# Complex Query Answering on Warden Alert Inductive (33% qualifier coverage) Source: [Complex Query Answering on Warden Alert Inductive (33% qualifier coverage)]() Collection index: [llms.txt]() Data updated: 2026-04-06T08:54:21.365Z Evaluation of Complex Query Answering performance on the Warden Alert Inductive dataset, restricted to the 33% qualifier coverage subset, using ranking metrics (MR, MRR, H@K). 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 | Complex query answering | | Dataset (including any stated split) | Warden Alert Inductive, 33% qualifier coverage | | Metric | MR (Mean Rank) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 16 of 16 | | 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 - [MR (Mean Rank)](): Lower is better; unit: SCALAR. - [MRR (Mean Reciprocal Rank)](): Higher is better; unit: PERCENT. - [H@1 (Hit Rate @ 1)](): Higher is better; unit: PERCENT. - [H@3 (Hit Rate @ 3)](): Higher is better; unit: PERCENT. - [H@10 (Hit Rate @ 10)](): Higher is better; unit: PERCENT. ## Recorded results | Method | MR (Mean Rank) | Result date | Report paper | | --- | --- | --- | --- | | HR-NBFNet-CQ | 1.78 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 1.95 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 3.125 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 3.23 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 3.385 | Not recorded | 69d33df37d0172140ec7363a | | HR-NBFNet-CQ | 3.485 | Not recorded | 69d33df37d0172140ec7363a | | HR-NBFNet-CQ | 3.575 | Not recorded | 69d33df37d0172140ec7363a | | HR-NBFNet-CQ | 3.84 | Not recorded | 69d33df37d0172140ec7363a | | HR-NBFNet-CQ | 17.85 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 26.545 | Not recorded | 69d33df37d0172140ec7363a | | HR-NBFNet-CQ | 32.08 | Not recorded | 69d33df37d0172140ec7363a | | HR-NBFNet-CQ | 38.92 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 43.81 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 50.26 | Not recorded | 69d33df37d0172140ec7363a | | StarQE | 100.66 | Not recorded | 69d33df37d0172140ec7363a | | HR-NBFNet-CQ | 111.33 | Not recorded | 69d33df37d0172140ec7363a | ### HR-NBFNet-CQ MR (Mean Rank): 1.78. Result ID: 69d374bb47f34ce924bb6c58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2p"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 1.95. Result ID: 69d374bb47f34ce924bb6c54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2p"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 3.125. Result ID: 69d374bb47f34ce924bb6c53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"1p"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 3.23. Result ID: 69d374bb47f34ce924bb6c56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2u"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 3.385. Result ID: 69d374bb47f34ce924bb6c55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2i"}. This record does not assert independent reproduction. ### HR-NBFNet-CQ MR (Mean Rank): 3.485. Result ID: 69d374bb47f34ce924bb6c57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"1p"}. This record does not assert independent reproduction. ### HR-NBFNet-CQ MR (Mean Rank): 3.575. Result ID: 69d374bb47f34ce924bb6c5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2u"}. This record does not assert independent reproduction. ### HR-NBFNet-CQ MR (Mean Rank): 3.84. Result ID: 69d374bb47f34ce924bb6c59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2i"}. This record does not assert independent reproduction. ### HR-NBFNet-CQ MR (Mean Rank): 17.85. Result ID: 69d374bb47f34ce924bb6c29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2i"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 26.545. Result ID: 69d374bb47f34ce924bb6c25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2i"}. This record does not assert independent reproduction. ### HR-NBFNet-CQ MR (Mean Rank): 32.08. Result ID: 69d374bb47f34ce924bb6c27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"1p"}. This record does not assert independent reproduction. ### HR-NBFNet-CQ MR (Mean Rank): 38.92. Result ID: 69d374bb47f34ce924bb6c2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2u"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 43.81. Result ID: 69d374bb47f34ce924bb6c23. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"1p"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 50.26. Result ID: 69d374bb47f34ce924bb6c26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2u"}. This record does not assert independent reproduction. ### StarQE MR (Mean Rank): 100.66. Result ID: 69d374bb47f34ce924bb6c24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2p"}. This record does not assert independent reproduction. ### HR-NBFNet-CQ MR (Mean Rank): 111.33. Result ID: 69d374bb47f34ce924bb6c28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query":"2p"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.