{ "schema_version": 1, "model": { "name": "3-digit-basic-calc", "parameters": 1596160, "source_checkpoint": "ckp/scratchpad_v3_256x2x8_bs32.pt", "representation": "scratchpad-v3", "decoding": "greedy" }, "conversion_validation": { "date": "2026-07-24", "dataset_rows_tokenized": 108000, "tokenizer_id_mismatches": 0, "learned_tensors_compared": 24, "learned_tensor_mismatches": 0, "export_tensor_count": 26, "derived_export_tensors": [ "decoder_layers.0.attn.rope.inv_freq", "decoder_layers.1.attn.rope.inv_freq" ], "prompt_logit_max_abs_difference": 0.0, "complete_162_token_logit_max_abs_difference": 0.0, "argmax_mismatches": 0 }, "validation": { "split": "val", "rows": 4000, "implementation": "exported Hugging Face architecture", "device": "cpu", "elapsed_seconds": 1513.414, "answer": { "+": {"correct": 999, "total": 1000, "accuracy": 0.999}, "-": {"correct": 997, "total": 1000, "accuracy": 0.997}, "*": {"correct": 1000, "total": 1000, "accuracy": 1.0}, "/": {"correct": 968, "total": 1000, "accuracy": 0.968}, "overall": {"correct": 3964, "total": 4000, "accuracy": 0.991} }, "trace_exact": { "+": {"correct": 999, "total": 1000, "accuracy": 0.999}, "-": {"correct": 997, "total": 1000, "accuracy": 0.997}, "*": {"correct": 1000, "total": 1000, "accuracy": 1.0}, "/": {"correct": 949, "total": 1000, "accuracy": 0.949}, "overall": {"correct": 3945, "total": 4000, "accuracy": 0.98625} }, "parse_success": {"correct": 4000, "total": 4000, "accuracy": 1.0} }, "locked_test": { "split": "test", "rows": 4000, "device": "mps", "source_report": "sample/scratchpad_v3_test_eval.json", "answer": { "+": {"correct": 999, "total": 1000, "accuracy": 0.999}, "-": {"correct": 999, "total": 1000, "accuracy": 0.999}, "*": {"correct": 1000, "total": 1000, "accuracy": 1.0}, "/": {"correct": 952, "total": 1000, "accuracy": 0.952}, "overall": {"correct": 3950, "total": 4000, "accuracy": 0.9875} }, "sequence_exact": {"correct": 3925, "total": 4000, "accuracy": 0.98125}, "parse_success": {"correct": 4000, "total": 4000, "accuracy": 1.0} }, "fresh_prompt_disjoint": { "seed": 20260723, "rows": 3000, "sampling": "uniform random operands and operation-balanced, excluding all 108000 dataset prompts", "implementation": "native checkpoint after exact exported-logit parity was established", "answer": { "+": {"correct": 747, "total": 750, "accuracy": 0.996}, "-": {"correct": 748, "total": 750, "accuracy": 0.9973333333}, "*": {"correct": 750, "total": 750, "accuracy": 1.0}, "/": {"correct": 698, "total": 750, "accuracy": 0.9306666667}, "overall": {"correct": 2943, "total": 3000, "accuracy": 0.981} }, "trace_exact": { "+": {"correct": 747, "total": 750, "accuracy": 0.996}, "-": {"correct": 748, "total": 750, "accuracy": 0.9973333333}, "*": {"correct": 750, "total": 750, "accuracy": 1.0}, "/": {"correct": 669, "total": 750, "accuracy": 0.892} }, "elapsed_seconds": 1227.1992 }, "division_failure_diagnosis": { "source": "locked_test", "answer_failures": 48, "first_wrong_component": { "quotient_digit_or_product": 47, "remainder": 1 }, "first_wrong_position": { "1": 4, "2": 11, "3": 17, "4": 10, "5": 4, "6": 2 } }, "grpo": { "baseline_division_accuracy": 0.968, "trial_1_division_accuracy": 0.968, "trial_2_division_accuracy": 0.966, "selected_checkpoint": "supervised baseline", "reason": "neither trial improved gated greedy validation" } }