{"id":"W4317659260","doi":"10.1145/3580519","title":"Validation of an Improved Vision-Based Web Page Parsing Pipeline","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McGill University; Mount Allison University","funders":"","keywords":"Computer science; Parsing; Pipeline (software); Segmentation; Ground truth; Web page; Set (abstract data type); Artificial intelligence; Pruning; Zoom; Machine learning; Visualization; Interface (matter); Information retrieval; World Wide Web; Programming language","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":[0.000615901,0.0001228637,0.0001188416,0.0002136346,0.0003440107,0.00007532621,0.001099002,0.0000572645,0.0000600799],"category_scores_gemma":[0.0001054304,0.00009643479,0.00008745593,0.001129298,0.00005354368,0.0002167664,0.00001610597,0.0002516064,0.0001490252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002916212,"about_ca_system_score_gemma":0.0001025904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001206642,"about_ca_topic_score_gemma":0.00002033388,"domain_scores_codex":[0.9987997,0.000189225,0.0002532277,0.0003179901,0.0002472583,0.000192615],"domain_scores_gemma":[0.9974989,0.0007232075,0.0001081904,0.001520526,0.00008405169,0.00006511265],"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":[0.00003798548,0.0005521195,0.00009756384,0.00003161047,0.00003166703,0.000001918949,0.0007092657,0.1764535,0.5837359,0.001285978,0.000285106,0.2367774],"study_design_scores_gemma":[0.0002897051,0.00009000406,0.0007848453,0.0000187996,0.00001235597,0.000001125096,0.00002963397,0.952543,0.04447203,0.001375328,0.0002816664,0.0001015712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3476848,0.000003156235,0.637315,0.01395349,0.0001328855,0.0002771108,0.00002388866,0.0005002673,0.0001094619],"genre_scores_gemma":[0.974986,0.000005445447,0.02454524,0.000232845,0.00002312923,0.00007173096,0.00001683056,0.00001690955,0.0001018292],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7760894,"threshold_uncertainty_score":0.3932497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02155203640625081,"score_gpt":0.294845347279104,"score_spread":0.2732933108728532,"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."}}