{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001061205,0.0008761186,0.001268541,0.004861656,0.0006432695,0.001032003,0.001229114,0.001194355,0.001365912],"category_scores_gemma":[0.006516653,0.0004918451,0.000769216,0.002880169,0.0003258745,0.002189635,0.001045312,0.000636712,0.000815751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003083563,"about_ca_system_score_gemma":0.0004388773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001423102,"about_ca_topic_score_gemma":0.004574127,"domain_scores_codex":[0.999022,0.0002415035,0.0001039851,0.0002179381,0.0003341554,0.00008038159],"domain_scores_gemma":[0.9961636,0.002001901,0.0003807495,0.0007609673,0.0005790702,0.0001138093],"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":[0.0006593869,0.0004596796,0.02003982,0.0004087514,0.0003641692,0.0004147174,0.000244332,0.02009752,0.03517593,0.002211322,0.01615008,0.9037743],"study_design_scores_gemma":[0.0000550652,0.0002910061,0.007222153,0.00003275321,0.0001840722,0.0006254078,0.000132291,0.9527382,0.02297129,0.009033531,0.006672212,0.00004201142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2593351,0.002256556,0.7082617,0.0004522202,0.0003636118,0.0002859504,0.002206767,0.02282663,0.004011355],"genre_scores_gemma":[0.6221258,0.0002287617,0.3717074,0.0001735844,0.0002297019,0.0002334602,0.002072103,0.000620738,0.002608367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004861656,"threshold_uncertainty_score":0.005612254,"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."}}