Evidence ledger

Tagged transcript baseline, development split, corpus 2026-09-07.1

MMeasuredEV-002

Produced by running code in this repository and preserved as an artifact.

Scope

Twelve synthetic development transcripts, run once with the deterministic Tagged transcript baseline.

Observation

Action precision 1.00 (8 of 8). Action recall 0.24 (8 of 34). Owner accuracy 0.00 (0 of 6). One case met the acceptance criteria: the no-action meeting, where the baseline correctly produced no action items.

Limitations

Development cases are the ones used while building the method, so they are not an independent test. Reported here for comparison with the held-out split only.

Source

experiments/runs/tagged-transcript-baseline--development--2026-09-07.1/report.json

Source date

2026-09-07

Retrieved

2026-09-07

Reviewer status

Pending review. Written down, not yet checked by a person.

How measured records are produced