{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003647971,0.001255731,0.001493614,0.004320518,0.001222274,0.002326805,0.002926508,0.002844627,0.001006553],"category_scores_gemma":[0.01451478,0.0008274328,0.0009676763,0.00217071,0.001798303,0.003264146,0.001385982,0.001626742,0.0009510131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007405194,"about_ca_system_score_gemma":0.0009119123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002650199,"about_ca_topic_score_gemma":0.003790465,"domain_scores_codex":[0.9963058,0.001411801,0.0003138971,0.00102622,0.0008128008,0.0001293853],"domain_scores_gemma":[0.986025,0.009151369,0.0008068622,0.00196224,0.001870002,0.0001845885],"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":[0.0002664983,0.001080334,0.01510433,0.0009644206,0.0002282566,0.0007442308,0.001259687,0.07028374,0.01830408,0.01295811,0.01414898,0.8646574],"study_design_scores_gemma":[0.00005971858,0.0002108113,0.004420291,0.0001304273,0.00009219127,0.0008453999,0.0002893634,0.9356293,0.01266017,0.03466192,0.010944,0.00005646762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07827849,0.001364507,0.9107724,0.001294849,0.00007831231,0.000393101,0.0005447489,0.00328276,0.003990924],"genre_scores_gemma":[0.3514553,0.0004493373,0.6390253,0.0005278435,0.0002154042,0.0004284784,0.002044774,0.0002064924,0.005647077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004320518,"threshold_uncertainty_score":0.01929253,"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."}}