{"id":"W7106839996","doi":"10.48448/73y8-jk80","title":"Coarse-to-Fine Grounded Memory for LLM Agent Planning","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Leverage (statistics); Flexibility (engineering); Key (lock); Focus (optics); Plan (archaeology); Grounded theory; Quality (philosophy)","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":[0.0006402507,0.00114236,0.0007813586,0.0004876851,0.0005479196,0.001241463,0.002703091,0.000896973,0.00572392],"category_scores_gemma":[0.003157548,0.0004848886,0.0007529724,0.000501745,0.0007672661,0.002628149,0.002753505,0.001611057,0.001431614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008374024,"about_ca_system_score_gemma":0.001870729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008354988,"about_ca_topic_score_gemma":0.01733665,"domain_scores_codex":[0.9995896,0.00008234687,0.00004047231,0.0001501357,0.00007749167,0.00005993314],"domain_scores_gemma":[0.9992777,0.0002261376,0.00006924651,0.0002841485,0.00008332333,0.00005959144],"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":[0.000419948,0.0002384132,0.002594414,0.0004253552,0.0001347655,0.0002474631,0.00059701,0.3744412,0.009449499,0.02335064,0.01281093,0.5752903],"study_design_scores_gemma":[0.00004952056,0.00007186396,0.0002402704,0.00002491889,0.00003708664,0.00004946731,0.00007615273,0.9594385,0.003586406,0.03105552,0.005346971,0.00002320544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03066779,0.001021272,0.9444442,0.0005424321,0.0001278699,0.0001539887,0.0006274095,0.01652718,0.00588786],"genre_scores_gemma":[0.5594757,0.0004379186,0.432858,0.0004510313,0.00004223034,0.0002855074,0.001030335,0.0007579228,0.00466151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008354988,"threshold_uncertainty_score":0.01914841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1066163613675271,"score_gpt":0.3845806528100807,"score_spread":0.2779642914425536,"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."}}