# Image Classification on Surgical correction experiment dataset (train milestones) Source: [Image Classification on Surgical correction experiment dataset (train milestones)]() Collection index: [llms.txt]() Data updated: 2026-04-01T06:52:01.164Z Evaluation of Image Classification performance on the Surgical correction experiment dataset (train milestones split), reporting accuracy thresholds and associated counts. 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 | Image Classification | | Dataset (including any stated split) | Surgical correction experiment dataset (train milestones) | | Metric | Best Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Best Accuracy](): Higher is better; unit: PERCENT. - [Count (Threshold 80%)](): Higher is better; unit: SCALAR. - [Count (Threshold 85%)](): Higher is better; unit: SCALAR. - [Count (Threshold 90%)](): Higher is better; unit: SCALAR. - [Count (Threshold 92%)](): Higher is better; unit: SCALAR. - [Count (Threshold 95%)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Best Accuracy | Result date | Report paper | | --- | --- | --- | --- | | 1cycle (Smith) | 95.36 | Not recorded | 69cca66e0636e5bf4afcba5e | | Hybrid-ep52 | 95.36 | Not recorded | 69cca66e0636e5bf4afcba5e | | Baseline (µ = 0.9) | 95.33 | Not recorded | 69cca66e0636e5bf4afcba5e | | Hybrid-90 | 95.3 | Not recorded | 69cca66e0636e5bf4afcba5e | | Physics (µ = 1−2√α) | 95.11 | Not recorded | 69cca66e0636e5bf4afcba5e | ### 1cycle (Smith) Best Accuracy: 95.36. Result ID: 69ccc05947f34ce924b5e361. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Hybrid-ep52 Best Accuracy: 95.36. Result ID: 69ccc05947f34ce924b5e363. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Switch":"ep52"}. This record does not assert independent reproduction. ### Baseline (µ = 0.9) Best Accuracy: 95.33. Result ID: 69ccc05947f34ce924b5e35f. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Hybrid-90 Best Accuracy: 95.3. Result ID: 69ccc05947f34ce924b5e362. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Switch":"ep47"}. This record does not assert independent reproduction. ### Physics (µ = 1−2√α) Best Accuracy: 95.11. Result ID: 69ccc05947f34ce924b5e360. [Reporting paper]() [Method origin 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.