diff --git a/evals/gsm8k_math/train_sample/v1/report.json b/evals/gsm8k_math/train_sample/v1/report.json index e880bb0a..bb4dc415 100644 --- a/evals/gsm8k_math/train_sample/v1/report.json +++ b/evals/gsm8k_math/train_sample/v1/report.json @@ -103,7 +103,7 @@ }, { "case_id": "gsm8k-train-sample-v1-0019", - "reason": "candidate_graph: recognizer matched but produced no injection for statement: 'The dog ends up having health problems and this requires 3 vet appointments, which cost $400 each.' (category=currency_amount)", + "reason": "candidate_graph: recognizer matched but produced no injection for statement: 'After the first appointment, John paid $100 for pet insurance that covers 80% of the subsequent visits.' (category=currency_amount)", "verdict": "refused" }, { @@ -123,7 +123,7 @@ }, { "case_id": "gsm8k-train-sample-v1-0023", - "reason": "candidate_graph: recognizer matched but produced no injection for statement: 'Nicole collected 400 Pokemon cards.' (category=discrete_count_statement)", + "reason": "candidate_graph: recognizer matched but produced no injection for statement: \"Cindy collected twice as many, and Rex collected half of Nicole and Cindy's combined total.\" (category=descriptive_setup_no_quantity)", "verdict": "refused" }, { @@ -133,12 +133,12 @@ }, { "case_id": "gsm8k-train-sample-v1-0025", - "reason": "candidate_graph: recognizer matched but produced no injection for statement: 'Lilibeth fills 6 baskets where each basket holds 50 strawberries.' (category=multiplicative_aggregation)", + "reason": "candidate_graph: no admissible candidate for question: \"If three of Lilibeth's friends pick the same amount as her, how many strawberries do Lilibeth and her friends pick in all?\"", "verdict": "refused" }, { "case_id": "gsm8k-train-sample-v1-0026", - "reason": "candidate_graph: recognizer matched but produced no injection for statement: 'Aaron and his brother Carson each saved up $40 to go to dinner.' (category=currency_amount)", + "reason": "candidate_graph: no admissible candidate for statement: 'Aaron and his brother Carson each saved up $40 to go to dinner.'", "verdict": "refused" }, { @@ -243,7 +243,7 @@ }, { "case_id": "gsm8k-train-sample-v1-0047", - "reason": "candidate_graph: recognizer matched but produced no injection for statement: 'John bakes 12 coconut macaroons, each weighing 5 ounces.' (category=multiplicative_aggregation)", + "reason": "candidate_graph: recognizer matched but produced no injection for statement: 'He then packs an equal number of the macaroons in 4 different brown bags, ready for delivery.' (category=discrete_count_statement)", "verdict": "refused" }, {