| { |
| "slug": "05-text-failure", |
| "title": "A limitation · Repeated text", |
| "title_zh": "一个失败案例 · 文字重复", |
| "validation_index_zero_based": 1507, |
| "sample_id": "8e24c5a5a1ef5a5113755b33ed12164fc37ce8fbbd35d1c7dba81bf950d53d00:2458:13", |
| "instruction": "In Impress,add two new slides.Enter“Ancient History”and“Modern Art”in the title areas of slides 1 and 2 respectively.Enter the table of contents“・Egyptian・Greek・Roman”in the content area of slide 3.After completion,change the font to“Likhan”uniformly.", |
| "history_records": 13, |
| "screenshot": "examples/validation/05-text-failure.png", |
| "screenshot_sha256": "4990e9c99d8b227a80b40179ccc8c7fda6ab7e5510a76fb30c975ebaa250a079", |
| "prediction": { |
| "action": "type", |
| "text": "・ Egyptianian GreekGreek Roman Roman" |
| }, |
| "reference": { |
| "action": "type", |
| "text": "・Egyptian・Greek・Roman" |
| }, |
| "action_correct": true, |
| "canonical_exact_match": false, |
| "coordinate_absolute_error_0_1000": null, |
| "task_success": null, |
| "scope": "saved offline next-action prediction; not a closed-loop rollout", |
| "source_dataset": "xlangai/AgentNet", |
| "source_dataset_revision": "d76ee50a63fad81cfdbe576416757d7c2091ed50", |
| "prediction_file_sha256": "7dad166f6d93202a410b91da3cae7db936c2d9ab6835282ad7f5a8c8b0bca9c5", |
| "validation_source_sha256": "9e7de6ecca3a66081e7aeb6dcf79ab1470ad3a14eb13439e81c42ce850c57d6d", |
| "checkpoint_sha256": "bd82d3c508a7b591b7c1578614231b142689982c842c6864c80baaa213e5dde5" |
| } |
|
|
