$ ls ~/experiments

Experiments

Track A — gpt-oss 20B context ladder

Verdict: partial pass. On Owlforge’s RTX 3090 Ti, gpt-oss:20b passed strict five-needle retrieval at 17,445 and 68,916 prompt tokens. At 107,832 prompt tokens it recovered all five values internally and emitted all five exact values, but violated the preregistered strict-JSON contract. That cell is therefore scored 0/5, not rescued after the fact.

Nominal archiveActual prompt tokensStrict scoreWall timePeak VRAMPeak powerVerdict
16,000 words17,4455/52.384 s15,918 MiB380.63 WPASS
64,000 words68,9165/516.658 s15,918 MiB474.16 WPASS
100,000 words107,8320/530.081 s15,918 MiB475.17 WFAIL — output contract

The 107,832-token response was not a retrieval miss: the reasoning trace identified every needle correctly, and the final channel contained each value. It returned newline-separated text instead of the required JSON object. The preregistered evaluator therefore failed it closed.

Two earlier runs are recorded as infrastructure failures rather than model-quality results:

  • v1: Ollama 0.32.5’s JSON-Schema response mode exposed an empty final channel for this model.
  • v2: the 256-token generation budget truncated an otherwise correct final object.

Public receipt: experiments/track-a/public/gpt-oss-20b-v3-receipt.json

Receipt SHA-256: e4ef0db25d7aee05f2eaecbbd5b5a6e43ac7cde01d67d658ea49f209292ab148

This control measures exact synthetic retrieval only. It does not establish long-context summarization, reasoning, tool use, or million-token usefulness.