{"id":"W4382239581","doi":"10.1609/aaai.v37i4.25527","title":"Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Theoretical computer science; Artificial intelligence; Graph; Beam search; Machine learning; Search algorithm; 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":[0.0008440565,0.0001153776,0.0001255929,0.0000875459,0.0003363137,0.0002810126,0.0006693725,0.00005338384,0.000005128107],"category_scores_gemma":[0.0002657326,0.00007602049,0.00004229076,0.0003639409,0.0003806219,0.0002364137,0.0002585014,0.0001963496,0.000006967298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000118014,"about_ca_system_score_gemma":0.00004620208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005003478,"about_ca_topic_score_gemma":0.000006978863,"domain_scores_codex":[0.9988887,0.000008688095,0.0002566854,0.0003484321,0.000252693,0.0002447951],"domain_scores_gemma":[0.9990467,0.0003176198,0.0001325449,0.0001696008,0.0002806099,0.00005293079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001287874,0.000007865307,0.0003008366,0.00002487738,0.000007434437,1.32634e-7,0.0008315272,0.00005632613,0.008181552,0.7530135,0.0000289896,0.2375341],"study_design_scores_gemma":[0.0000405414,0.0001048772,0.001955584,0.000174348,0.00001392091,0.00001569088,0.00199454,0.6477664,0.1407048,0.2069593,0.0001051482,0.0001647731],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.804803,0.0001283443,0.1773371,0.01323117,0.0007196275,0.001136997,0.000009239127,0.0002207475,0.002413763],"genre_scores_gemma":[0.9970692,0.000197427,0.002497649,0.0000793705,0.00003591706,0.00002787683,2.008101e-7,0.000006301104,0.00008606865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6477101,"threshold_uncertainty_score":0.3100025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1176371003688176,"score_gpt":0.3206746685680134,"score_spread":0.2030375681991958,"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."}}