{"id":"W4236760935","doi":"10.1109/wi.2004.10057","title":"Focused Crawling by Learning HMM from User's Topic-specific Browsing","year":2005,"lang":"en","type":"article","venue":"IEEE/WIC/ACM International Conference on Web Intelligence (WI'04)","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Crawling; Computer science; Hidden Markov model; Web page; Information retrieval; Focused crawler; World Wide Web; Web crawler; Session (web analytics); Task (project management); Traverse; Construct (python library); Static web page; Artificial intelligence; Web navigation","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005973912,0.0005518598,0.0005134692,0.0004693488,0.0004099755,0.00150792,0.004930913,0.0002367898,0.001831672],"category_scores_gemma":[0.0004103851,0.0005592405,0.0002745901,0.0005261255,0.0001765434,0.001505209,0.0005850226,0.0009821397,0.002087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003154915,"about_ca_system_score_gemma":0.0002366097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004224979,"about_ca_topic_score_gemma":0.0001777683,"domain_scores_codex":[0.9953263,0.0002244963,0.0009581929,0.001482798,0.001286667,0.0007214816],"domain_scores_gemma":[0.9966906,0.0005938949,0.0004662638,0.001399928,0.0005546806,0.0002946758],"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":[0.0001231973,0.0006437388,0.004419202,0.00002323874,0.000561571,0.0001096382,0.003576758,0.006566469,0.106663,0.09163043,0.01937495,0.7663078],"study_design_scores_gemma":[0.0006630807,0.0002989434,0.0004828237,0.0007595647,0.00005247067,0.00002463344,0.0009691959,0.5836912,0.1523395,0.007641886,0.2513794,0.001697317],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1820836,0.0003996174,0.7937046,0.008804793,0.002723335,0.0002231367,0.000178063,0.0006221869,0.01126075],"genre_scores_gemma":[0.9627437,0.0007962501,0.03064919,0.0008199451,0.0009663214,0.00002767583,0.0001877351,0.00004138649,0.003767802],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7806602,"threshold_uncertainty_score":0.9996859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06551536332156896,"score_gpt":0.3010360112915977,"score_spread":0.2355206479700288,"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."}}