# Binary temporal relation classification on TRACIE, MATRES, and TODAY (test) Source: [Binary temporal relation classification on TRACIE, MATRES, and TODAY (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:01.333Z Evaluation of Binary temporal relation classification performance across the test splits of the TRACIE, MATRES, and TODAY datasets. 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 | Binary temporal relation classification | | Dataset (including any stated split) | TRACIE, MATRES, and TODAY (test) | | Metric | TRACIE Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [TRACIE Accuracy](): Higher is better; unit: PERCENT. - [MATRES Accuracy](): Higher is better; unit: PERCENT. - [TODAY Accuracy](): Higher is better; unit: PERCENT. - [TODAY Accuracy (gold exp.)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | TRACIE Accuracy | Result date | Report paper | | --- | --- | --- | --- | | PatternTime (all) | 79.9 | Not recorded | 68fa6f961e209131cea46784 | | PatternTime (M+T+O) | 79.8 | Not recorded | 68fa6f961e209131cea46784 | | PatternTime (M+T) | 79.7 | Not recorded | 68fa6f961e209131cea46784 | | PatternTime | 77 | Not recorded | 68fa6f961e209131cea46784 | | T5 (T+O+G) | 73.5 | Not recorded | 68fa6f961e209131cea46784 | | T5 (M+T+O+G) | 73.3 | Not recorded | 68fa6f961e209131cea46784 | | T5 (M+T+O) | 73 | Not recorded | 68fa6f961e209131cea46784 | | T5 (T+O) | 72.9 | Not recorded | 68fa6f961e209131cea46784 | | T5 (in-domain) | 66.2 | Not recorded | 68fa6f961e209131cea46784 | | T5 (T) | 66.2 | Not recorded | 68fa6f961e209131cea46784 | | T5 (M+T) | 66.2 | Not recorded | 68fa6f961e209131cea46784 | | GPT-3.5 text-davinci-002 | 56.1 | Not recorded | 68fa6f961e209131cea46784 | | T5 (O+G) | 55.4 | Not recorded | 68fa6f961e209131cea46784 | | T5 (M) | 52.7 | Not recorded | 68fa6f961e209131cea46784 | | GPT-3.5 text-davinci-003 | 52.3 | Not recorded | 68fa6f961e209131cea46784 | | T5 (M+O) | 51.5 | Not recorded | 68fa6f961e209131cea46784 | | T5 (O) | 50.6 | Not recorded | 68fa6f961e209131cea46784 | | T5 (M+O+G) | 49.9 | Not recorded | 68fa6f961e209131cea46784 | ### PatternTime (all) TRACIE Accuracy: 79.9. Result ID: 6990e1f73a6c3148490401f8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"MATRES + TRACIE + TODAY + GPT-3.5","Loss":"CE + MR"}. This record does not assert independent reproduction. ### PatternTime (M+T+O) TRACIE Accuracy: 79.8. Result ID: 6990e1f73a6c3148490401f7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"MATRES + TRACIE + TODAY","Loss":"CE + MR"}. This record does not assert independent reproduction. ### PatternTime (M+T) TRACIE Accuracy: 79.7. Result ID: 6990e1f73a6c3148490401f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train Data":"MATRES + TRACIE","Loss":"CE"}. This record does not assert independent reproduction. ### PatternTime TRACIE Accuracy: 77. Result ID: 6990e1f73a6c3148490401ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train Data":"Distant","Loss":"Distant"}. This record does not assert independent reproduction. ### T5 (T+O+G) TRACIE Accuracy: 73.5. Result ID: 6990e1f73a6c3148490401f2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"TRACIE + TODAY + GPT-3.5","Loss":"CE + MR"}. This record does not assert independent reproduction. ### T5 (M+T+O+G) TRACIE Accuracy: 73.3. Result ID: 6990e1f73a6c3148490401f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"MATRES + TRACIE + TODAY + GPT-3.5","Loss":"CE + MR"}. This record does not assert independent reproduction. ### T5 (M+T+O) TRACIE Accuracy: 73. Result ID: 6990e1f73a6c3148490401f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"MATRES + TRACIE + TODAY","Loss":"CE + MR"}. This record does not assert independent reproduction. ### T5 (T+O) TRACIE Accuracy: 72.9. Result ID: 6990e1f73a6c3148490401f1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"TRACIE + TODAY","Loss":"CE + MR"}. This record does not assert independent reproduction. ### T5 (in-domain) TRACIE Accuracy: 66.2. Result ID: 6990e1f73a6c3148490401e9. [Reporting paper]() Recorded evaluation configuration: {"Loss":"CE/MR"}. This record does not assert independent reproduction. ### T5 (T) TRACIE Accuracy: 66.2. Result ID: 6990e1f73a6c3148490401f0. [Reporting paper]() Recorded evaluation configuration: {"Train Data":"TRACIE","Loss":"CE"}. This record does not assert independent reproduction. ### T5 (M+T) TRACIE Accuracy: 66.2. Result ID: 6990e1f73a6c3148490401f3. [Reporting paper]() Recorded evaluation configuration: {"Train Data":"MATRES + TRACIE","Loss":"CE"}. This record does not assert independent reproduction. ### GPT-3.5 text-davinci-002 TRACIE Accuracy: 56.1. Result ID: 6990e1f73a6c3148490401e7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"FewShot","Loss":"FewShot"}. This record does not assert independent reproduction. ### T5 (O+G) TRACIE Accuracy: 55.4. Result ID: 6990e1f73a6c3148490401ec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"TODAY + GPT-3.5-generated incidental supervision","Loss":"MR"}. This record does not assert independent reproduction. ### T5 (M) TRACIE Accuracy: 52.7. Result ID: 6990e1f73a6c3148490401ed. [Reporting paper]() Recorded evaluation configuration: {"Train Data":"MATRES","Loss":"CE"}. This record does not assert independent reproduction. ### GPT-3.5 text-davinci-003 TRACIE Accuracy: 52.3. Result ID: 6990e1f73a6c3148490401e8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"FewShot","Loss":"FewShot"}. This record does not assert independent reproduction. ### T5 (M+O) TRACIE Accuracy: 51.5. Result ID: 6990e1f73a6c3148490401ee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"MATRES + TODAY","Loss":"CE + MR"}. This record does not assert independent reproduction. ### T5 (O) TRACIE Accuracy: 50.6. Result ID: 6990e1f73a6c3148490401eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"TODAY (ours)","Loss":"MR"}. This record does not assert independent reproduction. ### T5 (M+O+G) TRACIE Accuracy: 49.9. Result ID: 6990e1f73a6c3148490401ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Train Data":"MATRES + TODAY + GPT-3.5","Loss":"CE + MR"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.