{"id":"W2798631888","doi":"10.1145/3209978.3210123","title":"Multi-level Abstraction Convolutional Model with Weak Supervision for Information Retrieval","year":2018,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Matching (statistics); Abstraction; Convolutional neural network; Semantic matching; Abstraction layer; Artificial intelligence; Training set; Word (group theory); Machine learning; Information retrieval; Natural language processing; Software; Programming language; Mathematics","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":[0.0003584461,0.0001061739,0.00008562162,0.0001517633,0.0003002991,0.0002090693,0.000307152,0.00007826721,0.00003943392],"category_scores_gemma":[0.00004905683,0.00007806504,0.00004264611,0.000268462,0.00006632732,0.004621125,0.0000676468,0.00008942661,0.0002595619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007272774,"about_ca_system_score_gemma":0.0002017311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001506722,"about_ca_topic_score_gemma":0.00000932572,"domain_scores_codex":[0.9988672,0.000009622684,0.0002839677,0.0001356331,0.0004634016,0.0002402319],"domain_scores_gemma":[0.9985477,0.00003771767,0.00008854009,0.000220187,0.001011308,0.00009452661],"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":[0.002685086,0.0007055358,0.00105032,0.0002277728,0.0000935768,0.000001542738,0.007657139,0.009801056,0.02096698,0.7214801,0.0242915,0.2110393],"study_design_scores_gemma":[0.00111255,0.0002892566,0.007993666,0.000008115575,0.000003563349,0.00001071229,0.00007108937,0.9793806,0.006254068,0.0002091559,0.004521891,0.0001452961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02112028,0.000001358876,0.9754817,0.0004551859,0.0001714014,0.0003842979,0.0000309878,0.0001460137,0.002208754],"genre_scores_gemma":[0.5414375,0.000002244785,0.4563208,0.0004214933,0.00005839523,0.00001655464,0.00007105664,0.000004243736,0.001667766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9695796,"threshold_uncertainty_score":0.3350204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06992547432501563,"score_gpt":0.2990072167605844,"score_spread":0.2290817424355688,"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."}}