{"id":"W4377104115","doi":"10.3390/a16050259","title":"Using Deep-Learned Vector Representations for Page Stream Segmentation by Agglomerative Clustering","year":2023,"lang":"en","type":"article","venue":"Algorithms","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Cluster analysis; Task (project management); Digitization; Artificial intelligence; Segmentation; Information retrieval; Pattern recognition (psychology); Computer vision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005453723,0.001963972,0.001279455,0.002370793,0.0004990071,0.001613463,0.002259499,0.001734245,0.002620678],"category_scores_gemma":[0.002152283,0.0006503128,0.001518862,0.002738459,0.0007059066,0.003017452,0.0008978042,0.002344644,0.003299829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001805741,"about_ca_system_score_gemma":0.00138217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02000635,"about_ca_topic_score_gemma":0.02191817,"domain_scores_codex":[0.9994543,0.00007393771,0.00003056359,0.0002409088,0.0001045355,0.00009570323],"domain_scores_gemma":[0.9993128,0.0001824656,0.00008801754,0.0001768703,0.0001880659,0.00005180945],"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":[0.0005322011,0.0003943247,0.003739422,0.0002255012,0.0001946041,0.0001558944,0.0002300596,0.3468178,0.01547473,0.006889525,0.02578149,0.5995646],"study_design_scores_gemma":[0.00001151785,0.00002690232,0.0002607009,0.00001008421,0.00001032352,0.00002562864,0.00002501627,0.990935,0.003253391,0.004299288,0.001131457,0.00001056308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1290534,0.002356302,0.8345336,0.0006574927,0.0003167521,0.0002163478,0.003042893,0.02570814,0.004115065],"genre_scores_gemma":[0.5464425,0.001085251,0.4237958,0.0005386028,0.000166665,0.0002788843,0.01564403,0.00119507,0.01085324],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02000635,"threshold_uncertainty_score":0.03977984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07573312849697603,"score_gpt":0.3630044820616022,"score_spread":0.2872713535646262,"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."}}