{"id":"W4412877105","doi":"10.1145/3711896.3737207","title":"Cross-Domain Web Information Extraction at Pinterest","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bridgepoint Active Healthcare","funders":"","keywords":"Computer science; World Wide Web; Information extraction; Domain (mathematical analysis); Information retrieval","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":[0.0003556107,0.0001841797,0.0002050754,0.000335836,0.000147098,0.001031519,0.001238241,0.0001967576,0.0001699875],"category_scores_gemma":[0.00005737236,0.0001690722,0.0001565412,0.0002482444,0.00002781588,0.00129395,0.003043092,0.0003230832,0.0005521836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000169032,"about_ca_system_score_gemma":0.000187509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002013256,"about_ca_topic_score_gemma":0.000124126,"domain_scores_codex":[0.9987152,0.00004805351,0.0004087029,0.0003818892,0.0002615998,0.0001845531],"domain_scores_gemma":[0.9983689,0.00005813778,0.000232516,0.00115628,0.000123817,0.00006035794],"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":[0.00007758536,0.0003643316,0.021436,0.001447985,0.001000651,0.00004592526,0.004676063,0.01998519,0.001105336,0.1319322,0.3683877,0.449541],"study_design_scores_gemma":[0.0004351518,0.00002975917,0.006314168,0.0002989409,0.00004810882,0.00001726986,0.0000781249,0.5117059,0.001248177,0.003542684,0.4755696,0.0007121083],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02461189,0.00003317668,0.9037672,0.001133128,0.00148036,0.0001146525,0.0001033049,0.0004620107,0.06829429],"genre_scores_gemma":[0.6595638,0.0002110715,0.2468337,0.002208363,0.0004357068,0.0001183526,0.001929029,0.00001507653,0.08868483],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6569335,"threshold_uncertainty_score":0.9946964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01878988256162153,"score_gpt":0.3083364524968135,"score_spread":0.289546569935192,"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."}}