{"id":"W2270926629","doi":"10.1007/s11280-015-0370-0","title":"Identifying semantic blocks in Web pages using Gestalt laws of grouping","year":2015,"lang":"en","type":"article","venue":"World Wide Web","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council","keywords":"Computer science; Gestalt psychology; Web page; Information retrieval; Merge (version control); Artificial intelligence; Natural language processing; Data mining; Theoretical computer science; Algorithm; Perception; World Wide Web","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":[0.0008306788,0.0003405048,0.0007748304,0.005290049,0.0009940492,0.002476916,0.0007435342,0.0009950337,0.002501116],"category_scores_gemma":[0.004656615,0.0004847142,0.0008093548,0.002786665,0.001998268,0.004809214,0.00132492,0.0006771055,0.0007442194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007529129,"about_ca_system_score_gemma":0.0004902726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004022046,"about_ca_topic_score_gemma":0.004905727,"domain_scores_codex":[0.9993807,0.0001288503,0.00006106288,0.0001651953,0.0001896006,0.00007455243],"domain_scores_gemma":[0.9974644,0.001034625,0.0004503989,0.0005109796,0.0003879328,0.000151715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001146652,0.0005697299,0.04913886,0.0007621094,0.0002659056,0.0008306606,0.003671983,0.06960794,0.1444181,0.2488799,0.006444423,0.4742638],"study_design_scores_gemma":[0.00003392839,0.000178426,0.03119601,0.00008799903,0.0001291286,0.0005304982,0.0009447064,0.7570916,0.02134304,0.1834788,0.004918862,0.00006706333],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2777657,0.0005220458,0.7146708,0.0002168037,0.00003431847,0.000175538,0.0003116734,0.001300622,0.005002675],"genre_scores_gemma":[0.8392152,0.0002988076,0.1574104,0.00007254827,0.00004134306,0.000129233,0.0003605418,0.0001757951,0.002296195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005290049,"threshold_uncertainty_score":0.008367121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07740306236981702,"score_gpt":0.3017733189573059,"score_spread":0.2243702565874888,"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."}}