{"id":"W2038876950","doi":"10.1080/08839510802028447","title":"CRAWLING THE CONSTRUCTION WEB – A MACHINE-LEARNING APPROACH WITHOUT NEGATIVE EXAMPLES","year":2008,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Web crawler; Crawling; Web page; Domain (mathematical analysis); Focused crawler; Class (philosophy); World Wide Web; Artificial intelligence; Machine learning; Information retrieval; Web navigation; Static web page","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":[0.0005603228,0.0002051749,0.0001886066,0.0001384324,0.0007312613,0.0001915227,0.001074254,0.00007534058,0.00002135729],"category_scores_gemma":[0.0007812429,0.0001608307,0.00006018622,0.0008849738,0.0004235454,0.0002039553,0.0003028613,0.000632458,0.0001789168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005715215,"about_ca_system_score_gemma":0.0001181455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00010199,"about_ca_topic_score_gemma":0.0000111495,"domain_scores_codex":[0.9980801,0.00008863892,0.0003277955,0.0005401024,0.0005132783,0.0004500715],"domain_scores_gemma":[0.9980493,0.00107402,0.00009641996,0.0005288471,0.0001508892,0.0001005745],"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":[0.00005658947,0.0001951571,0.007574531,0.00004652848,0.0001035522,0.00002942391,0.01666148,0.1005141,0.02544729,0.5443316,0.0001110377,0.3049287],"study_design_scores_gemma":[0.00005754094,0.00006144505,0.0006355452,0.00001663682,0.000007732364,0.0001385882,0.0009711579,0.8472436,0.131349,0.01778929,0.001248505,0.0004809677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0802012,0.00006232276,0.9171181,0.000127815,0.0002696163,0.0003266508,0.000001152581,0.0005040816,0.001389071],"genre_scores_gemma":[0.9175466,0.00003919225,0.08202844,0.00004856636,0.0001789098,0.00008889473,0.000002380015,0.00001958434,0.00004741014],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8373454,"threshold_uncertainty_score":0.6558484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06203447223025554,"score_gpt":0.2727079318439812,"score_spread":0.2106734596137256,"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."}}