Archived methodology
This page documents an earlier release. Its formulas, thresholds, labels, and findings are preserved for auditability but are not the current V8 public meanings. See the current methodology.
V4.3 Shadow Model Note
Status: V4.3-shadow task-weighted shadow model
Shadow publishedThis page explains release impact and readiness. It does not replace the formula spec on Methodology, the threshold detail on Appendix, the schema/download contract on Data, or the citation layer on Research.
Shadow baseline
V4.2
historical comparison basis for this shadow artifact
Required inputs ready
4/4
present locally for shadow scoring
Published task-native occupations
492
occupations currently scored with the task-native shadow model
Validation comparison
2/3
current match-or-improve gates passing
Published shadow artifacts
The shadow layer is now auditable as data, not just as a readiness note.
Shadow scores
Per-occupation task-adjusted scores and fallback status.
Comparison summary
Score deltas, band flips, and anchor-review counts versus V4.2.
Validation comparison
BLS, family, and cluster comparisons against the live baseline.
Current shadow validation deltas: cluster -0.6667, BLS -0.1808, family -0.2143.
What Changes Already Affect Users
Current live V7 keeps this separate
- Bootstrap uncertainty intervals are published on occupations in the live dataset.
- Structural risk and near-term risk are separated in the forecast layer.
- Task-primitives fields now publish weighted evidence where normalized O*NET task matches exist; sparse occupations remain explicit null.
- The release and governance surfaces now expose shadow-model readiness instead of hiding it.
- 492 occupations have published task-native shadow scores for archived comparison.
What still does not affect the headline score
- No implausible anchor label flips without written rationale: still pending review
Remaining Input Gaps
- All required local shadow-model inputs are now present.
Input Readiness
anthropic task penetration
data/raw/external/anthropic_task_penetration.csv
onet task statements
data/raw/external/onet/Task_Statements.txt
onet task ratings
data/raw/external/onet/Task_Ratings.txt
empirical mobility
data/raw/external/sg_empirical_mobility.json
Coverage Snapshot
Occupations
562
current published universe
Direct mapped
508
eligible for the direct coverage gate
Median direct matched task share
100%
current direct-coverage gate basis
Task-weighted share
88%
archived outside the live V7 headline
Promotion Gates
| Gate | Threshold | Actual | State |
|---|---|---|---|
Median matched task weight share across direct-mapped occupations This gate prevents a sparse task layer from directly changing the headline score before task matching is broadly comparable. | >= 0.6 | 1 | pass |
Experimental task-adjusted score matches or improves current validation diagnostics Requires at least 2 of 3 external checks to match or improve baseline. Current results: cluster directional accuracy 0.3333 vs 1; BLS rho -0.167 vs 0.0138; family rho -0.4633 vs -0.249. | at_least_2_of_3 | 2/3 | pass |
No implausible anchor label flips without written rationale 8/8 anchors screened; 1 candidates still need editorial sign-off. | zero_unexplained_flips | 1 | pending |
If V4.3 is eventually promoted
The intended direction is a task-weighted shadow model with effective coverage, automation-pressure, augmentation-upside, and concentration-aware net risk. Those candidate formulas are published as governance scaffolding, not live scoring rules.
effective_coverage = Σ_t w_it · exposure_t · success_t
net_risk = automation_pressure_i · (1 - λ · concentration_i) · market_modifier_i
What Must Happen Next
- Review the published shadow artifact against the current validation misses.
- Review anchor occupations and document any surprising label flips before promotion.
- Keep the current score published until the shadow model matches or improves current validation.
- Treat the empirical mobility prior as supporting evidence until a higher-granularity Singapore transition dataset exists.