Upload proofs/87652.json with huggingface_hub

Browse files

Files changed (1) hide show

proofs/87652.json +1 -0

proofs/87652.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"schema": 2, "epoch": 87652, "nonce": "b1f23b335a8c84fe", "hotkey": "5HWaQEaTX4u2WnewfycLnzdiqgjD8o9rxZFtetLP8W2NhR2Y", "source_hash": "24837b9ae6895829747c5eb448673693fedbeb2e3e62a5ca170051a512053fc0", "weights_hash": "55832a868b564f05ae2b0253467b9741a3888b259e26d1cd672847858f94c2e8", "model_id": "router", "total_cost_usd": 0.003751876, "n_calls": 6, "call_log_hash": "aec628b2eadfd65f924591035370951a68cf7c6c4f70af4d9de67e29f3f6a4ec", "measurement": "1449fadb4821cadef93f7eecc8c3b040e2cd244e01a2607ea531e5f7055c38d8", "confined": true, "latency_s": 210.55, "tokens_in": 1096, "tokens_out": 27692, "results": [{"benchmark": "mmlu", "task_id": "mmlu-12556", "answer": "A", "cost_usd": 4.6476e-05, "chosen_rung": 1, "rungs_used": [1], "distribution": [0.009927, 0.509184, 4e-06, 4e-06, 0.466468, 4e-06, 0.014409]}, {"benchmark": "mmlu", "task_id": "mmlu-13978", "answer": "C", "cost_usd": 7.900000000000002e-06, "chosen_rung": 4, "rungs_used": [4], "distribution": [0.124798, 0.015517, 2e-06, 2e-06, 0.859016, 2e-06, 0.000663]}, {"benchmark": "math", "task_id": "gsm8k-446", "answer": "First, calculate the total number of eggs Rozanne has. She starts with 4 dozen eggs, and since 1 dozen equals 12 eggs, 4 dozen is 4 \u00d7 12 = 48 eggs. Adding the 2 loose eggs gives 48 + 2 = 50 eggs in total.\n\nNext, determine how many eggs are required for one full tray. Each tray holds 5 glasses, and each glass needs 5 eggs, so one tray requires 5 \u00d7 5 = 25 eggs.\n\nFinally, divide the total number of eggs by the number of eggs needed per tray to find how many complete trays she can prepare: 50 \u00f7 25 = 2.\n\nRozanne can put out exactly 2 trays.\n\n2", "cost_usd": 0.00012379, "chosen_rung": 0, "rungs_used": [0], "distribution": [0.433489, 0.308465, 9e-06, 9e-06, 0.189366, 9e-06, 0.068653]}, {"benchmark": "math", "task_id": "gsm8k-1171", "answer": "Each bedroom: \\(20 \\times 12 = 240\\) square feet.\n\nFour bedrooms: \\(4 \\times 240 = 960\\) square feet.\n\nLiving room: \\(5 \\times 240 = 1200\\) square feet.\n\nTotal area: \\(960 + 1200 + 1000 = 3160\\) square feet.\n\n3160", "cost_usd": 9.400000000000001e-05, "chosen_rung": 4, "rungs_used": [4], "distribution": [0.288946, 0.006465, 5e-06, 5e-06, 0.63632, 5e-06, 0.068254]}, {"benchmark": "code", "task_id": "lcb-abc388_a", "answer": "import sys\n\ns = sys.stdin.readline().strip()\nprint(s[0] + \"UPC\")", "cost_usd": 3.6300000000000015e-05, "chosen_rung": 4, "rungs_used": [4], "distribution": [9e-06, 3.8e-05, 0.0, 0.0, 0.999936, 0.0, 1.6e-05]}, {"benchmark": "code", "task_id": "lcb-abc388_d", "answer": "```python\nimport sys\n\n# Increase recursion depth just in case, though not strictly needed here\nsys.setrecursionlimit(2000)\n\ndef main():\n # Read all input from stdin efficiently\n # Using sys.stdin.read().split() handles all whitespace separations (spaces, newlines)\n input_data = sys.stdin.read().split()\n \n if not input_data:\n return\n\n iterator = iter(input_data)\n try:\n N = int(next(iterator))\n except StopIteration:\n return\n\n # A is 0-indexed in list, but logic uses 1-based index for aliens\n # A[i] corresponds to alien i+1\n # We expect N integers for A\n # Using a list comprehension to consume exactly N integers\n A = [int(next(iterator)) for _ in range(N)]\n \n # Events array for difference array technique\n # Size N + 2 to handle 1-based indexing up to N+1 safely\n # events[k] stores the change in the number of active adults at step k\n # An active adult is one who has at least one stone and will give a stone to the next adult\n events = [0] * (N + 2)\n active = 0\n \n # Result list to store B_i\n B = []\n \n # Process each alien j from 1 to N\n # In 0-based index for A, this corresponds to index j-1\n for j in range(1, N + 1):\n # Update active count based on events scheduled for this year.\n # 'active' represents the number of adults with stones who will give a stone to the current alien j.\n # The difference array 'events' accumulates +1 when an interval starts and -1 when it ends.\n active += events[j]\n \n # R_j is the number of stones received by alien j from previous adults\n r_val = active\n \n # Calculate final stones for alien j (B_j)\n # Initial stones: A[j-1]\n # Received stones: r_val\n # Total available to give: A[j-1] + r_val\n # Years remaining to give: N - j\n # (Since alien j becomes adult at year j, it gives stones in years j+1, ..., N)\n \n a_val = A[j-1]\n total_stones = a_val + r_val\n years_to_give = N - j\n \n # Number of stones given is min(total_stones, years_to_give)\n # Because alien j gives 1 stone per year as long as it has stones.\n if total_stones < years_to_give:\n given = total_stones\n else:\n given = years_to_give\n \n b_val = total_stones - given\n B.append(str(b_val))\n \n # Determine the range of aliens that alien j will give stones to.\n # Alien j gives 1 stone to each alien k in [j+1, L_j]\n # where L_j = j + A_j + R_j.\n # This is because alien j starts with A_j + R_j stones and gives 1 per year.\n # Note: A_j is a_val, R_j is r_val.\n l_val = j + a_val + r_val\n \n # Schedule the interval [j+1, l_val] in the difference array.\n # This interval indicates that alien j will contribute to the 'active' count\n # for all future aliens k such that j+1 <= k <= l_val.\n \n # Add 1 to active count starting at j+1\n if j + 1 <= N:\n events[j+1] += 1\n \n # Subtract 1 from active count after l_val (i.e., at l_val + 1)\n # We only need to track up to N, so if l_val + 1 > N, we can ignore the subtraction\n # because it won't affect any R_k for k <= N.\n if l_val + 1 <= N:\n events[l_val + 1] -= 1\n \n # Print the results separated by spaces\n print(\" \".join(B))\n\nif __name__ == '__main__':\n main()\n```", "cost_usd": 0.00344341, "chosen_rung": 0, "rungs_used": [0], "distribution": [0.999867, 1.6e-05, 0.0, 0.0, 8.7e-05, 0.0, 3e-05]}], "quote": {"measurement": "1449fadb4821cadef93f7eecc8c3b040e2cd244e01a2607ea531e5f7055c38d8", "report_data": "d4407c824c9cfdc421b2506e18dc6a1739e8f05631acf3af6e256f519489c281", "platform_sig": "tdx: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"}}