{"id":"W2598574795","doi":"10.29173/cais435","title":"Towards a Comparison of Structured and Unstructured Text Retrieval","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Information retrieval; Computer science; Adjacency list; Unstructured data; SGML; Text retrieval; Document Structure Description; Document retrieval; Natural language processing; World Wide Web; Data mining; XML; Big data; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.01975515,0.000703254,0.001286568,0.01058889,0.0006656313,0.005704255,0.002030032,0.00197756,0.003380792],"category_scores_gemma":[0.09207857,0.0003678746,0.0006637587,0.005316294,0.00198454,0.01090654,0.002596798,0.001192189,0.002382519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001582846,"about_ca_system_score_gemma":0.001482903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001404202,"about_ca_topic_score_gemma":0.001252593,"domain_scores_codex":[0.9686736,0.0162744,0.001985129,0.001807802,0.01075159,0.0005074559],"domain_scores_gemma":[0.9362053,0.03859563,0.002408483,0.006195425,0.01552532,0.001069865],"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":[0.005199424,0.00100855,0.01086125,0.004229904,0.0007161542,0.0002116144,0.002492997,0.01727346,0.03047552,0.09145215,0.01734296,0.8187358],"study_design_scores_gemma":[0.002032222,0.01222165,0.08194131,0.003036736,0.001056562,0.001366634,0.01070482,0.2409635,0.0650055,0.4171429,0.1638877,0.0006404962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1754209,0.0402254,0.6935329,0.006496707,0.002121283,0.002351151,0.003067725,0.003574236,0.0732097],"genre_scores_gemma":[0.5458791,0.008197667,0.4270778,0.001675634,0.001142561,0.001129889,0.005788071,0.000793454,0.00831575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01975515,"threshold_uncertainty_score":0.1044765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02263581327200936,"score_gpt":0.2646467163219727,"score_spread":0.2420109030499633,"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."}}