thesisPrototype

Government data

US manufacturing production m/m, July 2026

Federal Reserve G.17 Manufacturing (NAICS) industrial production, seasonally adjusted monthly percent change for July 2026, first print

Forecast

+0.1%
-0.3%–+0.5%
80% prediction interval
gpt-5.5Run record ↗

Cumulative probability

Chance that the outcome is at or below each value.

0%25%50%75%100%-0.9%+0.1%+1.1%Forecast value

Shaded band: 80% interval (-0.3%–+0.5%). Dashed line: point estimate (+0.1%).

Derived from the point estimate and 80% interval; the agent did not report a full distribution.

Observed outcomeinside 80% interval
actual
+0.2%
forecast
+0.1% with 80% interval [-0.3%, +0.5%]
error
+0.1% · absolute +0.1%
cdf score
CRPS 0.10 · PIT 0.60
source
federal_reserve_g17 G.17 Industrial Production and Capacity Utilization, monthly seasonally adjusted

First print for 2026-07 captured from https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=IPMAN&vintage_date=2026-08-18 on the official release date named by the cell's resolver.

Analysis

§US Manufacturing Production July 2026 First Print

Framing and exact resolver: the target is the Federal Reserve G.17 Manufacturing (NAICS) industrial production monthly percent change, seasonally adjusted, for July 2026. The ledger resolver is ALFRED/FRED IPMAN first-vintage CSV; FRED/ALFRED is therefore used as the bound resolution mirror, while the Federal Reserve G.17 Table 1 Manufacturing (NAICS) monthly percent-change row identifies the official agency variant.

▸ Reported tool use: official.lookupmodel report
Federal Reserve G.17 release calendar lookup
↳ Fetched Fed calendar shows 2026 G.17 monthly release dates include July 17 as the most recent monthly release and August 18 as the next release; monthly releases are issued at 9:15 a.m.; listed 2026 dates include Jan 16, Feb 18, Mar 16, Apr 16, May 15, Jun 15, Jul 17, Aug 18, Sep 18, Oct 16, Nov 17, and Dec 16.
▸ Reported tool use: official.lookupmodel report
Federal Reserve G.17 current Table 1 percent-change lookup
↳ Fetched Table 1 Manufacturing (NAICS), seasonally adjusted monthly rates: Jan 2026 0.1, Feb 2026 0.7, Mar 2026 0.1, Apr 2026 0.7, May 2026 0.1, Jun 2026 0.0; Q2 2026 annual rate 4.6 and June 2025 to June 2026 change 1.1.
▸ Reported tool use: official.lookupmodel report
Federal Reserve G.17 current release industry-detail lookup
↳ Fetched current-release narrative: manufacturing output was unchanged in June at 0.0, durable manufacturing decreased 0.1, nondurable manufacturing increased 0.2, petroleum and coal products increased 2.1, and manufacturing output rose at a 4.7 annual rate in Q2.
▸ Reported tool use: history.lookupmodel report
FRED and ALFRED IPMAN exact index mirror lookup
↳ Fetched IPMAN index levels from public mirror: Jun 2026 98.6995, May 2026 98.6976, Apr 2026 98.5997, Mar 2026 97.8760, Feb 2026 97.7645; next release date shown as Aug 18, 2026.

Reference class/base rate: using the same seasonally adjusted Manufacturing (NAICS) monthly-rate variant, the last six official monthly prints average 0.283 percent. I discount that upward mean because the latest month was flat, durable manufacturing was negative, and the Q2 strength appears front-loaded rather than accelerating into June.

Prior/update/interval: persistence prior is recent Fed G.17 Manufacturing (NAICS) m/m prints from Jan-Jun 2026 [0.1, 0.7, 0.1, 0.7, 0.1, 0.0], with base rate mean 0.283; updates are -0.10 for June flatness, -0.05 for durable weakness, and -0.03 for front-loaded Q2, giving about 0.10 after rounding. For the 80% interval, I use the fetched same-year realized dispersion because the draft evidence set only fetched these exact same-variant monthly changes; sample dispersion of those monthly percent changes is sigma = 0.33, so half-width = 1.28*sigma = 1.28*0.33 = 0.42; point 0.10 minus/plus 0.42 gives [-0.32, 0.52].

Counter-considerations: upside risk is a July rebound in motor vehicles, high-tech equipment, or petroleum-related manufacturing that would land above the interval; downside risk is a broad durable-goods pullback, auto shutdowns, or machinery/electrical-equipment weakness that would land below the interval; outside the interval would require a monthly move larger than roughly 0.5 percent or below roughly -0.3 percent on the first print.

Review disposition: accepted the resolver critique by aligning resolutionSourceUrl to the ledger ALFRED IPMAN CSV and explicitly naming the IPMAN index-versus-percent-growth discrepancy; accepted the interval critique as a disclosure/justification rather than changing the numbers, because no longer same-variant realized-volatility sample was fetched in the draft evidence set.

Key drivers

  • Recent manufacturing NAICS momentum slowed to 0.0 percent in June after 0.1 percent in May and 0.7 percent in April.
  • Second-quarter manufacturing NAICS growth was positive but front-loaded, with no clear June carry-through.
  • Durable manufacturing slipped in June while nondurable manufacturing rose, suggesting offsetting components rather than a broad surge.
  • Manufacturing capacity utilization remained below its long-run average, limiting inflationary production pressure but leaving room for modest output gains.

Tool evidence

This run has no captured tool responses. “Reported tool use” in the analysis is the model’s account, not an archived tool response.

Sources and resolution

Official source
ALFRED/FRED IPMAN first-vintage CSV for Federal Reserve G.17 Industrial Production and Capacity Utilization
Resolved
August 23, 2026
Resolution rule
Resolve under the ledger sourceBinding to the first-print ALFRED/FRED vintage of IPMAN for the Federal Reserve G.17 Manufacturing (NAICS) industrial production index released on August 18, 2026. Because the ledger binds sourceSeriesId IPMAN, an index level, while targetUnit is percent_growth, compute the July 2026 month-over-month percent growth from the first-vintage IPMAN index level relative to the June 2026 level when needed; use the first official/ALFRED vintage and ignore later revisions. The Federal Reserve Table 1 one-decimal Manufacturing (NAICS) monthly percent change is the same G.17 variant used for public display context.
Run details

The analysis is the model’s written report. Tool-use descriptions in that report are model claims; the activity artifacts contain the execution record.

thesis.analyst · gpt-5.5 · fast · v2.4.0

pre-submit review · completed

Draft is mostly coherent, but the resolver/source fields do not exactly follow the canonical ledger contract and the interval relies on a very short six-month sample.

  • blocking resolver: The draft's resolutionSource and resolutionSourceUrl point to Federal Reserve Table 1, while the canonical ledger sourceBinding specifies the ALFRED/FRED IPMAN CSV, allowed host alfred.stlouisfed.org, and first_print policy.
  • warning interval: The 80% interval uses sigma from only Jan-Jun 2026, which is a very small and unusually recent sample for realized volatility.
  • info optional_suggestion: Clarify whether the ALFRED IPMAN index first print will be converted to a monthly percent change or whether the published one-decimal Table 1 percent change is authoritative.
  • info optional_suggestion: The tail scenarios are concrete, but they could name which July subcomponents would plausibly move the aggregate outside the stated bounds.

disposition accepted: Review disposition: accepted the resolver critique by aligning resolutionSourceUrl to the ledger ALFRED IPMAN CSV and explicitly naming the IPMAN index-versus-percent-growth discrepancy; accepted the interval critique as a disclosure/justification rather than changing the numbers, because no longer same-variant realized-volatility sample was fetched in the draft evidence set.

disposition accepted: Review disposition: accepted the resolver critique by aligning resolutionSourceUrl to the ledger ALFRED IPMAN CSV and explicitly naming the IPMAN index-versus-percent-growth discrepancy; accepted the interval critique as a disclosure/justification rather than changing the numbers, because no longer same-variant realized-volatility sample was fetched in the draft evidence set.

disposition not applicable: Review disposition: accepted the resolver critique by aligning resolutionSourceUrl to the ledger ALFRED IPMAN CSV and explicitly naming the IPMAN index-versus-percent-growth discrepancy; accepted the interval critique as a disclosure/justification rather than changing the numbers, because no longer same-variant realized-volatility sample was fetched in the draft evidence set.

disposition not applicable: Review disposition: accepted the resolver critique by aligning resolutionSourceUrl to the ledger ALFRED IPMAN CSV and explicitly naming the IPMAN index-versus-percent-growth discrepancy; accepted the interval critique as a disclosure/justification rather than changing the numbers, because no longer same-variant realized-volatility sample was fetched in the draft evidence set.

Activity artifacts

Complete original trace

§US Manufacturing Production July 2026 First Print

Framing and exact resolver: the target is the Federal Reserve G.17 Manufacturing (NAICS) industrial production monthly percent change, seasonally adjusted, for July 2026. The ledger resolver is ALFRED/FRED IPMAN first-vintage CSV; FRED/ALFRED is therefore used as the bound resolution mirror, while the Federal Reserve G.17 Table 1 Manufacturing (NAICS) monthly percent-change row identifies the official agency variant.

▸ Reported tool use: official.lookupmodel report
Federal Reserve G.17 release calendar lookup
↳ Fetched Fed calendar shows 2026 G.17 monthly release dates include July 17 as the most recent monthly release and August 18 as the next release; monthly releases are issued at 9:15 a.m.; listed 2026 dates include Jan 16, Feb 18, Mar 16, Apr 16, May 15, Jun 15, Jul 17, Aug 18, Sep 18, Oct 16, Nov 17, and Dec 16.
▸ Reported tool use: official.lookupmodel report
Federal Reserve G.17 current Table 1 percent-change lookup
↳ Fetched Table 1 Manufacturing (NAICS), seasonally adjusted monthly rates: Jan 2026 0.1, Feb 2026 0.7, Mar 2026 0.1, Apr 2026 0.7, May 2026 0.1, Jun 2026 0.0; Q2 2026 annual rate 4.6 and June 2025 to June 2026 change 1.1.
▸ Reported tool use: official.lookupmodel report
Federal Reserve G.17 current release industry-detail lookup
↳ Fetched current-release narrative: manufacturing output was unchanged in June at 0.0, durable manufacturing decreased 0.1, nondurable manufacturing increased 0.2, petroleum and coal products increased 2.1, and manufacturing output rose at a 4.7 annual rate in Q2.
▸ Reported tool use: history.lookupmodel report
FRED and ALFRED IPMAN exact index mirror lookup
↳ Fetched IPMAN index levels from public mirror: Jun 2026 98.6995, May 2026 98.6976, Apr 2026 98.5997, Mar 2026 97.8760, Feb 2026 97.7645; next release date shown as Aug 18, 2026.

Reference class/base rate: using the same seasonally adjusted Manufacturing (NAICS) monthly-rate variant, the last six official monthly prints average 0.283 percent. I discount that upward mean because the latest month was flat, durable manufacturing was negative, and the Q2 strength appears front-loaded rather than accelerating into June.

Prior/update/interval: persistence prior is recent Fed G.17 Manufacturing (NAICS) m/m prints from Jan-Jun 2026 [0.1, 0.7, 0.1, 0.7, 0.1, 0.0], with base rate mean 0.283; updates are -0.10 for June flatness, -0.05 for durable weakness, and -0.03 for front-loaded Q2, giving about 0.10 after rounding. For the 80% interval, I use the fetched same-year realized dispersion because the draft evidence set only fetched these exact same-variant monthly changes; sample dispersion of those monthly percent changes is sigma = 0.33, so half-width = 1.28*sigma = 1.28*0.33 = 0.42; point 0.10 minus/plus 0.42 gives [-0.32, 0.52].

Counter-considerations: upside risk is a July rebound in motor vehicles, high-tech equipment, or petroleum-related manufacturing that would land above the interval; downside risk is a broad durable-goods pullback, auto shutdowns, or machinery/electrical-equipment weakness that would land below the interval; outside the interval would require a monthly move larger than roughly 0.5 percent or below roughly -0.3 percent on the first print.

Review disposition: accepted the resolver critique by aligning resolutionSourceUrl to the ledger ALFRED IPMAN CSV and explicitly naming the IPMAN index-versus-percent-growth discrepancy; accepted the interval critique as a disclosure/justification rather than changing the numbers, because no longer same-variant realized-volatility sample was fetched in the draft evidence set.

calibrated forecast · 80% CI
+0.1%[-0.3% · +0.5%]
Target metadata

Data point: fed.g17.manufacturing_production_mom.2026_07.first_print

More government data forecasts