An evidence-review system must allocate additional model judgments and control their use. We study these software decisions on 6,164 frozen manufacturing source-task pairs. Benefit-targeted routing learns recovered agreement minus newly introduced disagreement. On the original 300-case test, 60 consultations yield 202/231 agreements with two human references versus 189/218 for a logistic-risk router. An additional 300 cases were independently annotated twice using equal frozen evidence. Without retraining the historical policies, the corresponding counts are 164/190 versus 163/193; the differences do not resolve an advantage. Strict scalar-Ridge controls share preprocessing, regularization and fitting, and remain inconclusive. Quotation and requested-state replacement gates retain rejected cases and budget costs; their joint gate rejects one original and two additional consultations without changing primary outcomes. Evidence ablations, fusion and bounded updates supply further controls. A completed 200-pair identity audit yields 97.45 percent weighted merge precision after eight author adjudications. This audits a provisional map, while prospective company-disjoint performance remains untested.
Figures & tables
Policy
Attempts
Valid
H1 G/L
H2 G/L
GPT only
0
0
0/0
0/0
Random expectation
60
56.4
6.6/3.2
6.0/4.2
A/B disagreement
60
54
11/6
12/5
Unclear first
60
57
13/6
15/5
Risk, logistic
60
57
9/8
10/8
Benefit, Ridge
60
56
17/3
18/3
Table 1: Fixed-response routing on all 300 cases. G/L: gained/lost reference agreements. Random rows are exact count expectations. † marks the later exploratory estimator-family controls.
Policy
J1
J2
Unchanged GPT ( B=0 )
161
190
Frozen risk, logistic
163
193
Frozen benefit, Ridge
164
190
Frozen risk, Ridge
165
193
Frozen benefit, logistic
160
188
Common-Ridge risk
166
194
Table 2: Additional 300 cases: concordant primary labels at B=60 . J1/J2 are the separate new human references. Common Ridge uses shared α=1 . No test-dependent refitting.
Representation
H1 F1
H2 F1
H1/H2 @60
T only
.2971
.3410
29/29
Title + description + T
.3445
.3927
29/30
Excerpt + T
.3230
.3691
31/32
Full text + T
.3366
.3827
30/31
Full text, without T
.3922
.4600
33/34
Full sparse TF-IDF + T
.3146
.3582
32/33
Table 3: Evidence ablations: three-class macro-F1 against original references; positives among the highest 60 positive scores. T denotes capability/state indicators.
Macro-F1
D@60
Method
H1
H2
H1
H2
Learned GPT strong
.6037
.6488
36
38
Learned GPT + GLM
.6206
.6888
34
35
Table 4: Post-consultation comparison on all 300 cases. F1: primary classification; D@60: human-reference disagreements with unchanged final GPT found by separately trained risk models. Unavailable fusion inputs retain matched GPT baseline outputs.
Large language model routing selects models, tools, experts, or inference strategies to balance answer quality, cost, latency, and deployment constraints.