# Classification on CSQA Source: [Classification on CSQA]() Collection index: [llms.txt]() Data updated: 2026-06-05T09:01:22.561Z Evaluation of standard Classification performance on the CSQA dataset, reporting Expected Calibration Error (ECE) and Brier Score (BS). 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 | Classification | | Dataset (including any stated split) | CSQA | | Metric | Expected Calibration Error (ECE) | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 16 of 16 | | 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 - [Expected Calibration Error (ECE)](): Lower is better; unit: PERCENT. - [Brier Score (BS)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Expected Calibration Error (ECE) | Result date | Report paper | | --- | --- | --- | --- | | CaliDist (As.) | 2.21 | Not recorded | 6a2258a086173ad9c1468bcb | | CaliDist (As.) | 2.32 | Not recorded | 6a2258a086173ad9c1468bcb | | CaliDist (Sa.) | 2.51 | Not recorded | 6a2258a086173ad9c1468bcb | | CaliDist (Pr.) | 2.55 | Not recorded | 6a2258a086173ad9c1468bcb | | CaliDist (Pr.) | 2.89 | Not recorded | 6a2258a086173ad9c1468bcb | | CaliDist (Sa.) | 3.35 | Not recorded | 6a2258a086173ad9c1468bcb | | Temperature Scaling | 4.57 | Not recorded | 6a2258a086173ad9c1468bcb | | Vanilla | 11.13 | Not recorded | 6a2258a086173ad9c1468bcb | | Consistency | 11.52 | Not recorded | 6a2258a086173ad9c1468bcb | | FSD | 14.65 | Not recorded | 6a2258a086173ad9c1468bcb | | Entropy | 20.46 | Not recorded | 6a2258a086173ad9c1468bcb | | Temperature Scaling | 23.87 | Not recorded | 6a2258a086173ad9c1468bcb | | Vanilla | 25.44 | Not recorded | 6a2258a086173ad9c1468bcb | | Entropy | 25.48 | Not recorded | 6a2258a086173ad9c1468bcb | | FSD | 25.49 | Not recorded | 6a2258a086173ad9c1468bcb | | Consistency | 25.54 | Not recorded | 6a2258a086173ad9c1468bcb | ### CaliDist (As.) Expected Calibration Error (ECE): 2.21. Result ID: 6a228fdcfbc373592c20cd58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### CaliDist (As.) Expected Calibration Error (ECE): 2.32. Result ID: 6a228fdcfbc373592c20cd60. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. ### CaliDist (Sa.) Expected Calibration Error (ECE): 2.51. Result ID: 6a228fdcfbc373592c20cd62. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. ### CaliDist (Pr.) Expected Calibration Error (ECE): 2.55. Result ID: 6a228fdcfbc373592c20cd61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. ### CaliDist (Pr.) Expected Calibration Error (ECE): 2.89. Result ID: 6a228fdcfbc373592c20cd59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### CaliDist (Sa.) Expected Calibration Error (ECE): 3.35. Result ID: 6a228fdcfbc373592c20cd5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### Temperature Scaling Expected Calibration Error (ECE): 4.57. Result ID: 6a228fdcfbc373592c20cd53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### Vanilla Expected Calibration Error (ECE): 11.13. Result ID: 6a228fdcfbc373592c20cd54. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### Consistency Expected Calibration Error (ECE): 11.52. Result ID: 6a228fdcfbc373592c20cd55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### FSD Expected Calibration Error (ECE): 14.65. Result ID: 6a228fdcfbc373592c20cd57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### Entropy Expected Calibration Error (ECE): 20.46. Result ID: 6a228fdcfbc373592c20cd56. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Phi-4-mini (3.8B)"}. This record does not assert independent reproduction. ### Temperature Scaling Expected Calibration Error (ECE): 23.87. Result ID: 6a228fdcfbc373592c20cd5b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. ### Vanilla Expected Calibration Error (ECE): 25.44. Result ID: 6a228fdcfbc373592c20cd5c. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. ### Entropy Expected Calibration Error (ECE): 25.48. Result ID: 6a228fdcfbc373592c20cd5e. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. ### FSD Expected Calibration Error (ECE): 25.49. Result ID: 6a228fdcfbc373592c20cd5f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. ### Consistency Expected Calibration Error (ECE): 25.54. Result ID: 6a228fdcfbc373592c20cd5d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM":"Gemma-3 (4B)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.