{"id":"W3006544536","doi":"10.48550/arxiv.2002.05825","title":"An Inductive Bias for Distances: Neural Nets that Respect the Triangle\\n Inequality","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Triangle inequality; Inductive bias; Subadditivity; Artificial neural network; Mathematics; Reinforcement learning; Metric space; Metric (unit); Euclidean space; Computer science; Discrete mathematics; Theoretical computer science; Artificial intelligence; Combinatorics; Multi-task learning; Task (project management)","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":[0.003698754,0.001246533,0.001123206,0.0008494407,0.0008393803,0.002149326,0.002818268,0.002253372,0.004516637],"category_scores_gemma":[0.03021623,0.0006141912,0.0008715084,0.00106674,0.003381451,0.007917248,0.005485655,0.005233251,0.001138678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002153809,"about_ca_system_score_gemma":0.001172539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001733459,"about_ca_topic_score_gemma":0.002459322,"domain_scores_codex":[0.9973611,0.0008314532,0.0001505874,0.0006082383,0.0007967105,0.0002518595],"domain_scores_gemma":[0.9905499,0.005343693,0.0008569971,0.001586873,0.001238044,0.0004244635],"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":[0.0002575683,0.00007734055,0.002186446,0.0002400174,0.00007850651,0.0001377443,0.0002627672,0.2424631,0.005828725,0.649945,0.003962873,0.09455991],"study_design_scores_gemma":[0.00002072373,0.0001253891,0.0002825784,0.0000442854,0.00001463107,0.00009656699,0.00003159488,0.6961002,0.002985249,0.2975828,0.002700193,0.00001583055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.023041,0.0004277638,0.9673379,0.0009085915,0.00008159663,0.0000452715,0.00009712377,0.0003077255,0.00775307],"genre_scores_gemma":[0.6986225,0.0009166519,0.2853189,0.001281547,0.0002727124,0.0003654865,0.0004921124,0.0005384098,0.01219157],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004516637,"threshold_uncertainty_score":0.01956111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3062366027530909,"score_gpt":0.2567398886339681,"score_spread":0.04949671411912282,"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."}}