{"id":"W1515339153","doi":"10.1007/978-3-540-69858-6_11","title":"Exploiting Multiple Features with MEMMs for Focused Web Crawling","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Crawling; Web crawler; Computer science; Focused crawler; Information retrieval; Web page; World Wide Web; Task (project management); Key (lock); Context (archaeology); Link analysis; Static web page; Web development","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"],"consensus_categories":[],"category_scores_codex":[0.0006566354,0.0006060173,0.0006909722,0.000911454,0.0006319215,0.0007174746,0.003413083,0.0002671527,0.000004364235],"category_scores_gemma":[0.0002171994,0.0004881573,0.0002069424,0.0006934465,0.0005388251,0.0007830402,0.0008487948,0.0006738909,0.00001126388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000143179,"about_ca_system_score_gemma":0.0006496131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004170524,"about_ca_topic_score_gemma":0.0002236198,"domain_scores_codex":[0.9958012,0.00002572115,0.0004774816,0.001901763,0.0009695531,0.0008243455],"domain_scores_gemma":[0.9964927,0.001103229,0.0003697471,0.001523702,0.0003166524,0.0001940102],"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":[0.00003101449,0.00005264616,0.000255212,0.00009152678,0.00008576358,0.0002395615,0.00196347,0.04150894,0.001089081,0.001646707,0.0002579701,0.9527781],"study_design_scores_gemma":[0.001049473,0.0003636137,0.00006600288,0.0008652704,0.00003763134,0.0002056615,0.000001210217,0.9795529,0.00682342,0.004827004,0.004875539,0.00133229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004319599,0.0004481006,0.9967913,0.0004558778,0.000543842,0.000349667,0.00002503355,0.0002610436,0.0006931474],"genre_scores_gemma":[0.1845824,0.00005863807,0.8133839,0.0007309573,0.0006240858,0.00002754961,0.00002229168,0.00005418938,0.0005160006],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9514458,"threshold_uncertainty_score":0.999757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02566325501353451,"score_gpt":0.2365196648302101,"score_spread":0.2108564098166756,"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."}}