Experiment · offhours

OffHours persistent-tension pilot (2026-08-21)

Unresolved narrative tension did not degrade measured work quality under the exercised conditions; a null result is a valid result. Retained outcome: worked with caveat.

Outcome
worked with caveat
Family
offhours
Evidence confidence
exact
Record
model evaluation

Evidence readout

unresolved tension scored 198/200 versus 197/200 resolved, a -0.5 percentage-point paired error difference with 95% interval -3.0 to +1.5

What the attempt taught

Unresolved narrative tension did not degrade measured work quality under the exercised conditions; a null result is a valid result.

Why it stopped or stayed bounded

The frozen experiment found no work-quality penalty, while provider prompt-token, quantization, and model-file provenance remained unavailable.

Method and scope

  • Experiment family: offhours.
  • Record kind: model evaluation.
  • Objective: context interference.
  • Methods: evaluation.
  • Base models: devin-glm-5.2.

Disposition

Closed as report-only evidence; do not tune scenarios after the null.

This retained disposition is historical evidence, not authorization to restart the experiment. A new run needs a fresh question, frozen evaluator, explicit resource budget, and scoped tracking issue.

How to read this dossier

This canonical page separates the retained repository decision from the material that informed it. A source may describe an external claim, historical measurement, local observation, or planned procedure; those evidence classes are not interchangeable. Follow the provenance links before reusing a number or method.

Status and disposition describe what PostTrainLLM retained when this record was indexed. They are not a live product promise, a newly run benchmark, or permission to restart historical work. Unknown or unmeasured fields remain unknown rather than being treated as zero.

To reuse the record, first name the exact claim you need and trace it to the linked source. Then check whether the original environment, model revision, data split, evaluator, hardware, and budget match the proposed use. If they do not, treat the record as a hypothesis or design reference and run the smallest fresh comparison that can falsify it. Preserve negative outcomes and regressions beside any improvement; a local win on one slice does not silently become a general capability claim.

Source provenance

The normalized record comes from docs/attempts.json. The links below are the tracked evidence and explanatory sources preserved with the record.