# Spoiler type classification on Clickbait Spoiling 1.0 (test) Source: [Spoiler type classification on Clickbait Spoiling 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:37:31.032Z Evaluation of Spoiler Type Classification performance on the test split of the Clickbait Spoiling 1.0 dataset, measured using Balanced Accuracy across multi-class and one-vs-rest settings (Phrase, Passage, Multipart). 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 | Spoiler type classification | | Dataset (including any stated split) | Clickbait Spoiling 1.0 (test) | | Metric | Balanced Acc (Multi-class) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Balanced Acc (Multi-class)](): Higher is better; unit: PERCENT. - [Balanced Acc (OVR: Phrase)](): Higher is better; unit: PERCENT. - [Balanced Acc (OVR: Passage)](): Higher is better; unit: PERCENT. - [Balanced Acc (OVR: Multipart)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Balanced Acc (Multi-class) | Result date | Report paper | | --- | --- | --- | --- | | DeBERTa | 73.63 | Not recorded | 68fa6c141e209131cea31ffd | | RoBERTa | 71.57 | Not recorded | 68fa6c141e209131cea31ffd | | BERT | 67.84 | Not recorded | 68fa6c141e209131cea31ffd | | Log. Regression | 60.04 | Not recorded | 68fa6c141e209131cea31ffd | | SVM | 59.62 | Not recorded | 68fa6c141e209131cea31ffd | | Naïve Bayes | 56.15 | Not recorded | 68fa6c141e209131cea31ffd | ### DeBERTa Balanced Acc (Multi-class): 73.63. Result ID: 698eca61ffc3901de0a13784. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"hyperparameter\_optimization":"grid search"}. This record does not assert independent reproduction. ### RoBERTa Balanced Acc (Multi-class): 71.57. Result ID: 698eca61ffc3901de0a13785. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"hyperparameter\_optimization":"grid search"}. This record does not assert independent reproduction. ### BERT Balanced Acc (Multi-class): 67.84. Result ID: 698eca61ffc3901de0a13783. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"hyperparameter\_optimization":"grid search"}. This record does not assert independent reproduction. ### Log. Regression Balanced Acc (Multi-class): 60.04. Result ID: 698eca61ffc3901de0a13782. [Reporting paper]() Recorded evaluation configuration: {"feature\_selection":"chi-square","feature\_weighting":"post-based features weighted 4x"}. This record does not assert independent reproduction. ### SVM Balanced Acc (Multi-class): 59.62. Result ID: 698eca61ffc3901de0a13781. [Reporting paper]() Recorded evaluation configuration: {"feature\_selection":"chi-square","feature\_weighting":"post-based features weighted 4x"}. This record does not assert independent reproduction. ### Naïve Bayes Balanced Acc (Multi-class): 56.15. Result ID: 698eca61ffc3901de0a13780. [Reporting paper]() Recorded evaluation configuration: {"feature\_selection":"chi-square","feature\_weighting":"post-based features weighted 4x"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.