# Causal Representation Learning on Synthetic Numerical Experiments Source: [Causal Representation Learning on Synthetic Numerical Experiments]() Collection index: [llms.txt]() Data updated: 2026-04-16T06:43:01.788Z Evaluation of models on the Synthetic Numerical Experiments dataset focusing on Causal Representation Learning, measured using metrics like R^2 and MCC variants. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Causal Representation Learning | | Dataset (including any stated split) | Synthetic Numerical Experiments | | Metric | R^2 Stage 1 | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 34 of 34 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [R^2 Stage 1](): Higher is better; unit: SCALAR. - [MCC Stage 1](): Higher is better; unit: SCALAR. - [MCC Stage 2](): Higher is better; unit: SCALAR. - [MCC VaDE](): Higher is better; unit: SCALAR. ## Recorded results | Method | R^2 Stage 1 | Result date | Report paper | | --- | --- | --- | --- | | two-stage method | 0.99 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.96 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.96 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.95 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.95 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.94 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.94 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.94 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.93 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.93 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.93 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.93 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.93 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.93 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.92 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.88 | Not recorded | 69e06ced7d0172140ec7c909 | | two-stage method | 0.75 | Not recorded | 69e06ced7d0172140ec7c909 | ### two-stage method R^2 Stage 1: 0.99. Result ID: 69e084b047f34ce924c9299f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"3","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.96. Result ID: 69e084b047f34ce924c929a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"50%","delta":"2","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.96. Result ID: 69e084b047f34ce924c929ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"50%","delta":"3","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.95. Result ID: 69e084b047f34ce924c929a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"75%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.95. Result ID: 69e084b047f34ce924c929a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"50%","delta":"1","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.94. Result ID: 69e084b047f34ce924c92993. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.94. Result ID: 69e084b047f34ce924c92997. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"40","k":"1","m":"10","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.94. Result ID: 69e084b047f34ce924c92999. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"0","m":"10","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.93. Result ID: 69e084b047f34ce924c92991. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"5","k":"1","m":"10","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.93. Result ID: 69e084b047f34ce924c92995. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"20","k":"1","m":"10","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.93. Result ID: 69e084b047f34ce924c9299b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"2","m":"10","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.93. Result ID: 69e084b047f34ce924c929ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"50%","delta":"0","theta":"15"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.93. Result ID: 69e084b047f34ce924c929af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"50%","delta":"0","theta":"30"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.93. Result ID: 69e084b047f34ce924c929b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"50%","delta":"0","theta":"45"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.92. Result ID: 69e084b047f34ce924c9299d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"3","m":"10","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.88. Result ID: 69e084b047f34ce924c929a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"20","rho":"50%","delta":"0","theta":"0"}. This record does not assert independent reproduction. ### two-stage method R^2 Stage 1: 0.75. Result ID: 69e084b047f34ce924c929a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"n":"10","k":"1","m":"10","rho":"1 var","delta":"0","theta":"0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.