c354047e17
Vocabulary v2 adds four themes the CY2027 docket's letters made unmissable: modifier-25-same-day, lactation-services, health-coaching, radiation-therapy (57 themes). tests/llm/golden_themes.yaml: 39 CMS-2026-2377 comments labelled by reading their opening text — expected themes (must carry) and acceptable ones (allowed, not required). llm.tageval scores predictions per slug (tp / fp outside expected∪acceptable / fn), micro precision/recall/F1 and the abstain rate, and gate() applies the spec thresholds (micro-F1 ≥ 0.70; no theme with support ≥ 5 under 0.5 precision). Predictions come from what the last run stored on the bib items (CI, no model calls) or --live through the chain. stack llm eval-tags [--golden] [--live] [--limit] exits 1 when the gate fails.
2.5 KiB
2.5 KiB
title, sidebar_position
| title | sidebar_position |
|---|---|
| stack pfs exposure | 77 |
stack pfs exposure
Usage: stack pfs exposure [OPTIONS]
The exposure calendar (pfs.code_exposure, #693): when each code became
payable, was revalued, changed payable status, ended, or was listed for
telehealth — dated 1 January of the rule year (or the correction notice's
date), anchored to the FR paragraph from its lineage, with the status and
RVU-decile band a control set matches on.
--write always rebuilds every code (control sets need the whole
calendar); --code/--family only filter what is printed.
╭─ Options ────────────────────────────────────────────────────────────────────╮
│ --code TEXT Filter to a code; repeatable. │
│ --family TEXT Filter to a family key (CCM, APCM, …); │
│ repeatable. │
│ --controls INTEGER With one --code and --year: list up to N │
│ never-treated control codes (same status + RVU │
│ band, no exposure within --window years). │
│ [default: 0] │
│ --year INTEGER The exposure year --controls refers to. │
│ [default: 0] │
│ --window INTEGER ±years a control must be quiet for. [default: 2] │
│ --write Rebuild the whole calendar into pfs.code_exposure │
│ and republish. │
│ --help Show this message and exit. │
╰──────────────────────────────────────────────────────────────────────────────╯