{ "recorded_date": "2026-10-20", "baseline_report": "bug20-shared-recovery-20261019.json", "candidate_report": "bug20-joint-structure-20261020.json", "scope": "interpretation and hypotheses only; excludes entity resolution and investigation", "accepted_only": { "baseline": { "call_count": 2, "input_tokens": { "known_sum": 31170, "missing_call_count": 0 }, "output_tokens": { "known_sum": 11757, "missing_call_count": 0 }, "reasoning_tokens": { "known_sum": 8328, "missing_call_count": 0 }, "visible_output_tokens": { "known_sum": 3429, "missing_call_count": 0 }, "cached_input_tokens": { "known_sum": 14024, "missing_call_count": 1 }, "api_elapsed_seconds_sum": 97.422 }, "candidate": { "call_count": 1, "input_tokens": { "known_sum": 13733, "missing_call_count": 0 }, "output_tokens": { "known_sum": 7863, "missing_call_count": 0 }, "reasoning_tokens": { "known_sum": 5247, "missing_call_count": 0 }, "visible_output_tokens": { "known_sum": 2616, "missing_call_count": 0 }, "cached_input_tokens": { "known_sum": 0, "missing_call_count": 1 }, "api_elapsed_seconds_sum": 51.156 } }, "all_attempts": { "baseline": { "call_count": 4, "input_tokens": { "known_sum": 63120, "missing_call_count": 0 }, "output_tokens": { "known_sum": 19587, "missing_call_count": 0 }, "reasoning_tokens": { "known_sum": 12903, "missing_call_count": 0 }, "visible_output_tokens": { "known_sum": 6684, "missing_call_count": 0 }, "cached_input_tokens": { "known_sum": 14024, "missing_call_count": 3 }, "api_elapsed_seconds_sum": 162.937 }, "candidate": { "call_count": 1, "input_tokens": { "known_sum": 13733, "missing_call_count": 0 }, "output_tokens": { "known_sum": 7863, "missing_call_count": 0 }, "reasoning_tokens": { "known_sum": 5247, "missing_call_count": 0 }, "visible_output_tokens": { "known_sum": 2616, "missing_call_count": 0 }, "cached_input_tokens": { "known_sum": 0, "missing_call_count": 1 }, "api_elapsed_seconds_sum": 51.156 } }, "account_eur": { "candidate_start": 12.46, "candidate_latest_reported": 12.47, "candidate_final": null, "settlement": "pending_provider_delay" }, "limitations": [ "Single runs with different prompt versions, not a controlled paired benchmark", "Baseline accepted hypothesis call reports 14024 cached input tokens; candidate planning reports no cached count", "Token reductions do not imply proportional price reductions" ] }