# Title Similarity on e-commerce title similarity (test) Source: [Title Similarity on e-commerce title similarity (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:58.195Z Evaluation of Title Similarity performance on the test split of the e-commerce title similarity dataset, measured using Accuracy. 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 | Title Similarity | | Dataset (including any stated split) | e-commerce title similarity (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | GP-TS psi | 98 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.10 | 97.9 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.25 | 97.9 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.30 | 97.9 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.35 | 97.9 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.50 | 97.9 | Not recorded | 68fa6f9a1e209131cea468b5 | | GP-TS rho | 97.9 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.05 | 97.8 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.15 | 97.8 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.20 | 97.8 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.40 | 97.8 | Not recorded | 68fa6f9a1e209131cea468b5 | | p=0.45 | 97.8 | Not recorded | 68fa6f9a1e209131cea468b5 | | RoBERTa base | 97.2 | Not recorded | 68fa6f9a1e209131cea468b5 | ### GP-TS psi Accuracy: 98. Result ID: 6990e3263a6c314849040a18. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":10}. This record does not assert independent reproduction. ### p=0.10 Accuracy: 97.9. Result ID: 6990e3263a6c314849040a0e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":27}. This record does not assert independent reproduction. ### p=0.25 Accuracy: 97.9. Result ID: 6990e3263a6c314849040a11. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":17}. This record does not assert independent reproduction. ### p=0.30 Accuracy: 97.9. Result ID: 6990e3263a6c314849040a12. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":19}. This record does not assert independent reproduction. ### p=0.35 Accuracy: 97.9. Result ID: 6990e3263a6c314849040a13. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":9}. This record does not assert independent reproduction. ### p=0.50 Accuracy: 97.9. Result ID: 6990e3263a6c314849040a16. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":8}. This record does not assert independent reproduction. ### GP-TS rho Accuracy: 97.9. Result ID: 6990e3263a6c314849040a17. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":13}. This record does not assert independent reproduction. ### p=0.05 Accuracy: 97.8. Result ID: 6990e3263a6c314849040a0d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":26}. This record does not assert independent reproduction. ### p=0.15 Accuracy: 97.8. Result ID: 6990e3263a6c314849040a0f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":13}. This record does not assert independent reproduction. ### p=0.20 Accuracy: 97.8. Result ID: 6990e3263a6c314849040a10. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":8}. This record does not assert independent reproduction. ### p=0.40 Accuracy: 97.8. Result ID: 6990e3263a6c314849040a14. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":9}. This record does not assert independent reproduction. ### p=0.45 Accuracy: 97.8. Result ID: 6990e3263a6c314849040a15. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":11}. This record does not assert independent reproduction. ### RoBERTa base Accuracy: 97.2. Result ID: 6990e3263a6c314849040a0c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"fine-tuning":true,"at interaction":0}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.