Contamination MapTabular / Model
Mitra
- Organisation
- Amazon
- Family
- Mitra · version v1
- Released
- 2025-06-22 (Hugging Face repo creation date (API createdAt) https://huggingface.co/api/models/autogluon/mitra-classifier (paper arXiv 2510.21204 posted 2025-10-24))
- Checkpoints
- autogluon/mitra-classifier, autogluon/mitra-regressor, autogluon/mitra-classifier-1.1
- Weights
- Open · Apache-2.0
- Links
- PaperModel cardCode
Training data disclosure: Full list
Level determined for 100% of benchmark cells.
- TestTest data seen0
- SeenSeen, split unclear0
- TrainTraining data seen0
- Related data seen0
- NoNot seen51
- ?Unknown0
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Other declared training data
-
Mitra mixture of synthetic priors (SCM and tree-based generators) · split: unknown
Evidence
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
huggingface.co · model card · Model card intro · retrieved 2026-10-15 “pre-trained on purely synthetic datasets”
huggingface.co · model card · Model card intro · retrieved 2026-10-15
Benchmark cells
TabArena
Not seen airfoil_self_noise · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Amazon_employee_access · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen anneal · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Another-Dataset-on-used-Fiat-500 · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen APSFailure · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen bank-marketing · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Bank_Customer_Churn · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Bioresponse · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen blood-transfusion-service-center · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen churn · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen coil2000_insurance_policies · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen concrete_compressive_strength · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen credit-g · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen credit_card_clients_default · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen customer_satisfaction_in_airline · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen diabetes · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Diabetes130US · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen diamonds · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen E-CommereShippingData · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Fitness_Club · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Food_Delivery_Time · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen GiveMeSomeCredit · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen hazelnut-spread-contaminant-detection · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen healthcare_insurance_expenses · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen heloc · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen hiva_agnostic · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen houses · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen HR_Analytics_Job_Change_of_Data_Scientists · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen in_vehicle_coupon_recommendation · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Is-this-a-good-customer · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen kddcup09_appetency · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen Marketing_Campaign · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen maternal_health_risk · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen miami_housing · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen MIC · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen NATICUSdroid · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen online_shoppers_intention · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen physiochemical_protein · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen polish_companies_bankruptcy · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen qsar-biodeg · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen QSAR-TID-11 · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen QSAR_fish_toxicity · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen SDSS17 · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen seismic-bumps · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen splice · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen students_dropout_and_academic_success · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen superconductivity · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen taiwanese_bankruptcy_prediction · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen website_phishing · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen wine_quality · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Not seen jm1 · absent from the complete list of training data
Evidence (1)
“Mitra classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers.”
Notes
72M-parameter 12-layer transformer. autogluon/mitra-classifier-1.1 (HF repo created 2026-03-12) has a card identical to v1 and no separate documentation; grouped here.
Sources
- Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models (arXiv v1) · paper · retrieved 2026-10-15
- autogluon/mitra-classifier model card · model card · retrieved 2026-10-15
- autogluon/mitra-regressor model card · model card · retrieved 2026-10-15
- autogluon/mitra-classifier-1.1 model card · model card · retrieved 2026-10-15