Ternary quantization

After grading, a reviewer model reads the submission's files and the agent's trajectory and checks each of the task's rules. A failed check makes the score 0. Step numbers link into the trajectory.

LLM adversarial review is not proof of arbitrary program behavior. Host storage and task-specific deterministic checks remain required.

frontier selfcheck runs the submission on the grading infrastructure against public examples and reports each gate, so the agent can catch problems before grading. Each run gets four. This agent used 3 of 4.

1. 1
   failed30m 10s into the runtook 5m 33s

   startup 154.1 s of 300 s; failed GPQA request as graded: RuntimeError: RuntimeError: Submission returned HTTP 500: b'{"error":{"message":"EngineCore encountered an issue. See stack trace (above) for the root cause.","type":"InternalServerError","param":null,"code":500}}' | RuntimeError: Subm

   6 gates

   • ✓review prerequisites
   • ✓ternary fraction · 3,497,000,960 of 3,679,333,376 audited parameters (text-model weights outside the input embedding and output head, and their scales) are ternary codes: 0.950444, which must exceed 0.95
   • ✓stored parameters · 3,679,333,376 stored (codes, scales, retained floats and 0 in tensors outside the manifest, uint8/int8 counting four each) against 1.1 x 3,570,052,096 original parameters
   • ✓weight audit · inspect_ternary passed, as verify requires before scoring
   • ✓startup · GET /health answered 200 after 154.1 s
   • ✗GPQA request as graded · RuntimeError: RuntimeError: Submission returned HTTP 500: b'{"error":{"message":"EngineCore encountered an issue. See stack trace (above) for the root cause.","type":"InternalServerError","param":null,"code":500}}' | RuntimeError: Submission HTTP request failed: ConnectionRefusedError: [Errno 111] Connection refused | RuntimeError: Submission HTTP request failed: ConnectionRefusedError: [Errno 111] Connection refused
2. 2
   failed38m 10s into the runtook 8m 19s

   startup 263.9 s of 300 s; failed GPQA request as graded: the response was rejected: ValueError: choice has no text content; got {"id": "chatcmpl-8de58d25cdc68e33", "object": "chat.completion", "created": 1791074101, "model": "submission", "choices": [{"index": 0, "message": {"role": "assista

   6 gates

   • ✓review prerequisites
   • ✓ternary fraction · 3,497,000,960 of 3,679,333,376 audited parameters (text-model weights outside the input embedding and output head, and their scales) are ternary codes: 0.950444, which must exceed 0.95
   • ✓stored parameters · 3,679,333,376 stored (codes, scales, retained floats and 0 in tensors outside the manifest, uint8/int8 counting four each) against 1.1 x 3,570,052,096 original parameters
   • ✓weight audit · inspect_ternary passed, as verify requires before scoring
   • ✓startup · GET /health answered 200 after 263.9 s
   • ✗GPQA request as graded · the response was rejected: ValueError: choice has no text content; got {"id": "chatcmpl-8de58d25cdc68e33", "object": "chat.completion", "created": 1791074101, "model": "submission", "choices": [{"index": 0, "message": {"role": "assistant", "content": null, "refusal": null, "annotations": null, "audio": null, "function_call": null, "tool_calls": [], "reas ...[clipped]
3. 3
   passed1h 19m into the runtook 6m 15s

   startup 157.8 s of 300 s; 1/1 gates passed; One wave of 16 concurrent public requests stood for the suite's 3,153 graded ones at that concurrency; MATH-500 and MMLU-Pro are held out.

   9 gates

   • ✓review prerequisites
   • ✓ternary fraction · 3,497,000,960 of 3,679,333,376 audited parameters (text-model weights outside the input embedding and output head, and their scales) are ternary codes: 0.950444, which must exceed 0.95
   • ✓stored parameters · 3,679,333,376 stored (codes, scales, retained floats and 0 in tensors outside the manifest, uint8/int8 counting four each) against 1.1 x 3,570,052,096 original parameters
   • ✓weight audit · inspect_ternary passed, as verify requires before scoring
   • ✓startup · GET /health answered 200 after 157.8 s
   • ✓GPQA request as graded · {"finish_reason": "length", "note": "cut off at max_tokens: grading scores such a reply zero", "content_characters": 0, "content_end": ""}
   • ✓slowest of 16 concurrent requests · 16 public requests at once (8 GPQA, 8 hard LiveCodeBench) as graded (max_tokens 4096, temperature 0, 300 s each): slowest 25.2 s, median 25.2 s; 14 stopped at max_tokens, 0 timed out. Grading sends every benchmark 16 at a time, scores a request over 300 s or still failing as wrong with no limit on how many; held-out requests may run longer.
   • ✓concurrent requests answered · 16 well-formed replies
   • ✓healthy after requests

The agent's last message before its session ended.