{"id":"W3195010973","doi":"10.1145/3459637.3482011","title":"MS MARCO Chameleons: Challenging the MS MARCO Leaderboard with Extremely Obstinate Queries","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Microsoft (Canada); University of Waterloo","funders":"","keywords":"Computer science; Set (abstract data type); Task (project management); Information retrieval; Perspective (graphical); Artificial intelligence","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":[0.0003072724,0.0002173036,0.0002163554,0.00005616822,0.0002791865,0.0003072998,0.0009009406,0.00005758691,0.0001654415],"category_scores_gemma":[0.00005777218,0.0001397963,0.00006941454,0.0003565434,0.00009369664,0.0004563244,0.0004814386,0.0002707451,0.0000491973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003267859,"about_ca_system_score_gemma":0.0001388128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001501943,"about_ca_topic_score_gemma":0.0003931331,"domain_scores_codex":[0.9981115,0.0001008046,0.0002457468,0.0006058658,0.0004320093,0.0005039996],"domain_scores_gemma":[0.9984418,0.0001572559,0.00007102937,0.001101515,0.0001374658,0.00009093534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001741277,0.00009819234,0.002184227,0.00009954724,0.000113136,0.0004829332,0.007433211,0.003434227,0.001615225,0.8216533,0.0009660608,0.1619025],"study_design_scores_gemma":[0.00175475,0.0002303401,0.01049788,0.0005415499,0.0000496769,0.0008152291,0.006922897,0.8282225,0.02098825,0.01924134,0.1088845,0.001851112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01820908,0.002395388,0.9194496,0.02832313,0.000363722,0.0001820683,7.434408e-7,0.0004143045,0.03066192],"genre_scores_gemma":[0.8811422,0.0002401614,0.109005,0.001387413,0.0001832896,0.00004327631,0.000001579446,0.00002581386,0.007971236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8629331,"threshold_uncertainty_score":0.5700727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03365566842748198,"score_gpt":0.2226192605793842,"score_spread":0.1889635921519022,"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."}}