{"id":"W2050467853","doi":"10.1145/2637002.2637025","title":"A qualitative exploration of secondary assessor relevance judging behavior","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud bin Abdulaziz University for Health Science; University of Waterloo; King Abdulaziz University; King Saud University","keywords":"Relevance (law); Think aloud protocol; Certainty; Psychology; Quality (philosophy); Test (biology); Information retrieval; Computer science; Mathematics; Epistemology; Human–computer interaction","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007201218,0.00008618899,0.0001594916,0.0001187056,0.00004735216,0.00005443428,0.0003399312,0.00004581543,0.00005876683],"category_scores_gemma":[0.0002130732,0.00008068675,0.00004589237,0.0002422218,0.00004042434,0.0017414,0.00008706828,0.0001018448,0.00004029086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001874806,"about_ca_system_score_gemma":0.00003869812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001471405,"about_ca_topic_score_gemma":0.0000108844,"domain_scores_codex":[0.9989015,0.0002146493,0.0003092166,0.0002368583,0.0002098528,0.0001279047],"domain_scores_gemma":[0.9989446,0.0003181351,0.0001640551,0.0003203111,0.000211194,0.00004168114],"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":[0.000002905955,0.0001277723,0.00007453658,0.00003362802,0.000007171847,0.000001355948,0.01019782,0.000001394621,0.02022769,0.1779348,0.0008633123,0.7905276],"study_design_scores_gemma":[0.0004249038,0.0003979681,0.0007614627,0.00008506195,0.00001190937,0.000006203567,0.001827961,0.008573955,0.8705108,0.1146905,0.002344798,0.0003644633],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02110398,0.00001154507,0.968123,0.0003654961,0.00007383186,0.00016449,0.000001479105,0.0003544934,0.009801677],"genre_scores_gemma":[0.7003567,0.000004652151,0.2991478,0.0001539089,0.00001521126,0.00008368246,0.000003010936,0.000005380191,0.0002296513],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8502831,"threshold_uncertainty_score":0.329031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05938001020438095,"score_gpt":0.3608155720620532,"score_spread":0.3014355618576723,"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."}}