{"id":"W2674238586","doi":"10.1145/3091107","title":"Search by Screenshots for Universal Article Clipping in Mobile Apps","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Chunking (psychology); Usability; Clipping (morphology); Rank (graph theory); Learning to rank; Key (lock); Artificial intelligence; Human–computer interaction; Ranking (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":[0.0006953799,0.002140268,0.001338601,0.004694532,0.0007877069,0.001683909,0.001032618,0.001014269,0.01176622],"category_scores_gemma":[0.005920581,0.0004600791,0.0008961295,0.002061674,0.0005616792,0.003227294,0.002094809,0.0007409683,0.004997952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005753562,"about_ca_system_score_gemma":0.0007033116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003476993,"about_ca_topic_score_gemma":0.009333991,"domain_scores_codex":[0.9991404,0.000184695,0.00006398889,0.0001968494,0.0003057228,0.0001083714],"domain_scores_gemma":[0.9964379,0.001822685,0.0002434274,0.0005848564,0.000631902,0.0002792533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001859778,0.0005601875,0.003890076,0.00232671,0.000180113,0.001387772,0.001778467,0.005291336,0.09023091,0.004493746,0.07498226,0.8130186],"study_design_scores_gemma":[0.000421268,0.002819408,0.02893196,0.0005531135,0.0004283855,0.004315007,0.005022647,0.5638672,0.187673,0.02661746,0.178857,0.0004934921],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1963445,0.006087406,0.6551557,0.001155769,0.0005152962,0.002555856,0.01073482,0.1019351,0.02551552],"genre_scores_gemma":[0.3659181,0.001336885,0.6060811,0.000514795,0.0003234268,0.0009857392,0.01029735,0.001899439,0.01264315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01176622,"threshold_uncertainty_score":0.03936195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02974584000255332,"score_gpt":0.2824627019365408,"score_spread":0.2527168619339875,"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."}}