{"id":"W6947728179","doi":"10.48448/wmk6-t180","title":"LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Minnow Environmental (Canada)","funders":"","keywords":"Parsing; Generalization; Task (project management); Natural language; Meaning (existential); Representation (politics); Graph; Baseline (sea)","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":[0.003004314,0.002107269,0.0008471015,0.001806381,0.001137023,0.001685438,0.002506889,0.002319748,0.009955102],"category_scores_gemma":[0.01101018,0.001060756,0.002301889,0.001506116,0.001920443,0.006725563,0.003707078,0.004285997,0.005793799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001161268,"about_ca_system_score_gemma":0.002170854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00442242,"about_ca_topic_score_gemma":0.01204148,"domain_scores_codex":[0.9975374,0.0009638933,0.0001078144,0.0009397647,0.0003566031,0.00009450547],"domain_scores_gemma":[0.9941678,0.003201959,0.0003027286,0.001699426,0.0004919874,0.0001361658],"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":[0.0005164245,0.0004163581,0.00305146,0.0007589961,0.0002871081,0.0009400051,0.001554786,0.1456298,0.0316015,0.1198563,0.07997959,0.6154076],"study_design_scores_gemma":[0.00007429749,0.0000661807,0.0005406126,0.00007136614,0.00005916552,0.000240198,0.0001728174,0.6552169,0.01526479,0.3022847,0.02593537,0.00007361617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004510947,0.0001226982,0.9665354,0.0003744695,0.00006872854,0.00008430013,0.001113578,0.02568367,0.001506261],"genre_scores_gemma":[0.09694495,0.0002029129,0.8848714,0.0007640141,0.00008281017,0.0002577283,0.008026881,0.0055672,0.003282152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009955102,"threshold_uncertainty_score":0.03330314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02903384472066008,"score_gpt":0.276883119031344,"score_spread":0.247849274310684,"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."}}