Spaces:
Sleeping
Sleeping
| EN_TASKS = [ | |
| { | |
| "id": "ambiguity_1", | |
| "base_prompt": "The sentence is ambiguous: 'He saw the man with the binoculars.' Who has the binoculars? Provide an interpretation and explain briefly.", | |
| "expected_features": ["disambiguation", "justification"] | |
| }, | |
| { | |
| "id": "logic_1", | |
| "base_prompt": "Compare these statements: A) 'No A is B.' B) 'Not all A are B.' Are they logically equivalent? Explain briefly.", | |
| "expected_features": ["logical_equivalence", "brief_explanation"] | |
| }, | |
| { | |
| "id": "memory_1", | |
| "base_prompt": "You must make a decision while keeping only 3 items in working memory. Decide and explain which item you discard and why.", | |
| "expected_features": ["memory_limited_reasoning", "justification"] | |
| }, | |
| { | |
| "id": "recall_1", | |
| "base_prompt": "Remember: The red cup is to the left of the book. You will be asked later if anything has changed.", | |
| "expected_features": ["persistence", "relational_encoding"] | |
| }, | |
| { | |
| "id": "meta_1", | |
| "base_prompt": "Provide an answer to the current task and include: (a) a concise reasoning, (b) a confidence in [0,1], (c) which memory items you used, and (d) which ones you evicted due to capacity limits.", | |
| "expected_features": ["self_estimation", "meta_reasoning"] | |
| } | |
| ] | |