# Next-step prediction on Synthetic HMM Undercomplete case, N=4000 Source: [Next-step prediction on Synthetic HMM Undercomplete case, N=4000]() Collection index: [llms.txt]() Data updated: 2026-04-27T07:39:51.959Z Evaluation of models performing next-step prediction on the Synthetic HMM Undercomplete case dataset (N=4000), measured by validation loss. 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 | Next-step prediction | | Dataset (including any stated split) | Synthetic HMM Undercomplete case, N=4000 | | Metric | Validation Loss | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 7 of 7 | | 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 - [Validation Loss](): Lower is better; unit: SCALAR. ## Recorded results | Method | Validation Loss | Result date | Report paper | | --- | --- | --- | --- | | HMM Filter | 1.368 | Not recorded | 6916b7a40052cac1dc65e1ea | | nanoGPT-s | 1.458 | Not recorded | 6916b7a40052cac1dc65e1ea | | nanoGPT-m | 1.475 | Not recorded | 6916b7a40052cac1dc65e1ea | | Belief Net | 1.569 | Not recorded | 6916b7a40052cac1dc65e1ea | | Spectral | 1.624 | Not recorded | 6916b7a40052cac1dc65e1ea | | Baum-Welch | 1.951 | Not recorded | 6916b7a40052cac1dc65e1ea | | Random | 4.852 | Not recorded | 6916b7a40052cac1dc65e1ea | ### HMM Filter Validation Loss: 1.368. Result ID: 69ef11b447f34ce924d4f1cf. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### nanoGPT-s Validation Loss: 1.458. Result ID: 69ef11b447f34ce924d4f1cc. [Reporting paper]() Recorded evaluation configuration: {"# parameters":"73,920","training time":"2.5 min","# iterations":"2,000 iter."}. This record does not assert independent reproduction. ### nanoGPT-m Validation Loss: 1.475. Result ID: 69ef11b447f34ce924d4f1cd. [Reporting paper]() Recorded evaluation configuration: {"# parameters":"221,760","training time":"7.5 min","# iterations":"2,000 iter."}. This record does not assert independent reproduction. ### Belief Net Validation Loss: 1.569. Result ID: 69ef11b447f34ce924d4f1ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# parameters":"12,352","training time":"20 min","# iterations":"2,000 iter."}. This record does not assert independent reproduction. ### Spectral Validation Loss: 1.624. Result ID: 69ef11b447f34ce924d4f1cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# parameters":"524,416","# iterations":"(PCA)"}. This record does not assert independent reproduction. ### Baum-Welch Validation Loss: 1.951. Result ID: 69ef11b447f34ce924d4f1ca. [Reporting paper]() Recorded evaluation configuration: {"# parameters":"12,352","training time":"51 min","# iterations":"20 iter."}. This record does not assert independent reproduction. ### Random Validation Loss: 4.852. Result ID: 69ef11b447f34ce924d4f1d0. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.