core/evals/gsm8k_parser_dev/cases.jsonl

50 lines
32 KiB
JSON

{"id":"gpd-001","problem":"Sam has 5 apples. He buys 3 more. How many apples does Sam have?","expected_answer":8,"expected_unit":"apples","ground_truth_graph":{"entities":["Sam"],"initial_state":[{"entity":"Sam","quantity":{"unit":"apples","value":5}}],"operations":[{"actor":"Sam","kind":"add","operand":{"unit":"apples","value":3}}],"unknown":{"entity":"Sam","unit":"apples"}},"patterns":["initial_has","operation_buy_more","question_how_many_entity"],"notes":"Single-entity, single-add. The simplest GSM8K-style pattern. 'He' resolves anaphorically to 'Sam'."}
{"id":"gpd-002","problem":"Tom has 12 candies. He eats 4. How many candies does Tom have left?","expected_answer":8,"expected_unit":"candies","ground_truth_graph":{"entities":["Tom"],"initial_state":[{"entity":"Tom","quantity":{"unit":"candies","value":12}}],"operations":[{"actor":"Tom","kind":"subtract","operand":{"unit":"candies","value":4}}],"unknown":{"entity":"Tom","unit":"candies"}},"patterns":["initial_has","operation_eat_loses","question_how_many_left"],"notes":"Single-entity, single-subtract. 'eats' is a loss verb. Question suffix 'left' is a comprehension cue but the unknown shape is identical to gpd-001."}
{"id":"gpd-003","problem":"Lisa has 10 books. She buys 5 more, then donates 3. How many books does Lisa have?","expected_answer":12,"expected_unit":"books","ground_truth_graph":{"entities":["Lisa"],"initial_state":[{"entity":"Lisa","quantity":{"unit":"books","value":10}}],"operations":[{"actor":"Lisa","kind":"add","operand":{"unit":"books","value":5}},{"actor":"Lisa","kind":"subtract","operand":{"unit":"books","value":3}}],"unknown":{"entity":"Lisa","unit":"books"}},"patterns":["initial_has","operation_buy_more","operation_donate_loses","question_how_many_entity"],"notes":"Single-entity, multi-step. 'then' is a sequence marker; operation order must follow text order."}
{"id":"gpd-004","problem":"Anna has 8 marbles. She gives 3 to Ben. How many marbles does Anna have now?","expected_answer":5,"expected_unit":"marbles","ground_truth_graph":{"entities":["Anna","Ben"],"initial_state":[{"entity":"Anna","quantity":{"unit":"marbles","value":8}}],"operations":[{"actor":"Anna","kind":"transfer","operand":{"unit":"marbles","value":3},"target":"Ben"}],"unknown":{"entity":"Anna","unit":"marbles"}},"patterns":["initial_has","operation_give_transfer","question_how_many_entity"],"notes":"Two-entity transfer. Ben appears only as a transfer target \u2014 no initial possession is asserted for Ben. The 'transfer' kind decomposes downstream into subtract(actor) + add(target); the parser emits the closer-to-NL form."}
{"id":"gpd-005","problem":"Tom has 4 stickers. Sara has 7 stickers. How many stickers do they have in total?","expected_answer":11,"expected_unit":"stickers","ground_truth_graph":{"entities":["Tom","Sara"],"initial_state":[{"entity":"Tom","quantity":{"unit":"stickers","value":4}},{"entity":"Sara","quantity":{"unit":"stickers","value":7}}],"operations":[],"unknown":{"entity":null,"unit":"stickers"}},"patterns":["initial_has","initial_has","question_how_many_total"],"notes":"Multi-entity initial possessions, no operations, sum question. 'they' refers to all introduced entities; Unknown.entity=null signals total across entities."}
{"id":"gpd-006","problem":"Nora has 9 pencils. She buys 4 more. How many pencils does Nora have?","expected_answer":13,"expected_unit":"pencils","ground_truth_graph":{"entities":["Nora"],"initial_state":[{"entity":"Nora","quantity":{"unit":"pencils","value":9}}],"operations":[{"actor":"Nora","kind":"add","operand":{"unit":"pencils","value":4}}],"unknown":{"entity":"Nora","unit":"pencils"}},"patterns":["initial_has","operation_buy_more","question_how_many_entity"],"notes":"Single-entity add case using explicit buy-more phrasing with direct anaphora resolution."}
{"id":"gpd-007","problem":"Evan has 14 shells. He gets 5 more shells. How many shells does Evan have now?","expected_answer":19,"expected_unit":"shells","ground_truth_graph":{"entities":["Evan"],"initial_state":[{"entity":"Evan","quantity":{"unit":"shells","value":14}}],"operations":[{"actor":"Evan","kind":"add","operand":{"unit":"shells","value":5}}],"unknown":{"entity":"Evan","unit":"shells"}},"patterns":["initial_has","operation_get_more","question_how_many_now"],"notes":"Single-entity add case that exercises the get-more lexical variant."}
{"id":"gpd-008","problem":"Priya has 6 buttons. She finds 7 buttons on the floor. How many buttons does Priya have?","expected_answer":13,"expected_unit":"buttons","ground_truth_graph":{"entities":["Priya"],"initial_state":[{"entity":"Priya","quantity":{"unit":"buttons","value":6}}],"operations":[{"actor":"Priya","kind":"add","operand":{"unit":"buttons","value":7}}],"unknown":{"entity":"Priya","unit":"buttons"}},"patterns":["initial_has","operation_find_adds","question_how_many_entity"],"notes":"Find-adds case where the discovered amount is explicitly unit-qualified."}
{"id":"gpd-009","problem":"Caleb has 15 crackers. He eats 6. How many crackers does Caleb have left?","expected_answer":9,"expected_unit":"crackers","ground_truth_graph":{"entities":["Caleb"],"initial_state":[{"entity":"Caleb","quantity":{"unit":"crackers","value":15}}],"operations":[{"actor":"Caleb","kind":"subtract","operand":{"unit":"crackers","value":6}}],"unknown":{"entity":"Caleb","unit":"crackers"}},"patterns":["initial_has","operation_eat_loses","question_how_many_left"],"notes":"Direct subtract case using the eat-loss verb and left-style question."}
{"id":"gpd-010","problem":"Maya has 18 marbles. She loses 5. How many marbles does Maya have now?","expected_answer":13,"expected_unit":"marbles","ground_truth_graph":{"entities":["Maya"],"initial_state":[{"entity":"Maya","quantity":{"unit":"marbles","value":18}}],"operations":[{"actor":"Maya","kind":"subtract","operand":{"unit":"marbles","value":5}}],"unknown":{"entity":"Maya","unit":"marbles"}},"patterns":["initial_has","operation_lose_loses","question_how_many_now"],"notes":"Single-step lose-loses subtract with straightforward pronoun carryover."}
{"id":"gpd-011","problem":"Liam has 20 tickets. He sells 8. How many tickets does Liam have left?","expected_answer":12,"expected_unit":"tickets","ground_truth_graph":{"entities":["Liam"],"initial_state":[{"entity":"Liam","quantity":{"unit":"tickets","value":20}}],"operations":[{"actor":"Liam","kind":"subtract","operand":{"unit":"tickets","value":8}}],"unknown":{"entity":"Liam","unit":"tickets"}},"patterns":["initial_has","operation_sell_loses","question_how_many_left"],"notes":"Sell-loses pattern mapped to subtract while preserving unit consistency."}
{"id":"gpd-012","problem":"Ava has 16 books. She donates 7. How many books does Ava have now?","expected_answer":9,"expected_unit":"books","ground_truth_graph":{"entities":["Ava"],"initial_state":[{"entity":"Ava","quantity":{"unit":"books","value":16}}],"operations":[{"actor":"Ava","kind":"subtract","operand":{"unit":"books","value":7}}],"unknown":{"entity":"Ava","unit":"books"}},"patterns":["initial_has","operation_donate_loses","question_how_many_now"],"notes":"Donation phrasing is modeled as subtract on the actor with no transfer target."}
{"id":"gpd-013","problem":"Owen has 22 sheets. He uses 9. How many sheets does Owen have left?","expected_answer":13,"expected_unit":"sheets","ground_truth_graph":{"entities":["Owen"],"initial_state":[{"entity":"Owen","quantity":{"unit":"sheets","value":22}}],"operations":[{"actor":"Owen","kind":"subtract","operand":{"unit":"sheets","value":9}}],"unknown":{"entity":"Owen","unit":"sheets"}},"patterns":["initial_has","operation_use_loses","question_how_many_left"],"notes":"Use-loses subtraction case with the same entity referenced by pronoun in sequence."}
{"id":"gpd-014","problem":"Rina has 7 ribbons. She doubles her ribbons. How many ribbons does Rina have now?","expected_answer":14,"expected_unit":"ribbons","ground_truth_graph":{"entities":["Rina"],"initial_state":[{"entity":"Rina","quantity":{"unit":"ribbons","value":7}}],"operations":[{"actor":"Rina","kind":"multiply","operand":{"unit":"ribbons","value":2}}],"unknown":{"entity":"Rina","unit":"ribbons"}},"patterns":["initial_has","operation_double","question_how_many_now"],"notes":"Double pattern encoded as multiply by scalar 2 on the actor quantity."}
{"id":"gpd-015","problem":"Noah has 5 kites. He triples his kites. How many kites does Noah have now?","expected_answer":15,"expected_unit":"kites","ground_truth_graph":{"entities":["Noah"],"initial_state":[{"entity":"Noah","quantity":{"unit":"kites","value":5}}],"operations":[{"actor":"Noah","kind":"multiply","operand":{"unit":"kites","value":3}}],"unknown":{"entity":"Noah","unit":"kites"}},"patterns":["initial_has","operation_triple","question_how_many_now"],"notes":"Triple pattern represented with multiply and scalar operand value 3."}
{"id":"gpd-016","problem":"Ruth has 24 oranges. She splits them evenly into 6 groups and keeps one group. How many oranges does Ruth have now?","expected_answer":4,"expected_unit":"oranges","ground_truth_graph":{"entities":["Ruth"],"initial_state":[{"entity":"Ruth","quantity":{"unit":"oranges","value":24}}],"operations":[{"actor":"Ruth","kind":"divide","operand":{"unit":"oranges","value":6}}],"unknown":{"entity":"Ruth","unit":"oranges"}},"patterns":["initial_has","operation_split_divide","question_how_many_now"],"notes":"Split-divide case uses explicit equal-group language and actor-retains-one-group semantics."}
{"id":"gpd-017","problem":"Iris has 11 apples. She buys 3 more. Then she eats 2. How many apples does Iris have?","expected_answer":12,"expected_unit":"apples","ground_truth_graph":{"entities":["Iris"],"initial_state":[{"entity":"Iris","quantity":{"unit":"apples","value":11}}],"operations":[{"actor":"Iris","kind":"add","operand":{"unit":"apples","value":3}},{"actor":"Iris","kind":"subtract","operand":{"unit":"apples","value":2}}],"unknown":{"entity":"Iris","unit":"apples"}},"patterns":["initial_has","operation_buy_more","operation_eat_loses","question_how_many_entity"],"notes":"Two-step same-entity chain where 'Then' fixes operation order in source text."}
{"id":"gpd-018","problem":"Kai has 13 stones. He gets 4 more stones. Then he loses 5. How many stones does Kai have now?","expected_answer":12,"expected_unit":"stones","ground_truth_graph":{"entities":["Kai"],"initial_state":[{"entity":"Kai","quantity":{"unit":"stones","value":13}}],"operations":[{"actor":"Kai","kind":"add","operand":{"unit":"stones","value":4}},{"actor":"Kai","kind":"subtract","operand":{"unit":"stones","value":5}}],"unknown":{"entity":"Kai","unit":"stones"}},"patterns":["initial_has","operation_get_more","operation_lose_loses","question_how_many_now"],"notes":"Get-then-lose composition tests additive followed by subtractive mutation on one entity."}
{"id":"gpd-019","problem":"Jade has 21 coins. She finds 2 coins. Then she sells 6. How many coins does Jade have left?","expected_answer":17,"expected_unit":"coins","ground_truth_graph":{"entities":["Jade"],"initial_state":[{"entity":"Jade","quantity":{"unit":"coins","value":21}}],"operations":[{"actor":"Jade","kind":"add","operand":{"unit":"coins","value":2}},{"actor":"Jade","kind":"subtract","operand":{"unit":"coins","value":6}}],"unknown":{"entity":"Jade","unit":"coins"}},"patterns":["initial_has","operation_find_adds","operation_sell_loses","question_how_many_left"],"notes":"Find-add followed by sell-loss provides mixed verb mapping while keeping one unit."}
{"id":"gpd-020","problem":"Milo has 30 crayons. He donates 4. Then he uses 5. How many crayons does Milo have now?","expected_answer":21,"expected_unit":"crayons","ground_truth_graph":{"entities":["Milo"],"initial_state":[{"entity":"Milo","quantity":{"unit":"crayons","value":30}}],"operations":[{"actor":"Milo","kind":"subtract","operand":{"unit":"crayons","value":4}},{"actor":"Milo","kind":"subtract","operand":{"unit":"crayons","value":5}}],"unknown":{"entity":"Milo","unit":"crayons"}},"patterns":["initial_has","operation_donate_loses","operation_use_loses","question_how_many_now"],"notes":"Back-to-back subtractive verbs verify ordered operation application without target entity."}
{"id":"gpd-021","problem":"Lena has 8 dolls. She doubles her dolls. Then she donates 3 dolls. How many dolls does Lena have now?","expected_answer":13,"expected_unit":"dolls","ground_truth_graph":{"entities":["Lena"],"initial_state":[{"entity":"Lena","quantity":{"unit":"dolls","value":8}}],"operations":[{"actor":"Lena","kind":"multiply","operand":{"unit":"dolls","value":2}},{"actor":"Lena","kind":"subtract","operand":{"unit":"dolls","value":3}}],"unknown":{"entity":"Lena","unit":"dolls"}},"patterns":["initial_has","operation_double","operation_donate_loses","question_how_many_now"],"notes":"Rewrite of gpd-021 to remove metaphorical mixed-unit phrasing while preserving a deterministic multiply-then-subtract structure."}
{"id":"gpd-022","problem":"Zane has 4 cards. He triples his cards. Then he donates 2. How many cards does Zane have left?","expected_answer":10,"expected_unit":"cards","ground_truth_graph":{"entities":["Zane"],"initial_state":[{"entity":"Zane","quantity":{"unit":"cards","value":4}}],"operations":[{"actor":"Zane","kind":"multiply","operand":{"unit":"cards","value":3}},{"actor":"Zane","kind":"subtract","operand":{"unit":"cards","value":2}}],"unknown":{"entity":"Zane","unit":"cards"}},"patterns":["initial_has","operation_triple","operation_donate_loses","question_how_many_left"],"notes":"Triple then donate verifies scalar multiplication followed by subtraction on same entity."}
{"id":"gpd-023","problem":"Pia has 36 beads. She splits them evenly into 4 groups and keeps one group. Then she buys 3 more beads. How many beads does Pia have now?","expected_answer":12,"expected_unit":"beads","ground_truth_graph":{"entities":["Pia"],"initial_state":[{"entity":"Pia","quantity":{"unit":"beads","value":36}}],"operations":[{"actor":"Pia","kind":"divide","operand":{"unit":"beads","value":4}},{"actor":"Pia","kind":"add","operand":{"unit":"beads","value":3}}],"unknown":{"entity":"Pia","unit":"beads"}},"patterns":["initial_has","operation_split_divide","operation_buy_more","question_how_many_now"],"notes":"Divide-first pipeline confirms split-divide semantics before later additive mutation."}
{"id":"gpd-024","problem":"Tara has 17 flowers. She loses 4. Then she gets 6 more flowers. How many flowers does Tara have now?","expected_answer":19,"expected_unit":"flowers","ground_truth_graph":{"entities":["Tara"],"initial_state":[{"entity":"Tara","quantity":{"unit":"flowers","value":17}}],"operations":[{"actor":"Tara","kind":"subtract","operand":{"unit":"flowers","value":4}},{"actor":"Tara","kind":"add","operand":{"unit":"flowers","value":6}}],"unknown":{"entity":"Tara","unit":"flowers"}},"patterns":["initial_has","operation_lose_loses","operation_get_more","question_how_many_now"],"notes":"Loss followed by get-more checks mixed subtract/add flow with consistent unit tracking."}
{"id":"gpd-025","problem":"Uma has 19 stickers. She uses 7. Then she finds 5 stickers. How many stickers does Uma have now?","expected_answer":17,"expected_unit":"stickers","ground_truth_graph":{"entities":["Uma"],"initial_state":[{"entity":"Uma","quantity":{"unit":"stickers","value":19}}],"operations":[{"actor":"Uma","kind":"subtract","operand":{"unit":"stickers","value":7}},{"actor":"Uma","kind":"add","operand":{"unit":"stickers","value":5}}],"unknown":{"entity":"Uma","unit":"stickers"}},"patterns":["initial_has","operation_use_loses","operation_find_adds","question_how_many_now"],"notes":"Use-loses and find-adds are combined to exercise opposite-direction updates on one actor."}
{"id":"gpd-026","problem":"Wren has 25 cups. She sells 10. Then she buys 4 more. How many cups does Wren have left?","expected_answer":19,"expected_unit":"cups","ground_truth_graph":{"entities":["Wren"],"initial_state":[{"entity":"Wren","quantity":{"unit":"cups","value":25}}],"operations":[{"actor":"Wren","kind":"subtract","operand":{"unit":"cups","value":10}},{"actor":"Wren","kind":"add","operand":{"unit":"cups","value":4}}],"unknown":{"entity":"Wren","unit":"cups"}},"patterns":["initial_has","operation_sell_loses","operation_buy_more","question_how_many_left"],"notes":"Sell then buy sequence checks source-order semantics across opposite operation kinds."}
{"id":"gpd-027","problem":"Yara has 6 scarves. She donates 1. Then she triples her scarves. How many scarves does Yara have now?","expected_answer":15,"expected_unit":"scarves","ground_truth_graph":{"entities":["Yara"],"initial_state":[{"entity":"Yara","quantity":{"unit":"scarves","value":6}}],"operations":[{"actor":"Yara","kind":"subtract","operand":{"unit":"scarves","value":1}},{"actor":"Yara","kind":"multiply","operand":{"unit":"scarves","value":3}}],"unknown":{"entity":"Yara","unit":"scarves"}},"patterns":["initial_has","operation_donate_loses","operation_triple","question_how_many_now"],"notes":"Subtract-before-multiply case guards against accidental commutation of operations."}
{"id":"gpd-028","problem":"Bryn has 10 blocks. She doubles her blocks. Then she splits them evenly into 5 groups and keeps one group. How many blocks does Bryn have now?","expected_answer":4,"expected_unit":"blocks","ground_truth_graph":{"entities":["Bryn"],"initial_state":[{"entity":"Bryn","quantity":{"unit":"blocks","value":10}}],"operations":[{"actor":"Bryn","kind":"multiply","operand":{"unit":"blocks","value":2}},{"actor":"Bryn","kind":"divide","operand":{"unit":"blocks","value":5}}],"unknown":{"entity":"Bryn","unit":"blocks"}},"patterns":["initial_has","operation_double","operation_split_divide","question_how_many_now"],"notes":"Multiply then divide chain stresses scalar operator ordering under one entity and unit."}
{"id":"gpd-029","problem":"Seth has 12 marbles. He buys 8 more. Then he uses 5. Then he finds 1 marble. How many marbles does Seth have now?","expected_answer":16,"expected_unit":"marbles","ground_truth_graph":{"entities":["Seth"],"initial_state":[{"entity":"Seth","quantity":{"unit":"marbles","value":12}}],"operations":[{"actor":"Seth","kind":"add","operand":{"unit":"marbles","value":8}},{"actor":"Seth","kind":"subtract","operand":{"unit":"marbles","value":5}},{"actor":"Seth","kind":"add","operand":{"unit":"marbles","value":1}}],"unknown":{"entity":"Seth","unit":"marbles"}},"patterns":["initial_has","operation_buy_more","operation_use_loses","operation_find_adds","question_how_many_now"],"notes":"Three-step chain tests repeated add/subtract with a singular-surface noun canonicalized to plural unit."}
{"id":"gpd-030","problem":"Gina has 28 candies. She eats 9. Then she gets 3 more candies. Then she sells 4. How many candies does Gina have now?","expected_answer":18,"expected_unit":"candies","ground_truth_graph":{"entities":["Gina"],"initial_state":[{"entity":"Gina","quantity":{"unit":"candies","value":28}}],"operations":[{"actor":"Gina","kind":"subtract","operand":{"unit":"candies","value":9}},{"actor":"Gina","kind":"add","operand":{"unit":"candies","value":3}},{"actor":"Gina","kind":"subtract","operand":{"unit":"candies","value":4}}],"unknown":{"entity":"Gina","unit":"candies"}},"patterns":["initial_has","operation_eat_loses","operation_get_more","operation_sell_loses","question_how_many_now"],"notes":"Final single-entity tranche case includes three ordered operations to increase parser path depth."}
{"id":"gpd-031","problem":"Anna has 12 marbles. Ben has 5 marbles. Anna gives 4 marbles to Ben. How many marbles does Anna have now?","expected_answer":8,"expected_unit":"marbles","ground_truth_graph":{"entities":["Anna","Ben"],"initial_state":[{"entity":"Anna","quantity":{"unit":"marbles","value":12}},{"entity":"Ben","quantity":{"unit":"marbles","value":5}}],"operations":[{"actor":"Anna","kind":"transfer","operand":{"unit":"marbles","value":4},"target":"Ben"}],"unknown":{"entity":"Anna","unit":"marbles"}},"patterns":["initial_has","operation_give_transfer","question_how_many_now"],"notes":"Two-entity give-transfer where unknown targets the sender after one transfer."}
{"id":"gpd-032","problem":"Tom has 9 letters. Sara has 3 letters. Tom sends 2 letters to Sara. How many letters does Sara have now?","expected_answer":5,"expected_unit":"letters","ground_truth_graph":{"entities":["Tom","Sara"],"initial_state":[{"entity":"Tom","quantity":{"unit":"letters","value":9}},{"entity":"Sara","quantity":{"unit":"letters","value":3}}],"operations":[{"actor":"Tom","kind":"transfer","operand":{"unit":"letters","value":2},"target":"Sara"}],"unknown":{"entity":"Sara","unit":"letters"}},"patterns":["initial_has","operation_send_transfer","question_how_many_now"],"notes":"Send-transfer variant asks for receiver quantity after mutation."}
{"id":"gpd-033","problem":"Mia has 15 pencils. Noah has 7 pencils. Mia gives 6 pencils to Noah. How many pencils does Noah have now?","expected_answer":13,"expected_unit":"pencils","ground_truth_graph":{"entities":["Mia","Noah"],"initial_state":[{"entity":"Mia","quantity":{"unit":"pencils","value":15}},{"entity":"Noah","quantity":{"unit":"pencils","value":7}}],"operations":[{"actor":"Mia","kind":"transfer","operand":{"unit":"pencils","value":6},"target":"Noah"}],"unknown":{"entity":"Noah","unit":"pencils"}},"patterns":["initial_has","operation_give_transfer","question_how_many_now"],"notes":"Receiver-focused give case with explicit same-unit transfer between named entities."}
{"id":"gpd-034","problem":"Eli has 20 stamps. Zoe has 4 stamps. Eli sends 5 stamps to Zoe. How many stamps does Eli have left?","expected_answer":15,"expected_unit":"stamps","ground_truth_graph":{"entities":["Eli","Zoe"],"initial_state":[{"entity":"Eli","quantity":{"unit":"stamps","value":20}},{"entity":"Zoe","quantity":{"unit":"stamps","value":4}}],"operations":[{"actor":"Eli","kind":"transfer","operand":{"unit":"stamps","value":5},"target":"Zoe"}],"unknown":{"entity":"Eli","unit":"stamps"}},"patterns":["initial_has","operation_send_transfer","question_how_many_left"],"notes":"Sender-focused send-transfer with left-style question surface."}
{"id":"gpd-035","problem":"Ryan has 11 books. Ava has 2 books. Ryan gives 3 books to Ava. How many books does Ava have now?","expected_answer":5,"expected_unit":"books","ground_truth_graph":{"entities":["Ryan","Ava"],"initial_state":[{"entity":"Ryan","quantity":{"unit":"books","value":11}},{"entity":"Ava","quantity":{"unit":"books","value":2}}],"operations":[{"actor":"Ryan","kind":"transfer","operand":{"unit":"books","value":3},"target":"Ava"}],"unknown":{"entity":"Ava","unit":"books"}},"patterns":["initial_has","operation_give_transfer","question_how_many_now"],"notes":"Standard give-transfer with both entities initialized in introduction order."}
{"id":"gpd-036","problem":"Omar has 14 balls. Lina has 6 balls. Omar sends 4 balls to Lina. How many balls does Omar have now?","expected_answer":10,"expected_unit":"balls","ground_truth_graph":{"entities":["Omar","Lina"],"initial_state":[{"entity":"Omar","quantity":{"unit":"balls","value":14}},{"entity":"Lina","quantity":{"unit":"balls","value":6}}],"operations":[{"actor":"Omar","kind":"transfer","operand":{"unit":"balls","value":4},"target":"Lina"}],"unknown":{"entity":"Omar","unit":"balls"}},"patterns":["initial_has","operation_send_transfer","question_how_many_now"],"notes":"Send-transfer balances give/send lexical coverage while preserving simple arithmetic."}
{"id":"gpd-037","problem":"Clara has 18 beads. Ivan has 9 beads. Clara gives 7 beads to Ivan. How many beads does Clara have now?","expected_answer":11,"expected_unit":"beads","ground_truth_graph":{"entities":["Clara","Ivan"],"initial_state":[{"entity":"Clara","quantity":{"unit":"beads","value":18}},{"entity":"Ivan","quantity":{"unit":"beads","value":9}}],"operations":[{"actor":"Clara","kind":"transfer","operand":{"unit":"beads","value":7},"target":"Ivan"}],"unknown":{"entity":"Clara","unit":"beads"}},"patterns":["initial_has","operation_give_transfer","question_how_many_now"],"notes":"Give-transfer case with sender unknown to verify actor-side decrement semantics."}
{"id":"gpd-038","problem":"Peter has 10 cards. Quinn has 12 cards. Peter sends 5 cards to Quinn. How many cards does Quinn have now?","expected_answer":17,"expected_unit":"cards","ground_truth_graph":{"entities":["Peter","Quinn"],"initial_state":[{"entity":"Peter","quantity":{"unit":"cards","value":10}},{"entity":"Quinn","quantity":{"unit":"cards","value":12}}],"operations":[{"actor":"Peter","kind":"transfer","operand":{"unit":"cards","value":5},"target":"Quinn"}],"unknown":{"entity":"Quinn","unit":"cards"}},"patterns":["initial_has","operation_send_transfer","question_how_many_now"],"notes":"Receiver-side unknown with send verb confirms transfer target increment behavior."}
{"id":"gpd-039","problem":"Nia has 16 marbles. Leo has 8 marbles. Nia gives 2 marbles to Leo. How many marbles do they have in total now?","expected_answer":24,"expected_unit":"marbles","ground_truth_graph":{"entities":["Nia","Leo"],"initial_state":[{"entity":"Nia","quantity":{"unit":"marbles","value":16}},{"entity":"Leo","quantity":{"unit":"marbles","value":8}}],"operations":[{"actor":"Nia","kind":"transfer","operand":{"unit":"marbles","value":2},"target":"Leo"}],"unknown":{"entity":null,"unit":"marbles"}},"patterns":["initial_has","operation_give_transfer","question_how_many_total"],"notes":"Transfer-invariant total question ensures unknown entity null sums post-operation state."}
{"id":"gpd-040","problem":"Hugo has 13 coins. Iris has 1 coin. Hugo sends 6 coins to Iris. How many coins does Iris have now?","expected_answer":7,"expected_unit":"coins","ground_truth_graph":{"entities":["Hugo","Iris"],"initial_state":[{"entity":"Hugo","quantity":{"unit":"coins","value":13}},{"entity":"Iris","quantity":{"unit":"coins","value":1}}],"operations":[{"actor":"Hugo","kind":"transfer","operand":{"unit":"coins","value":6},"target":"Iris"}],"unknown":{"entity":"Iris","unit":"coins"}},"patterns":["initial_has","operation_send_transfer","question_how_many_now"],"notes":"Send transfer with singular noun surface canonicalized to plural unit in graph."}
{"id":"gpd-041","problem":"Dina has 19 cards. Omar has 4 cards. Dina gives 5 cards to Omar. Omar gives 3 cards to Dina. How many cards does Dina have now?","expected_answer":17,"expected_unit":"cards","ground_truth_graph":{"entities":["Dina","Omar"],"initial_state":[{"entity":"Dina","quantity":{"unit":"cards","value":19}},{"entity":"Omar","quantity":{"unit":"cards","value":4}}],"operations":[{"actor":"Dina","kind":"transfer","operand":{"unit":"cards","value":5},"target":"Omar"},{"actor":"Omar","kind":"transfer","operand":{"unit":"cards","value":3},"target":"Dina"}],"unknown":{"entity":"Dina","unit":"cards"}},"patterns":["initial_has","operation_give_transfer","question_how_many_now"],"notes":"Bidirectional transfer sequence stresses strict source-text operation ordering."}
{"id":"gpd-042","problem":"Cal has 8 letters. Bea has 15 letters. Cal sends 2 letters to Bea. Bea sends 6 letters to Cal. How many letters does Bea have now?","expected_answer":11,"expected_unit":"letters","ground_truth_graph":{"entities":["Cal","Bea"],"initial_state":[{"entity":"Cal","quantity":{"unit":"letters","value":8}},{"entity":"Bea","quantity":{"unit":"letters","value":15}}],"operations":[{"actor":"Cal","kind":"transfer","operand":{"unit":"letters","value":2},"target":"Bea"},{"actor":"Bea","kind":"transfer","operand":{"unit":"letters","value":6},"target":"Cal"}],"unknown":{"entity":"Bea","unit":"letters"}},"patterns":["initial_has","operation_send_transfer","question_how_many_now"],"notes":"Two sends in opposite directions provide a higher-depth transfer-only case."}
{"id":"gpd-043","problem":"Mara has 6 stickers. Cole has 9 stickers. How many stickers do they have in total?","expected_answer":15,"expected_unit":"stickers","ground_truth_graph":{"entities":["Mara","Cole"],"initial_state":[{"entity":"Mara","quantity":{"unit":"stickers","value":6}},{"entity":"Cole","quantity":{"unit":"stickers","value":9}}],"operations":[],"unknown":{"entity":null,"unit":"stickers"}},"patterns":["initial_has","question_how_many_total"],"notes":"Two-entity no-op total-sum case with pronoun 'they' resolving to all introduced entities."}
{"id":"gpd-044","problem":"Aria has 4 apples. Blake has 7 apples. Cora has 5 apples. How many apples do they have in total?","expected_answer":16,"expected_unit":"apples","ground_truth_graph":{"entities":["Aria","Blake","Cora"],"initial_state":[{"entity":"Aria","quantity":{"unit":"apples","value":4}},{"entity":"Blake","quantity":{"unit":"apples","value":7}},{"entity":"Cora","quantity":{"unit":"apples","value":5}}],"operations":[],"unknown":{"entity":null,"unit":"apples"}},"patterns":["initial_has","question_how_many_total"],"notes":"Three-entity aggregate with no state mutation to isolate multi-entity summation behavior."}
{"id":"gpd-045","problem":"Drew has 3 pens. Elle has 8 pens. Finn has 6 pens. Gwen has 9 pens. How many pens do they have in total?","expected_answer":26,"expected_unit":"pens","ground_truth_graph":{"entities":["Drew","Elle","Finn","Gwen"],"initial_state":[{"entity":"Drew","quantity":{"unit":"pens","value":3}},{"entity":"Elle","quantity":{"unit":"pens","value":8}},{"entity":"Finn","quantity":{"unit":"pens","value":6}},{"entity":"Gwen","quantity":{"unit":"pens","value":9}}],"operations":[],"unknown":{"entity":null,"unit":"pens"}},"patterns":["initial_has","question_how_many_total"],"notes":"Four-entity no-op total checks entity-order preservation at maximum tranche width."}
{"id":"gpd-046","problem":"Amy has 5 shells. Ben has 10 shells. Cia has 4 shells. Ben buys 3 more shells. How many shells do they have in total now?","expected_answer":22,"expected_unit":"shells","ground_truth_graph":{"entities":["Amy","Ben","Cia"],"initial_state":[{"entity":"Amy","quantity":{"unit":"shells","value":5}},{"entity":"Ben","quantity":{"unit":"shells","value":10}},{"entity":"Cia","quantity":{"unit":"shells","value":4}}],"operations":[{"actor":"Ben","kind":"add","operand":{"unit":"shells","value":3}}],"unknown":{"entity":null,"unit":"shells"}},"patterns":["initial_has","operation_buy_more","question_how_many_total"],"notes":"Multi-entity limited-op case where one actor mutates before total aggregation."}
{"id":"gpd-047","problem":"Dax has 12 marbles. Ema has 11 marbles. Fox has 7 marbles. Gia has 10 marbles. Fox loses 2 marbles. How many marbles do they have in total now?","expected_answer":38,"expected_unit":"marbles","ground_truth_graph":{"entities":["Dax","Ema","Fox","Gia"],"initial_state":[{"entity":"Dax","quantity":{"unit":"marbles","value":12}},{"entity":"Ema","quantity":{"unit":"marbles","value":11}},{"entity":"Fox","quantity":{"unit":"marbles","value":7}},{"entity":"Gia","quantity":{"unit":"marbles","value":10}}],"operations":[{"actor":"Fox","kind":"subtract","operand":{"unit":"marbles","value":2}}],"unknown":{"entity":null,"unit":"marbles"}},"patterns":["initial_has","operation_lose_loses","question_how_many_total"],"notes":"Four-entity limited-op total tests subtract mutation on a non-leading entity index."}
{"id":"gpd-048","problem":"Hal has 6 coins. Ina has 9 coins. Hal doubles his coins. How many coins do they have in total now?","expected_answer":21,"expected_unit":"coins","ground_truth_graph":{"entities":["Hal","Ina"],"initial_state":[{"entity":"Hal","quantity":{"unit":"coins","value":6}},{"entity":"Ina","quantity":{"unit":"coins","value":9}}],"operations":[{"actor":"Hal","kind":"multiply","operand":{"unit":"coins","value":2}}],"unknown":{"entity":null,"unit":"coins"}},"patterns":["initial_has","operation_double","question_how_many_total"],"notes":"Two-entity total with limited multiply operation before summation across all entities."}
{"id":"gpd-049","problem":"Jay has 18 stamps. Kai has 6 stamps. Lux has 12 stamps. Jay splits his stamps evenly into 3 groups and keeps one group. How many stamps do they have in total now?","expected_answer":24,"expected_unit":"stamps","ground_truth_graph":{"entities":["Jay","Kai","Lux"],"initial_state":[{"entity":"Jay","quantity":{"unit":"stamps","value":18}},{"entity":"Kai","quantity":{"unit":"stamps","value":6}},{"entity":"Lux","quantity":{"unit":"stamps","value":12}}],"operations":[{"actor":"Jay","kind":"divide","operand":{"unit":"stamps","value":3}}],"unknown":{"entity":null,"unit":"stamps"}},"patterns":["initial_has","operation_split_divide","question_how_many_total"],"notes":"Divide-limited multi-entity case verifies total computation after scalar reduction of one entity."}
{"id":"gpd-050","problem":"Mila has 14 dollars. Nori has 5 dollars. Oren has 13 dollars. Paz has 8 dollars. How many dollars do they have in total?","expected_answer":40,"expected_unit":"dollars","ground_truth_graph":{"entities":["Mila","Nori","Oren","Paz"],"initial_state":[{"entity":"Mila","quantity":{"unit":"dollars","value":14}},{"entity":"Nori","quantity":{"unit":"dollars","value":5}},{"entity":"Oren","quantity":{"unit":"dollars","value":13}},{"entity":"Paz","quantity":{"unit":"dollars","value":8}}],"operations":[],"unknown":{"entity":null,"unit":"dollars"}},"patterns":["initial_has","question_how_many_total"],"notes":"Final multi-entity no-op case uses currency unit canonicalized directly as dollars."}