coulomb/assembly-economics
5
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
assembly-economics/checkpoints
History
tegwick dc4e3adc99 Close loose ends: WP-0018 finished (T04 capture link tested, T05 reference-model decision), WP-0016 finished (J4 from China data), WP-0014 blocked (owner declaration + grant v2 confirmed; waits on rein-aharness publisher and 2027), WP-0015 blocked (EU Pm measured, noise calibrated; AR data and Q4 2026 data pending); Calibration v0.6 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 14913@bnt-lap001
Assistant-Session: add7ef69-b901-4756-9a67-34cf1125d96f
2026-10-14 02:31:02 +02:00
..
2026 Close loose ends: WP-0018 finished (T04 capture link tested, T05 reference-model decision), WP-0016 finished (J4 from China data), WP-0014 blocked (owner declaration + grant v2 confirmed; waits on rein-aharness publisher and 2027), WP-0015 blocked (EU Pm measured, noise calibrated; AR data and Q4 2026 data pending); Calibration v0.6 2026-10-14 02:31:02 +02:00
data Checkpoint 2026-10-13 (light) — activity-core 2026-10-13 06:01:06 +00:00
EXECUTION_DECLARATION.md Execution declaration approved by the founder (decision addendum); WP-0014-T01 updated 2026-10-13 19:46:38 +02:00
IndicatorCatalog.md ASSEMBLY-WP-0018-T01: dematerialization vs. Eurostat resource productivity; operator corrected; decoupling depends on phi_r (EU fit 0.66: none; DE 0.15: holds), BR-011; E5 wired 2026-10-13 23:26:24 +02:00
PLAYBOOK.md Checkpoint executor: deterministic runner, sources, tests; definitions route to assembly-checkpoint 2026-10-12 18:45:12 +02:00
predictions.md WP-0015: L4/L7 collected, mapping update, 35/39 targets measured (Calibration v0.4), GSA around calibrated starts, first prediction observations; T06 waits for AR growth and EU/AR Pm 2026-10-13 19:15:58 +02:00
README.md ASSEMBLY-WP-0010-T02 (part): checkpoint protocol, playbook, schedule, catalog v0.1, register; activity definitions 2026-10-12 18:21:55 +02:00
run_checkpoint.py ASSEMBLY-WP-0017 finished: IMM filter on observed US data (B3 through mid-2026, B3→B4 flip candidate Q3 2026, not confirmed), robustness, checkpoint pointer; residual to WP-0015-T07 2026-10-13 22:41:08 +02:00
schedule.md Enable checkpoint definitions; one-day baseline window for checkpoint 0 (2026-10-12) 2026-10-12 18:48:12 +02:00
sources.json ASSEMBLY-WP-0018-T01: dematerialization vs. Eurostat resource productivity; operator corrected; decoupling depends on phi_r (EU fit 0.66: none; DE 0.15: holds), BR-011; E5 wired 2026-10-13 23:26:24 +02:00
test_run_checkpoint.py ASSEMBLY-WP-0017 finished: IMM filter on observed US data (B3 through mid-2026, B3→B4 flip candidate Q3 2026, not confirmed), robustness, checkpoint pointer; residual to WP-0015-T07 2026-10-13 22:41:08 +02:00

README.md

Reality checkpoints

Regular comparison of the GADM adoption band and model readings with observed economic, sociological and technical data. Method: research/ScenarioBandMethod.md § 6. Workplan: ASSEMBLY-WP-0010.

Files

File Purpose
schedule.md phase windows; every run checks it first
PLAYBOOK.md step-by-step instructions for the executing agent
IndicatorCatalog.md indicators, jurisdictions, sources, mapping to model quantities
predictions.md append-only register of pre-registered predictions
YYYY/YYYY-MM-DD-<kind>.md one record per checkpoint run

Protocol

  1. Window check. Is today inside an active window in schedule.md for this kind? If not, record an out-of-window no-op and stop.
  2. Collect. Gather the indicators for this kind from IndicatorCatalog.md: light = adoption, investment and sentiment indicators; full = all catalog sections. Use the most recent published value, and record value, unit, reference period, publication date and source URL. Never invent a value: if it isn't found, record not found and the sources tried.
  3. Compare. For every indicator with an entry in predictions.md, locate the observation in the band (which anchor B1–B4 it tracks), and mark it inside or outside the band. Indicators without a registered prediction are recorded as observations only.
  4. Assess. Short notes per jurisdiction: which archetype and band anchor reality currently tracks, notable legislation or sentiment changes, and surprises.
  5. Record. Write checkpoints/YYYY/YYYY-MM-DD-<kind>.md from the template in PLAYBOOK.md. Append the observations to the matching entries in predictions.md. Never edit earlier predictions or observations.
  6. No silent re-tuning. Model changes suggested by a checkpoint become an intake (intakes/intakes.md) or a workplan task. Parameter changes go through models/ParameterGrounding.md.
  7. Complete. Commit and push, then post a State Hub progress event with event_type: assembly_checkpoint and detail: repo, date, kind, path, in_band, out_of_band, not_found.