{"id":"W4392271337","doi":"10.48550/arxiv.2402.17464","title":"Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Canadian Institute for Advanced Research; Vector Institute; University of British Columbia; Government of Canada","keywords":"Generative grammar; Hierarchy; Computer science; Message passing; Generative model; Artificial intelligence; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001533479,0.0004781345,0.000392057,0.0002763857,0.0001606676,0.0002282779,0.0004020967,0.0004107662,0.0001895999],"category_scores_gemma":[0.00001094381,0.0005474334,0.0001834567,0.0003291876,0.00006882997,0.0001897264,0.0005725277,0.0009821948,0.0001788497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002702546,"about_ca_system_score_gemma":0.00008085816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002675815,"about_ca_topic_score_gemma":0.00003264636,"domain_scores_codex":[0.9983245,0.00006730924,0.000260311,0.0008209608,0.0001065609,0.0004203657],"domain_scores_gemma":[0.9990588,0.00004697561,0.0000965733,0.0005510076,0.00007911185,0.000167538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000913958,0.00001999157,0.00004339064,0.0005635839,0.0002004634,0.0002147282,0.0002331845,0.9934909,0.00006629373,0.001673565,0.001792536,0.001692259],"study_design_scores_gemma":[0.0002251939,0.00001835916,0.00005104924,0.0003772652,0.0002207505,0.000002931909,0.00004275706,0.9702848,0.002362274,0.009332589,0.01637081,0.00071128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2021471,0.001272729,0.7572063,0.000159573,0.004166165,0.0006314844,0.0001813989,0.002133587,0.03210176],"genre_scores_gemma":[0.9927514,0.0005862144,0.000968193,0.00004330017,0.0004405913,0.000005095053,0.0001748006,0.0001026937,0.004927665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7906044,"threshold_uncertainty_score":0.9996977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04128550560194362,"score_gpt":0.1774156107145556,"score_spread":0.1361301051126119,"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."}}