{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006748162,0.0001199022,0.0002090796,0.0003922072,0.00004801417,0.0001067773,0.0005603893,0.00004051585,0.000007337286],"category_scores_gemma":[0.0001018013,0.0001178005,0.0000549702,0.001135926,0.00006158129,0.0004942593,0.000243772,0.0001540376,0.00001155188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009034257,"about_ca_system_score_gemma":0.0001464127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006823931,"about_ca_topic_score_gemma":0.0002471105,"domain_scores_codex":[0.9987015,0.00008159311,0.0003730753,0.000282489,0.0003171213,0.0002442011],"domain_scores_gemma":[0.999129,0.00008936747,0.0001758574,0.0004180467,0.0001094842,0.00007823019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004324002,0.0005083383,0.1339924,0.0004498383,0.00006470909,0.0002472108,0.00459113,0.0001723091,0.7224828,0.05558565,0.005328736,0.07653362],"study_design_scores_gemma":[0.00153291,0.0001103456,0.01759162,0.001427545,0.00003792983,0.00006423735,0.0005402811,0.471089,0.4695987,0.02264616,0.01428216,0.001079076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4083763,0.001366492,0.5776315,0.002314426,0.000613255,0.0004804511,0.000003098526,0.0006775855,0.00853695],"genre_scores_gemma":[0.9710889,0.00003603356,0.02808052,0.0001235386,0.00003175541,0.000005284526,8.902621e-7,0.00001010547,0.0006229503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5627126,"threshold_uncertainty_score":0.4803765,"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."}}