{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002666028,0.001670253,0.001427205,0.003823208,0.001421358,0.002153591,0.00169375,0.001825788,0.01062593],"category_scores_gemma":[0.006204205,0.00130092,0.001167045,0.003072925,0.0007867823,0.005047009,0.003862165,0.002737616,0.01024426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009764861,"about_ca_system_score_gemma":0.001613583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007179645,"about_ca_topic_score_gemma":0.01196224,"domain_scores_codex":[0.9973105,0.0002953138,0.0001328971,0.001216418,0.0008762311,0.0001686699],"domain_scores_gemma":[0.9978248,0.0004893793,0.0001000612,0.0008876473,0.0005419302,0.0001562331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008579287,0.0005536859,0.005698609,0.0004916513,0.0003302677,0.001323455,0.0005628505,0.007259698,0.05628211,0.005336115,0.1792708,0.7420328],"study_design_scores_gemma":[0.0002817692,0.0002891779,0.01409202,0.0001441238,0.0001552532,0.003222025,0.000421669,0.502102,0.2015802,0.02143374,0.256045,0.0002329876],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06541505,0.001764563,0.5652616,0.001703087,0.0004516168,0.0007603056,0.01523366,0.3301452,0.01926486],"genre_scores_gemma":[0.2143948,0.0007595267,0.6820048,0.0009230801,0.0001274542,0.000398763,0.06179543,0.00885859,0.03073751],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01062593,"threshold_uncertainty_score":0.03554726,"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."}}