examples/v10_examples.json

[
  {"id":"graph_solved","category":"transitivity","prompt":"Handoff log: a hands off to b; b hands off to c. Ignore the separate handoff x hands off to b. The handoff chain beginning at a ends at","expected_display_answer":"c","expected_solved":true,"expected_boundary_reason":null},
  {"id":"graph_refused","category":"transitivity","prompt":"Graph ledger: main(a,b); main(a,c). Resolve main* from a; terminal node:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"graph:ambiguous_branch"},
  {"id":"arith_solved","category":"arithmetic","prompt":"Ledger entry: begin 20, pay out 5, add back 3, scale by 2. The ledger closes at","expected_display_answer":"36","expected_solved":true,"expected_boundary_reason":null},
  {"id":"arith_refused","category":"arithmetic","prompt":"Machine value 9 is doubled, then 3 is added, then the result is divided by 0. Integer quotient:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"arithmetic:division_by_zero"},
  {"id":"code_solved","category":"code_reasoning","prompt":"Trace Python: total=0; for i in range(8): add i only when i is even. total is","expected_display_answer":"12","expected_solved":true,"expected_boundary_reason":null},
  {"id":"code_refused","category":"code_reasoning","prompt":"Trace Python: x=7; y=mystery(x); y is","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"code:unknown_function"},
  {"id":"boolean_and_solved","category":"boolean_logic","prompt":"Logic board: A=true; B=false; C=true. Evaluate A AND C:","expected_display_answer":"true","expected_solved":true,"expected_boundary_reason":null},
  {"id":"boolean_not_solved","category":"boolean_logic","prompt":"Logic board: A=true; B=false; C=true. Evaluate A AND NOT B:","expected_display_answer":"true","expected_solved":true,"expected_boundary_reason":null},
  {"id":"boolean_nested_solved","category":"boolean_logic","prompt":"Logic board: A=true; B=false; C=false. Evaluate (A AND NOT B) OR C:","expected_display_answer":"true","expected_solved":true,"expected_boundary_reason":null},
  {"id":"boolean_false_solved","category":"boolean_logic","prompt":"Truth row: A is false, B is true, C is false. Value of (A or B) and C:","expected_display_answer":"false","expected_solved":true,"expected_boundary_reason":null},
  {"id":"boolean_missing_refused","category":"boolean_logic","prompt":"Logic board: A=true; B=false. Evaluate A AND C:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"boolean:missing_variable"},
  {"id":"boolean_contradiction_refused","category":"boolean_logic","prompt":"Logic board: A=true; A=false; B=true. Evaluate A AND B:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"boolean:contradiction"},
  {"id":"boolean_xor_refused","category":"boolean_logic","prompt":"Logic board: A=true; B=false. Evaluate A XOR B:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"boolean:unsupported_or_unknown"},
  {"id":"set_union_solved","category":"set_reasoning","prompt":"Set ledger: A={a,b}; B={b,c}. Compute A union B:","expected_display_answer":"{a,b,c}","expected_solved":true,"expected_boundary_reason":null},
  {"id":"set_intersection_solved","category":"set_reasoning","prompt":"Set ledger: A={a,b,c}; B={b,c,d}. Compute A intersection B:","expected_display_answer":"{b,c}","expected_solved":true,"expected_boundary_reason":null},
  {"id":"set_minus_solved","category":"set_reasoning","prompt":"Set ledger: A={a,b,c}; B={b,c,d}. Compute A minus B:","expected_display_answer":"{a}","expected_solved":true,"expected_boundary_reason":null},
  {"id":"set_difference_solved","category":"set_reasoning","prompt":"Collection row: A={g,h,i}; B={h,k}. Return A difference B:","expected_display_answer":"{g,i}","expected_solved":true,"expected_boundary_reason":null},
  {"id":"set_empty_solved","category":"set_reasoning","prompt":"Set ledger: A={a}; B={a,b}. Compute A minus B:","expected_display_answer":"{}","expected_solved":true,"expected_boundary_reason":null},
  {"id":"set_missing_refused","category":"set_reasoning","prompt":"Set ledger: A={a,b}; B={b,c}. Compute A union C:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"set:missing_set"},
  {"id":"set_power_refused","category":"set_reasoning","prompt":"Set ledger: A={a,b}; B={b,c}. Compute power set A:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"set:unsupported_operation"},
  {"id":"string_reverse_solved","category":"string_reasoning","prompt":"String ops: start='alpha'; reverse; append 'x'. Result:","expected_display_answer":"ahplax","expected_solved":true,"expected_boundary_reason":null},
  {"id":"string_upper_solved","category":"string_reasoning","prompt":"String ops: start='alpha'; uppercase; append '!'. Result:","expected_display_answer":"ALPHA!","expected_solved":true,"expected_boundary_reason":null},
  {"id":"string_replace_solved","category":"string_reasoning","prompt":"String ops: start='alpha'; replace 'a'->'o'; append 'z'. Result:","expected_display_answer":"olphoz","expected_solved":true,"expected_boundary_reason":null},
  {"id":"string_prepend_solved","category":"string_reasoning","prompt":"Text transform: start='mango'; prepend 'pre_'; replace 'a'->'e'. Final text:","expected_display_answer":"pre_mengo","expected_solved":true,"expected_boundary_reason":null},
  {"id":"string_lower_reverse_solved","category":"string_reasoning","prompt":"Text transform: start='River'; lowercase; reverse. Final text:","expected_display_answer":"revir","expected_solved":true,"expected_boundary_reason":null},
  {"id":"string_shuffle_refused","category":"string_reasoning","prompt":"String ops: start='alpha'; shuffle; append 'x'. Result:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"string:unsupported_or_unknown"},
  {"id":"string_unknown_refused","category":"string_reasoning","prompt":"String ops: start='alpha'; unknown transform; append 'x'. Result:","expected_display_answer":"<ABSTAIN>","expected_solved":false,"expected_boundary_reason":"string:unsupported_or_unknown"},
  {"id":"boolean_paraphrase_solved","category":"boolean_logic","prompt":"Truth row: A is true, B is false, C is true. Value of A or not B:","expected_display_answer":"true","expected_solved":true,"expected_boundary_reason":null},
  {"id":"set_paraphrase_solved","category":"set_reasoning","prompt":"Collection row: A={g,h}; B={h,i}. Return A union B:","expected_display_answer":"{g,h,i}","expected_solved":true,"expected_boundary_reason":null},
  {"id":"string_paraphrase_solved","category":"string_reasoning","prompt":"Text transform: start='tango'; append '_ok'; uppercase. Final text:","expected_display_answer":"TANGO_OK","expected_solved":true,"expected_boundary_reason":null}
]