update to tech report version (#10)

* feat(run_eval): add checkpoint resume functionality and update example documentation;
- update new bootcamp benchmark dataset

* refactor(data_pipeline): optimize data generation pipeline; add multiple preset configurations for data generation

* docs: update bootcamp list and add new scripts

- Update Fulllist_InternBootcamp.md with new bootcamps and categories
- Add new scripts to .gitignore:
  - examples/pipelines/filter_autogen_configs.py
  - examples/pipelines/quickgen_data_configs_from_eval_meta.py
- Update dependencies in setup.py:
  - Add scipy and scikit-learn

* refactor(internbootcamp): update bootcamp modules and improve error handling

- Update import statements in __init__.py files
- Add timestamp to target directory name in verl_data_preprocess.py
- Improve error handling and scoring logic in bootcamp_judger.py
- Remove unnecessary comments and update puzzle descriptions in multiple files
This commit is contained in:
Yongkang Chen 2025-08-28 12:39:47 +08:00 committed by GitHub
parent 125a7818e0
commit a8249acc18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2952 changed files with 105460 additions and 17649 deletions

View file

@ -0,0 +1,100 @@
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = p ¬q and C2 = ¬p ¬q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["p", "¬q"], "C2": ["¬p", "¬q"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s ¬r p and C2 = ¬s q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "¬r", "p"], "C2": ["¬s", "q"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s q and C2 = ¬s q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "q"], "C2": ["¬s", "q"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s q and C2 = ¬s ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "q"], "C2": ["¬s", "¬p"], "expected": "q ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q and C2 = ¬q ¬s ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q"], "C2": ["¬q", "¬s", "¬r"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬s ¬p and C2 = ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬s", "¬p"], "C2": ["¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q ¬p and C2 = ¬q s ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q", "¬p"], "C2": ["¬q", "s", "¬r"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s p and C2 = ¬s r ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "p"], "C2": ["¬s", "r", "¬r"], "expected": "r ¬r p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r ¬p and C2 = ¬r p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "¬p"], "C2": ["¬r", "p"], "expected": "¬p p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = p ¬r and C2 = ¬p ¬s ¬q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["p", "¬r"], "C2": ["¬p", "¬s", "¬q"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p ¬s and C2 = ¬p ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "¬s"], "C2": ["¬p", "¬r"], "expected": "¬s ¬r"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q ¬s and C2 = ¬q ¬s s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "¬s"], "C2": ["¬q", "¬s", "s"], "expected": "¬s s"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p and C2 = ¬p s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p"], "C2": ["¬p", "s"], "expected": "s"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p ¬q and C2 = ¬p s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "¬q"], "C2": ["¬p", "s"], "expected": "s ¬q"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r s and C2 = ¬r ¬s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "s"], "C2": ["¬r", "¬s"], "expected": "¬s s"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬s s and C2 = ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬s", "s"], "C2": ["¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p s ¬q and C2 = ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "s", "¬q"], "C2": ["¬p"], "expected": "s ¬q"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p ¬q and C2 = ¬p ¬q ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "¬q"], "C2": ["¬p", "¬q", "¬r"], "expected": "¬q ¬r"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p ¬r and C2 = ¬p ¬q, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "¬r"], "C2": ["¬p", "¬q"], "expected": "¬q ¬r"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p and C2 = ¬p s ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p"], "C2": ["¬p", "s", "¬r"], "expected": "s ¬r"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬s s ¬r and C2 = ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬s", "s", "¬r"], "C2": ["¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s ¬p and C2 = ¬s ¬p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "¬p"], "C2": ["¬s", "¬p"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r and C2 = ¬s ¬q q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r"], "C2": ["¬s", "¬q", "q"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r"], "C2": ["¬r"], "expected": "0"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = p ¬r and C2 = ¬p r ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["p", "¬r"], "C2": ["¬p", "r", "¬r"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬p and C2 = s ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬p"], "C2": ["s", "¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s and C2 = ¬s q ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s"], "C2": ["¬s", "q", "¬r"], "expected": "¬r q"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r s ¬p and C2 = ¬r ¬s s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r", "s", "¬p"], "C2": ["¬r", "¬s", "s"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r ¬s and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "¬s"], "C2": ["¬r"], "expected": "¬s"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q s ¬r and C2 = ¬q ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "s", "¬r"], "C2": ["¬q", "¬p"], "expected": "s ¬r ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s ¬r and C2 = ¬s ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "¬r"], "C2": ["¬s", "¬r"], "expected": "¬r"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r"], "C2": ["¬r"], "expected": "0"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r and C2 = ¬r q ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r"], "C2": ["¬r", "q", "¬p"], "expected": "q ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q ¬p and C2 = ¬q ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q", "¬p"], "C2": ["¬q", "¬r"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q ¬p and C2 = s ¬p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q", "¬p"], "C2": ["s", "¬p"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r s q and C2 = r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r", "s", "q"], "C2": ["r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬s and C2 = ¬s q ¬p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬s"], "C2": ["¬s", "q", "¬p"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q ¬s and C2 = ¬q, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "¬s"], "C2": ["¬q"], "expected": "¬s"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r s ¬q and C2 = ¬r s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "s", "¬q"], "C2": ["¬r", "s"], "expected": "s ¬q"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬q q and C2 = s ¬p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬q", "q"], "C2": ["s", "¬p"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s and C2 = ¬s r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s"], "C2": ["¬s", "r"], "expected": "r"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬p ¬r p and C2 = ¬q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬p", "¬r", "p"], "C2": ["¬q"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p q and C2 = ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "q"], "C2": ["¬p"], "expected": "q"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p and C2 = ¬p s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p"], "C2": ["¬p", "s"], "expected": "s"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s ¬r p and C2 = ¬s ¬p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "¬r", "p"], "C2": ["¬s", "¬p"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬q p and C2 = p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬q", "p"], "C2": ["p"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q ¬s and C2 = ¬q, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "¬s"], "C2": ["¬q"], "expected": "¬s"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q s p and C2 = ¬q s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "s", "p"], "C2": ["¬q", "s"], "expected": "s p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q ¬s and C2 = ¬q ¬r ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "¬s"], "C2": ["¬q", "¬r", "¬p"], "expected": "¬s ¬r ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r s q and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "s", "q"], "C2": ["¬r"], "expected": "s q"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p s and C2 = ¬p r ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "s"], "C2": ["¬p", "r", "¬r"], "expected": "r s ¬r"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬s r p and C2 = r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬s", "r", "p"], "C2": ["r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s ¬q and C2 = ¬s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "¬q"], "C2": ["¬s"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p and C2 = ¬p r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p"], "C2": ["¬p", "r"], "expected": "r"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r p and C2 = q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r", "p"], "C2": ["q"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r"], "C2": ["¬r"], "expected": "0"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q and C2 = ¬q s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q"], "C2": ["¬q", "s"], "expected": "s"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s and C2 = ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s"], "C2": ["¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p r s and C2 = ¬p r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "r", "s"], "C2": ["¬p", "r"], "expected": "r s"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = p and C2 = ¬p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["p"], "C2": ["¬p"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q p and C2 = ¬q r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "p"], "C2": ["¬q", "r"], "expected": "r p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = p ¬s r and C2 = ¬p r ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["p", "¬s", "r"], "C2": ["¬p", "r", "¬r"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s r p and C2 = ¬s ¬q ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "r", "p"], "C2": ["¬s", "¬q", "¬p"], "expected": "r ¬q p ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s p ¬p and C2 = ¬s ¬q q, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "p", "¬p"], "C2": ["¬s", "¬q", "q"], "expected": "q ¬q p ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r ¬q q and C2 = ¬r ¬s s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "¬q", "q"], "C2": ["¬r", "¬s", "s"], "expected": "¬s s ¬q q"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r q and C2 = ¬r s ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "q"], "C2": ["¬r", "s", "¬p"], "expected": "s q ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p s q and C2 = ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "s", "q"], "C2": ["¬p"], "expected": "s q"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r"], "C2": ["¬r"], "expected": "0"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q ¬s ¬p and C2 = ¬q ¬s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "¬s", "¬p"], "C2": ["¬q", "¬s"], "expected": "¬s ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r and C2 = ¬s r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r"], "C2": ["¬s", "r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r ¬s s and C2 = ¬r p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "¬s", "s"], "C2": ["¬r", "p"], "expected": "¬s s p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r ¬q ¬p and C2 = ¬r s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r", "¬q", "¬p"], "C2": ["¬r", "s"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r"], "C2": ["¬r"], "expected": "0"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s ¬q and C2 = r ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "¬q"], "C2": ["r", "¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s ¬p and C2 = ¬s ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "¬p"], "C2": ["¬s", "¬p"], "expected": "¬p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r and C2 = s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r"], "C2": ["s"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r p and C2 = ¬r ¬s ¬q, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "p"], "C2": ["¬r", "¬s", "¬q"], "expected": "¬s ¬q p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r ¬s and C2 = ¬r p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r", "¬s"], "C2": ["¬r", "p"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p ¬s q and C2 = ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "¬s", "q"], "C2": ["¬p"], "expected": "¬s q"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q and C2 = ¬s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q"], "C2": ["¬s"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q s p and C2 = ¬q ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q", "s", "p"], "C2": ["¬q", "¬r"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s ¬p and C2 = q be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "¬p"], "C2": ["q"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q ¬r and C2 = ¬q r s, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q", "¬r"], "C2": ["¬q", "r", "s"], "expected": "r s ¬r"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q and C2 = s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q"], "C2": ["s"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬r and C2 = s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬r"], "C2": ["s"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s and C2 = p ¬p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s"], "C2": ["p", "¬p"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r ¬q p and C2 = ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "¬q", "p"], "C2": ["¬r"], "expected": "¬q p"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p ¬s and C2 = ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "¬s"], "C2": ["¬p"], "expected": "¬s"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = r p ¬p and C2 = ¬r ¬s p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["r", "p", "¬p"], "C2": ["¬r", "¬s", "p"], "expected": "¬s p ¬p"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r and C2 = ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r"], "C2": ["¬r"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p r and C2 = ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "r"], "C2": ["¬p"], "expected": "r"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = q and C2 = ¬q, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["q"], "C2": ["¬q"], "expected": "0"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = r and C2 = r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["r"], "C2": ["r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = p and C2 = ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["p"], "C2": ["¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = q ¬r ¬p and C2 = s ¬r be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["q", "¬r", "¬p"], "C2": ["s", "¬r"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = s q and C2 = ¬s be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["s", "q"], "C2": ["¬s"], "expected": true}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s r and C2 = ¬s ¬r, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "r"], "C2": ["¬s", "¬r"], "expected": "r ¬r"}}
{"data_source": "KorLogicResolution", "prompt": "Can clauses C1 = ¬s ¬q p and C2 = ¬q p be resolved?\nA. Yes\nB. No\nAnswer format: [[option]].", "ground_truth": {"problem_type": "can_resolve", "C1": ["¬s", "¬q", "p"], "C2": ["¬q", "p"], "expected": false}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = p q and C2 = ¬p ¬q, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["p", "q"], "C2": ["¬p", "¬q"], "expected": "¬q q"}}
{"data_source": "KorLogicResolution", "prompt": "If C1 = s r ¬q and C2 = ¬s ¬p, what is dispel(C1, C2)?\nProvide answer in format [[result]].\nFor multiple results use [[result1;result2]].\nFor empty clause write [[0]].", "ground_truth": {"problem_type": "compute_dispel", "C1": ["s", "r", "¬q"], "C2": ["¬s", "¬p"], "expected": "r ¬q ¬p"}}