{
  "created_at": "2026-09-26T18:10:31.859675Z",
  "dataset": "princeton-nlp/SWE-bench_Verified",
  "endpoint": {
    "base_url": "http://127.0.0.1:<ephemeral-port>/v1",
    "model": "swift15-flash-next-nvfp4-tp2-327k-r3"
  },
  "failure": {
    "class": "model_failure",
    "code": "swe_limits_exceeded",
    "stage": "agent"
  },
  "harnesses": {
    "agent": {
      "name": "mini-swe-agent",
      "revision": "a83fcae82d2a08f0ee0c688f9d137b3566c097f8"
    },
    "grader": {
      "name": "swe-bench",
      "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
    },
    "python_environment": {
      "architecture": "x86_64",
      "platform": "linux",
      "python": {
        "implementation": "CPython",
        "version": "3.14.4"
      },
      "resolved_packages_sha256": "809336a2a74041fa07adad60eaca2208acd936f3728d2368d22f98657576a37a",
      "schema": "anvil-serving.swe-python-environment/v1"
    }
  },
  "instances": [
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "04c5a20d30ce391bafd5b5678802d88dfb845cd457c3fd8213a9aee839cf1d70",
        "resolved": true,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "sphinx-doc__sphinx-9658",
      "prediction_sha256": "87fd530f199629945b7a0d57253684e14a6ea5924017b488847b4fa92698fddf",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "retained_private": true,
        "sha256": "f4c0d068dacce4268145c47a53770383533b8c2ab923c86087c56b5cb2c3043d"
      }
    },
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "04c5a20d30ce391bafd5b5678802d88dfb845cd457c3fd8213a9aee839cf1d70",
        "resolved": true,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "sympy__sympy-12096",
      "prediction_sha256": "55fd30dcc8ea363cfba081e7be364070ac8b43c9d90f2debca997e322865569b",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "retained_private": true,
        "sha256": "dc9a5d446d36e5a615f66c958ea198fbe4d7f1286660af5f705e24104db07431"
      }
    },
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "04c5a20d30ce391bafd5b5678802d88dfb845cd457c3fd8213a9aee839cf1d70",
        "resolved": false,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "django__django-13512",
      "prediction_sha256": "df3baae45eeef908a7b46c1c4776457d65523ec32570b860823eb90dd732781c",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "retained_private": true,
        "sha256": "f26f4cba595f3078ba04b230d01848c2a08a37c6d084815d907a47d141d5e7d7"
      }
    },
    {
      "duration_s": null,
      "exit_status": "LimitsExceeded",
      "failure_class": "model_failure",
      "grader": {
        "completed": false,
        "name": "swe-bench",
        "report_sha256": "04c5a20d30ce391bafd5b5678802d88dfb845cd457c3fd8213a9aee839cf1d70",
        "resolved": null,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "pydata__xarray-4356",
      "prediction_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "retained_private": true,
        "sha256": "1666b9176034c520ac94334f4728faa612e0242e5635f74f9a38e19665200c22"
      }
    },
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "04c5a20d30ce391bafd5b5678802d88dfb845cd457c3fd8213a9aee839cf1d70",
        "resolved": false,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "pylint-dev__pylint-8898",
      "prediction_sha256": "f7c6474657ce0bcbd77d0a3f6fb6bae0c832acef8bbe586281e2111cdd107e5a",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "retained_private": true,
        "sha256": "1ababdffa60a74b9a2013560be063016098de2eb21c54dcf66262509ee24223e"
      }
    }
  ],
  "official_grader_complete": false,
  "ownership_id": "swift-tp2-20260926",
  "plan_sha256": "87985e103d3c1a9bedd6ae257c384dcee8ba729a018a406c2f0d04ab75e6e1d1",
  "profile": "scout",
  "profile_sha256": "fce0e6e1e7497585bdfc6f76507d3baaff99a6b4f174d841d268de20c68de7f6",
  "promotion": {
    "authorized": false,
    "message": "Benchmark evidence does not authorize model promotion."
  },
  "public_sanitization": {
    "omitted": [
      "request_ids",
      "trajectory paths",
      "commands",
      "stdout",
      "stderr",
      "container identifiers"
    ],
    "reason": "raw trajectories and private operations logs are retained only in private evidence"
  },
  "request_controls": {
    "reasoning_effort": null,
    "sampling": {
      "temperature": {
        "effective_request": 1.0,
        "requested": 1.0,
        "sent": true
      },
      "top_p": {
        "effective_request": 0.95,
        "requested": 0.95,
        "sent": true
      }
    },
    "thinking_mode": "default"
  },
  "run_id": "swift-tp2-r3-swe",
  "schema": "anvil-serving.swe-run/v1",
  "selection": {
    "instance_ids": [
      "sphinx-doc__sphinx-9658",
      "sympy__sympy-12096",
      "django__django-13512",
      "pydata__xarray-4356",
      "pylint-dev__pylint-8898"
    ],
    "kind": "explicit_instance_ids",
    "sha256": "622934396fb97d950f803dfbb0791f6a398a5a6fe0fd94cc27b329f1a953cac4"
  },
  "split": "test",
  "stages": [
    {
      "duration_s": 6354.312284,
      "failure_class": "model_failure",
      "name": "agent",
      "output_truncated": false,
      "returncode": 0,
      "status": "failed"
    },
    {
      "duration_s": 76.5277,
      "failure_class": "test_failure",
      "name": "official_grader",
      "output_truncated": false,
      "returncode": 0,
      "status": "failed"
    }
  ]
}