{"id":"W335269702","doi":"","title":"Measuring Robustness with First Relevant Score in the TREC 2012 Microblog Track","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Microblogging; Robustness (evolution); Computer science; Social media; Rank (graph theory); Measure (data warehouse); Context (archaeology); Post hoc; Artificial intelligence; Information retrieval; Data mining; Mathematics; World Wide Web; Medicine","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":[0.001459716,0.0002410328,0.0002396748,0.0001696729,0.0002610804,0.0003613689,0.001470254,0.0001086997,0.0001205653],"category_scores_gemma":[0.0001384178,0.0001478781,0.00006174167,0.001077609,0.000144849,0.002160625,0.0001670423,0.0005120191,0.0001812838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008908851,"about_ca_system_score_gemma":0.0002419996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000496247,"about_ca_topic_score_gemma":0.0001362946,"domain_scores_codex":[0.9976224,0.0001543593,0.0003865118,0.0002878886,0.000796441,0.0007524359],"domain_scores_gemma":[0.9984801,0.0002651784,0.0001427108,0.0006830406,0.0002563236,0.0001726281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.002549377,0.0038884,0.2477087,0.001440404,0.0001928721,0.0004909044,0.1464949,0.002201287,0.01189263,0.3735753,0.008539576,0.2010256],"study_design_scores_gemma":[0.005131407,0.001253216,0.8933228,0.001068957,0.00009031172,0.001074679,0.002273968,0.03112246,0.02969355,0.0005412903,0.03175639,0.002670999],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8783618,0.0004013122,0.112657,0.002395257,0.0003339652,0.0007858247,0.000008254341,0.0001765794,0.004880047],"genre_scores_gemma":[0.9967799,0.00004735804,0.002418559,0.0002058886,0.0000666452,0.00001595759,0.00000538598,0.000009909062,0.0004504382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.645614,"threshold_uncertainty_score":0.6030294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08410569437123029,"score_gpt":0.2573694548114804,"score_spread":0.1732637604402501,"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."}}