{"id":"W2025470942","doi":"10.1016/j.asoc.2015.02.029","title":"Automated classification and localization of daily deal content from the Web","year":2015,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; News aggregator; Discriminative model; Web page; Set (abstract data type); Information retrieval; Web content; Machine learning; World Wide Web; Artificial intelligence","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":[0.0004400951,0.00007571712,0.0001282103,0.00003293568,0.0001082059,0.0001013114,0.0003789621,0.0000358107,5.113517e-7],"category_scores_gemma":[0.00004737433,0.00005681361,0.00001783398,0.0002820693,0.00005229514,0.0000835039,0.0002132023,0.00005928304,0.000008079693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001608009,"about_ca_system_score_gemma":0.00005460679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001429491,"about_ca_topic_score_gemma":0.000009648115,"domain_scores_codex":[0.9991814,0.00004909304,0.000228727,0.0002389103,0.0001909274,0.0001108712],"domain_scores_gemma":[0.9991593,0.0002162222,0.0001704309,0.0003152129,0.0000864603,0.00005242154],"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":[0.00004652995,0.0002575611,0.1499709,0.0000506278,0.0003821825,0.000005997243,0.02572541,0.039044,0.02873138,0.1393116,0.02143697,0.5950367],"study_design_scores_gemma":[0.0002631877,0.000008946155,0.01035213,0.00001480723,0.00001398725,8.963149e-7,0.0005793213,0.9876155,0.0002206263,0.0003513553,0.0005123662,0.00006691958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.206255,0.0000752739,0.7927341,0.0002390952,0.00004950839,0.00005984335,0.000003612275,0.0002468528,0.0003367063],"genre_scores_gemma":[0.9723647,0.000002442156,0.02733895,0.0002116063,0.00003686409,0.000001527046,0.00003576385,0.000004433402,0.000003677076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9485714,"threshold_uncertainty_score":0.2316792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06116658146903416,"score_gpt":0.2576346301896803,"score_spread":0.1964680487206462,"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."}}