956,0.004110088,0.2920125,0.001291169,0.2241305,0.4494556,0.0009450755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.08253288,0.00003689699,0.1546415,0.009961689,0.005228383,0.001837963,0.00008663453,0.0005591278,0.7451149],"genre_scores_gemma":[0.9810895,0.00004656271,0.01514333,0.0003956349,0.00008262738,0.0002429939,0.00006315372,0.00000861292,0.002927547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8985566,"threshold_uncertainty_score":0.7335902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06448416126311513,"score_gpt":0.2933610998971692,"score_spread":0.2288769386340541,"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."}}