Observed congressional language, rendered as two cited automated composites.

Automated measurement. Composite prose is generated from claims selected and counted by code.

OnScript · 2026-08-08

Observed congressional language on 2026-08-08, rendered as two cited automated composites.

Democrats

Measurement: 21 publications were observed for the Democratic party on 2026-08-08.

Composite state: deterministic_fallback

Today 21 of us released statements. 3 offices across 3 publications and 3 families carried "statement after voting against". Our most synchronized phrase, used by 6 of us: statement after voting against.

A composite voice, machine-composed from the day’s measured phrases. No member spoke these exact sentences; the quoted spans are verbatim (see receipts).

voice: deterministic template (not a language model) · verifier: passed
Receipts
3 offices · 3 publications · 3 families carried · 3 of 257 (1.2%)
✓ publication verified✓ message key✓ 3 familiesphrase shown 3/3✓ sourced 3/3
Technology & AI · Elections & democracy · Other
  • statement after voting against the continuing resolution to
    Edward J. Markey (D-MA) · 2026-08-08 · source · archived
  • statement after voting against the confirmation of the
    Tina Smith (D-MN) · 2026-08-08 · source · archived
  • statement after voting against the nomination of todd
    Adam B. Schiff (D-CA) · 2026-08-08 · source · archived
Republicans

Measurement: 11 publications were observed for the Republican party on 2026-08-08.

Composite state: generated_verified

We released 11 statements today.

A composite voice, machine-composed from the day’s measured phrases. No member spoke these exact sentences; the quoted spans are verbatim (see receipts).

generator: sonnet_direct · model: claude-sonnet-5 · quiet day · verifier: passed

No talking point cleared the 3-member threshold today — nothing to cite.

How this is counted

Participation in eligible message claims

Each measure keeps one count unit from numerator through denominator.

D

  • Office participation: 3 offices of 16 offices. Window: party-day 2026-08-08. Method: participation-measures-v1.
  • Publication participation: 3 publications of 21 publications. Window: party-day 2026-08-08. Method: participation-measures-v1.
  • Document-family participation: 3 document families of 21 document families. Window: party-day 2026-08-08. Method: participation-measures-v1.

R

  • Office participation: 0 offices of 8 offices. Window: party-day 2026-08-08. Method: participation-measures-v1.
  • Publication participation: 0 publications of 11 publications. Window: party-day 2026-08-08. Method: participation-measures-v1.
  • Document-family participation: 0 document families of 11 document families. Window: party-day 2026-08-08. Method: participation-measures-v1.

These two bases differ. Office counts come from the day's eligible caucus offices in the nightly symmetry audit; publication counts come from the day's source publications. A joint release is one publication and can carry several offices, so the two never have to agree.

Nightly symmetry audit: nightly symmetry audit. Every distilled claim above is citation-backed.

Repeated phrase observations

This table lists repeated phrase observations, ranked by how many members used the same exact phrase. It is not filtered to coordinated messages, so it can include official names, procedural formulas, and biographical phrasing, not only messages. The sparkline is the phrase's 14-day trajectory.

Each party’s own most-synchronized phrases, ranked within the party so the larger caucus can’t fill the table — every count travels with its caucus denominator.

D repeated phrases

  1. 6 of 257 (2.3%) statement after voting against Phrase trend14 observations; peak 10 members.
  2. 6 of 257 (2.3%) rule of law Phrase trend14 observations; peak 8 members.
  3. 4 of 257 (1.6%) 1 8 billion Phrase trend14 observations; peak 6 members.
  4. 3 of 257 (1.2%) uphold the rule of law Phrase trend14 observations; peak 3 members.
  5. 3 of 257 (1.2%) applied fairly and Phrase trend3 observations; peak 3 members.
  6. 3 of 257 (1.2%) family and his businesses Phrase trend10 observations; peak 3 members.
  7. 3 of 257 (1.2%) the president’s personal Phrase trend14 observations; peak 3 members.
  8. 3 of 257 (1.2%) voting against the Phrase trend14 observations; peak 10 members.

R repeated phrases

  1. 3 of 271 (1.1%) continuing resolution cr Phrase trend14 observations; peak 3 members.
  2. 3 of 271 (1.1%) a continuing resolution Phrase trend14 observations; peak 5 members.

Each table is one party measured against that party's own caucus, so row counts are not comparable across the two. Differences in how much each party publishes are measured in the nightly symmetry audit, not here. See the nightly symmetry audit.