{"id":"W2145410165","doi":"10.1145/2600428.2609534","title":"The effect of expanding relevance judgements with duplicates","year":2014,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Relevance (law); Context (archaeology); Set (abstract data type); Natural language processing; Reusability; Information retrieval; Artificial intelligence; Test set; Sentence; Data mining; Programming language; Software","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02460408,0.002101629,0.002098011,0.001944332,0.002564366,0.002585505,0.001821352,0.002183516,0.00183905],"category_scores_gemma":[0.2079079,0.0008875424,0.001261414,0.001705283,0.001600769,0.004652251,0.003034572,0.003426414,0.0006356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001137017,"about_ca_system_score_gemma":0.001689298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005236203,"about_ca_topic_score_gemma":0.005012564,"domain_scores_codex":[0.9742863,0.01237309,0.002791249,0.004407713,0.005339641,0.000801986],"domain_scores_gemma":[0.691846,0.254402,0.009060442,0.02412494,0.01711032,0.003456339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01553048,0.004111916,0.05660184,0.003758949,0.002312298,0.00249471,0.008374381,0.1093196,0.2789847,0.001738253,0.01000524,0.5067676],"study_design_scores_gemma":[0.002282546,0.02693575,0.2315757,0.0009014707,0.005854466,0.005841363,0.006740254,0.3435034,0.3345361,0.01438142,0.02597563,0.001472083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754572,0.002436536,0.01572725,0.0004497867,0.0004156474,0.0004068635,0.0003567964,0.001117239,0.003632779],"genre_scores_gemma":[0.9660268,0.0003846818,0.02959649,0.0003962262,0.0003575729,0.0002062451,0.001033337,0.0003395995,0.001658958],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02460408,"threshold_uncertainty_score":0.1301204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006888291307441076,"score_gpt":0.2347738308926272,"score_spread":0.2278855395851861,"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."}}