{"id":"W2400703308","doi":"10.1609/socs.v3i1.18241","title":"Are We There Yet? — Estimating Search Progress","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Combinatorial Search","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Incremental heuristic search; Beam search; Heuristic; Best-first search; Iterative deepening depth-first search; Bidirectional search; Search algorithm; Computer science; Focus (optics); Path (computing); Mathematical optimization; Beam stack search; Search problem; Algorithm; Mathematics; Artificial intelligence","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":[0.0009056724,0.0001786511,0.0002033197,0.00008205175,0.0003030909,0.0005333361,0.002465994,0.0001004652,0.00002765657],"category_scores_gemma":[0.0002405359,0.0001421864,0.0001309713,0.0005339968,0.0000981185,0.000365004,0.001126305,0.0005328333,0.00002049726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602105,"about_ca_system_score_gemma":0.0001568443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000312249,"about_ca_topic_score_gemma":7.51013e-7,"domain_scores_codex":[0.9972534,0.00004325203,0.0003242467,0.0004813387,0.001536781,0.0003609693],"domain_scores_gemma":[0.9978558,0.0002749056,0.0002578086,0.0002466297,0.001265324,0.00009950885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000165742,0.0007562184,0.08306169,0.0003784677,0.0002412798,0.00004084049,0.002710501,0.002150438,0.02411739,0.8704406,0.009022506,0.006914324],"study_design_scores_gemma":[0.003026133,0.0005206721,0.006469116,0.003970208,0.00003366074,0.0001294903,0.0007477506,0.235339,0.6601921,0.07802203,0.01061665,0.0009331473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8417601,0.0003971348,0.00136081,0.1133453,0.0150835,0.0006770011,0.00002755812,0.0003521749,0.0269964],"genre_scores_gemma":[0.9926602,0.00001426628,0.006032897,0.0001581866,0.0004617374,0.00002159943,0.000002324299,0.00002059711,0.0006281816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7924186,"threshold_uncertainty_score":0.5798191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02905911484794281,"score_gpt":0.288302032702786,"score_spread":0.2592429178548432,"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."}}