Search the runs
What can be asked
Each term is a field the record names; every term must match. Values are matched exactly, as recorded.
setting:<step>.<name>=<value>: a step's recorded setting; * for any stepinput:<name>=<digest>: a step's input by name and digestinputs:same-as:<run>: every input of the first step equal to that run'sfirst_diff:<step>: a held comparison of the run first differs at that stepfirst_diff:any:<kind>: ...and a setting, input, configuration or output differs therediff:same-as:<run>: first differs from the same baseline, at the same step, in the same wayverdict:<word>: the verifier's verdict, PASS or FAILrow:"<name>"=<result>: a row of the verifier's that read FAIL or NOT-RUNmodel:<field>=<value>: a model-call record's field: model, weights, engine, engine_version, dtype, batch_invariantengine:<name>: a model-call record's enginegated:<step>: a step the manifest declares gatedpipeline:<id>: the console's pipeline, P1, P2, ...since:<run>: runs that arrived after that runbenchmark:yes|no: marked as a benchmark, or not
Compared with pz-60-agent-capture-baseline-subagent, the run this search was asked from.
2 runs match every term.
| Run | Pipeline | What matched, as recorded | Compare with this run |
|---|---|---|---|
| pz-62-agent-capture-row-changed-subagent | P2 |
| not compared on this demo |
| pz-64-agent-capture-batch-off-subagent | P2 |
| not compared on this demo |