Workflow evaluation

examples/compliance-reviewer/golden500/exec-67.harness.json scored against examples/compliance-reviewer/golden500/exec-67.harness.json · 500 records · strict mode · generated 2026-09-29T00:00:00.000Z
A record needed a person if the answer key says it should not have gone out without review.

Silent error rate
9.8%
25 of the 256 records that went out without review should have had one
The true rate on records like these is likely between 6.7% and 14.0% (95% range).
With 256 records, each one moves it by 0.4 points.
Straight-through
51.2%
went out without review
256 of 500 · likely 46.8–55.6%
Silent omissions
0.0%
blocked or suppressed, but should have gone out or to a person
0 of 500 · likely 0.0–0.8%
Review precision
89.3%
sent to a person, and needed one
218 of 244 · likely 84.8–92.6%
Safeguard failures
0
went out past the workflow's own confidence gate or floor

Silent errors

Records that went out without review, but needed a person.

RecordSeverityTypesWentAnswer keyWhat differedTrap
E38mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G012mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G033mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G036mediumSP-SHOULD-REVIEW
SP-MISSING
PASS_WITH_NOTESVIOLATIONviolations never found: SUPERLATIVEdeterministic
G039mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: STATISTIC_NO_CONTEXT, RESULTS_NO_DISCLAIMERllm
G077mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: UNVERIFIABLE_COMPARISONllm
G087mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: STATISTIC_NO_CONTEXTllm
G093mediumSP-SHOULD-REVIEW
SP-MISSING
PASS_WITH_NOTESVIOLATIONviolations never found: SUPERLATIVEdeterministic
G101mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G121mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G160mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: UNVERIFIABLE_COMPARISONllm
G201mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G225mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G252mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G262mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: IMPLIED_SUPERIORITYllm
G273mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G276mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: UNVERIFIABLE_COMPARISONllm
G341mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G368mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: RESULTS_NO_DISCLAIMERdeterministic
G383mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G385mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: UNVERIFIABLE_COMPARISONllm
G411mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G431mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
G445mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
SP-MISSING
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEW
violations never found: SUPERLATIVE
both
G457mediumSP-SHOULD-REVIEW
SP-MISSING-REJECTED
PASS_WITH_NOTESVIOLATIONviolations found, but set aside: AWARD_CLAIM_REVIEWllm
What the types mean
SP-SHOULD-REVIEW
went out, but should have gone to a person
SP-MISSING-REJECTED
the model found a correct value, but it was set aside for low confidence
SP-MISSING
a correct value was never found

Silent omissions

None.

Safeguard failures

None.

Unnecessary reviews (sent to a person, but could have gone out): G017, G026, G027, G035, G060, G062, G078, G089, G127, G131, G173, G196, G198, G199, G203, G220, G222, G314, G342, G351, G363, G378, G409, G410, G437, G456

Output quality

498 records; left out: G145 (model failed), G224 (model failed). Precision: of the values the workflow applied, the share the answer key lists. Recall: of the values the answer key lists, the share the workflow applied. F1 balances the two (1 is perfect). A value the workflow found but set aside does not count as applied.

OutputPrecisionRecallF1Exact matchTP / FP / FN
violations67.7%78.2%0.72670.3%279 / 133 / 78

Per trap

A trap is a record built to provoke one kind of mistake. Each row shows how the records of one trap were handled.

TrapRecordsRouted rightSilent errorsOmissionsUnnecessary reviews
both5857 of 58G445nonenone
deterministic8279 of 82G036, G093, G368nonenone
llm10382 of 103E38, G012, G033, G039, G077, G087, G101, G121, G160, G201, G225, G252, G262, G273, G276, G341, G383, G385, G411, G431, G457nonenone
none257231 of 257nonenoneG017, G026, G027, G035, G060, G062, G078, G089, G127, G131, G173, G196, G198, G199, G203, G220, G222, G314, G342, G351, G363, G378, G409, G410, G437, G456

Calibration

Does a stated confidence mean what it says? 430 claims, groups of 0.1. Average gap 0.385 (0 is perfectly calibrated). The grey diagonal is where stated equals actual; a dot above it was right more often than stated, below it less often. Each thin line is the likely range (95%) for that dot.

0%20%40%60%80%100%0.50.60.70.80.91.0stated confidenceactually right
StatedClaimsRightAccuracyGapLikely range
0.50–0.60700.0%-0.550.0–35.4%
0.60–0.7036513.9%-0.496.1–28.7%
0.70–0.80772633.8%-0.4124.2–44.9%
0.80–0.901766637.5%-0.4730.7–44.8%
0.90–1.001349570.9%-0.2262.7–77.9%

Every record

RecordWentAnswer keyNeeded a personOutcomeTrap
E01BLOCKVIOLATIONyesokdeterministic
E02BLOCKVIOLATIONyesokdeterministic
E03BLOCKVIOLATIONyesokdeterministic
E04BLOCKVIOLATIONyesokdeterministic
E05BLOCKVIOLATIONyesokdeterministic
E06BLOCKVIOLATIONyesokdeterministic
E07BLOCKVIOLATIONyesokdeterministic
E08BLOCKVIOLATIONyesokboth
E09BLOCKVIOLATIONyesokdeterministic
E10BLOCKVIOLATIONyesokdeterministic
E11BLOCKVIOLATIONyesokdeterministic
E12REVIEW_REQUIREDVIOLATIONyesokdeterministic
E13REVIEW_REQUIREDVIOLATIONyesokdeterministic
E14PASSCLEANnooknone
E15REVIEW_REQUIREDVIOLATIONyesokllm
E16REVIEW_REQUIREDVIOLATIONyesokllm
E17REVIEW_REQUIREDVIOLATIONyesokllm
E18REVIEW_REQUIREDVIOLATIONyesokllm
E19REVIEW_REQUIREDVIOLATIONyesokllm
E20REVIEW_REQUIREDVIOLATIONyesokllm
E21REVIEW_REQUIREDVIOLATIONyesokllm
E22REVIEW_REQUIREDVIOLATIONyesokllm
E23REVIEW_REQUIREDVIOLATIONyesokllm
E24PASSCLEANnooknone
E25BLOCKVIOLATIONyesokdeterministic
E26BLOCKVIOLATIONyesokdeterministic
E27PASSCLEANnooknone
E28PASSCLEANnooknone
E29PASSCLEANnooknone
E30PASSCLEANnooknone
E31PASSCLEANnooknone
E32PASSCLEANnooknone
E33PASSCLEANnooknone
E34PASSCLEANnooknone
E35PASSCLEANnooknone
E36PASSCLEANnooknone
E37PASSCLEANnooknone
E38PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
E39REVIEW_REQUIREDVIOLATIONyesokllm
E40PASSCLEANnooknone
G001BLOCKVIOLATIONyesokdeterministic
G002BLOCKVIOLATIONyesokboth
G003PASSCLEANnooknone
G004REVIEW_REQUIREDVIOLATIONyesokboth
G005PASSCLEANnooknone
G006REVIEW_REQUIREDVIOLATIONyesokllm
G007PASSCLEANnooknone
G008PASSCLEANnooknone
G009PASSCLEANnooknone
G010PASSCLEANnooknone
G011REVIEW_REQUIREDVIOLATIONyesokdeterministic
G012PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G013PASS_WITH_NOTESCLEANnooknone
G014PASSCLEANnooknone
G015REVIEW_REQUIREDVIOLATIONyesokllm
G016BLOCKVIOLATIONyesokdeterministic
G017BLOCKCLEANnounnecessary reviewnone
G018REVIEW_REQUIREDVIOLATIONyesokboth
G019PASSCLEANnooknone
G020BLOCKVIOLATIONyesokllm
G021REVIEW_REQUIREDVIOLATIONyesokdeterministic
G022PASSCLEANnooknone
G023PASS_WITH_NOTESCLEANnooknone
G024PASSCLEANnooknone
G025PASSCLEANnooknone
G026BLOCKCLEANnounnecessary reviewnone
G027REVIEW_REQUIREDCLEANnounnecessary reviewnone
G028REVIEW_REQUIREDVIOLATIONyesokllm
G029PASSCLEANnooknone
G030BLOCKVIOLATIONyesokboth
G031PASSCLEANnooknone
G032PASSCLEANnooknone
G033PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G034PASSCLEANnooknone
G035BLOCKCLEANnounnecessary reviewnone
G036PASS_WITH_NOTESVIOLATIONyesmedium silent errordeterministic
G037PASSCLEANnooknone
G038BLOCKVIOLATIONyesokdeterministic
G039PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G040PASSCLEANnooknone
G041BLOCKVIOLATIONyesokboth
G042PASSCLEANnooknone
G043REVIEW_REQUIREDVIOLATIONyesokllm
G044PASS_WITH_NOTESCLEANnooknone
G045PASSCLEANnooknone
G046BLOCKVIOLATIONyesokboth
G047PASSCLEANnooknone
G048PASSCLEANnooknone
G049BLOCKVIOLATIONyesokdeterministic
G050REVIEW_REQUIREDVIOLATIONyesokllm
G051PASSCLEANnooknone
G052PASSCLEANnooknone
G053REVIEW_REQUIREDVIOLATIONyesokboth
G054PASSCLEANnooknone
G055PASSCLEANnooknone
G056PASSCLEANnooknone
G057BLOCKVIOLATIONyesokllm
G058PASSCLEANnooknone
G059BLOCKVIOLATIONyesokdeterministic
G060BLOCKCLEANnounnecessary reviewnone
G061REVIEW_REQUIREDVIOLATIONyesokllm
G062BLOCKCLEANnounnecessary reviewnone
G063PASSCLEANnooknone
G064BLOCKVIOLATIONyesokboth
G065PASS_WITH_NOTESCLEANnooknone
G066BLOCKVIOLATIONyesokboth
G067PASSCLEANnooknone
G068REVIEW_REQUIREDVIOLATIONyesokllm
G069REVIEW_REQUIREDVIOLATIONyesokdeterministic
G070PASSCLEANnooknone
G071PASSCLEANnooknone
G072BLOCKVIOLATIONyesokdeterministic
G073BLOCKVIOLATIONyesokboth
G074PASSCLEANnooknone
G075BLOCKVIOLATIONyesokboth
G076PASSCLEANnooknone
G077PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G078REVIEW_REQUIREDCLEANnounnecessary reviewnone
G079BLOCKVIOLATIONyesokdeterministic
G080REVIEW_REQUIREDVIOLATIONyesokllm
G081BLOCKVIOLATIONyesokdeterministic
G082PASSCLEANnooknone
G083REVIEW_REQUIREDVIOLATIONyesokllm
G084REVIEW_REQUIREDVIOLATIONyesokdeterministic
G085PASS_WITH_NOTESCLEANnooknone
G086PASSCLEANnooknone
G087PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G088PASSCLEANnooknone
G089REVIEW_REQUIREDCLEANnounnecessary reviewnone
G090PASSCLEANnooknone
G091BLOCKVIOLATIONyesokboth
G092PASSCLEANnooknone
G093PASS_WITH_NOTESVIOLATIONyesmedium silent errordeterministic
G094PASSCLEANnooknone
G095REVIEW_REQUIREDVIOLATIONyesokllm
G096PASSCLEANnooknone
G097BLOCKVIOLATIONyesokdeterministic
G098REVIEW_REQUIREDVIOLATIONyesokllm
G099PASSCLEANnooknone
G100BLOCKVIOLATIONyesokdeterministic
G101PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G102PASS_WITH_NOTESCLEANnooknone
G103BLOCKVIOLATIONyesokboth
G104REVIEW_REQUIREDVIOLATIONyesokllm
G105PASSCLEANnooknone
G106REVIEW_REQUIREDVIOLATIONyesokdeterministic
G107PASSCLEANnooknone
G108REVIEW_REQUIREDVIOLATIONyesokllm
G109PASSCLEANnooknone
G110PASSCLEANnooknone
G111REVIEW_REQUIREDVIOLATIONyesokllm
G112BLOCKVIOLATIONyesokboth
G113PASSCLEANnooknone
G114REVIEW_REQUIREDVIOLATIONyesokllm
G115PASSCLEANnooknone
G116PASSCLEANnooknone
G117BLOCKVIOLATIONyesokdeterministic
G118REVIEW_REQUIREDVIOLATIONyesokllm
G119REVIEW_REQUIREDVIOLATIONyesokboth
G120PASS_WITH_NOTESCLEANnooknone
G121PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G122PASS_WITH_NOTESCLEANnooknone
G123REVIEW_REQUIREDVIOLATIONyesokllm
G124BLOCKVIOLATIONyesokdeterministic
G125REVIEW_REQUIREDVIOLATIONyesokdeterministic
G126PASSCLEANnooknone
G127BLOCKCLEANnounnecessary reviewnone
G128PASSCLEANnooknone
G129PASS_WITH_NOTESCLEANnooknone
G130BLOCKVIOLATIONyesokdeterministic
G131BLOCKCLEANnounnecessary reviewnone
G132REVIEW_REQUIREDVIOLATIONyesokllm
G133PASS_WITH_NOTESCLEANnooknone
G134BLOCKVIOLATIONyesokboth
G135BLOCKVIOLATIONyesokllm
G136PASSCLEANnooknone
G137REVIEW_REQUIREDVIOLATIONyesokllm
G138PASSCLEANnooknone
G139REVIEW_REQUIREDVIOLATIONyesokdeterministic
G140PASSCLEANnooknone
G141REVIEW_REQUIREDVIOLATIONyesokllm
G142BLOCKVIOLATIONyesokdeterministic
G143PASSCLEANnooknone
G144REVIEW_REQUIREDVIOLATIONyesokllm
G145REVIEW_REQUIREDVIOLATIONyesokllm
G146PASSCLEANnooknone
G147REVIEW_REQUIREDVIOLATIONyesokllm
G148PASS_WITH_NOTESCLEANnooknone
G149BLOCKVIOLATIONyesokboth
G150PASS_WITH_NOTESCLEANnooknone
G151PASSCLEANnooknone
G152PASSCLEANnooknone
G153PASSCLEANnooknone
G154BLOCKVIOLATIONyesokdeterministic
G155BLOCKVIOLATIONyesokboth
G156REVIEW_REQUIREDVIOLATIONyesokllm
G157REVIEW_REQUIREDVIOLATIONyesokdeterministic
G158PASS_WITH_NOTESCLEANnooknone
G159BLOCKVIOLATIONyesokdeterministic
G160PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G161PASSCLEANnooknone
G162REVIEW_REQUIREDVIOLATIONyesokboth
G163BLOCKVIOLATIONyesokdeterministic
G164PASSCLEANnooknone
G165PASSCLEANnooknone
G166REVIEW_REQUIREDVIOLATIONyesokllm
G167BLOCKVIOLATIONyesokboth
G168PASS_WITH_NOTESCLEANnooknone
G169PASSCLEANnooknone
G170REVIEW_REQUIREDVIOLATIONyesokdeterministic
G171REVIEW_REQUIREDVIOLATIONyesokboth
G172PASSCLEANnooknone
G173REVIEW_REQUIREDCLEANnounnecessary reviewnone
G174PASSCLEANnooknone
G175PASSCLEANnooknone
G176BLOCKVIOLATIONyesokdeterministic
G177PASSCLEANnooknone
G178BLOCKVIOLATIONyesokboth
G179BLOCKVIOLATIONyesokdeterministic
G180PASSCLEANnooknone
G181REVIEW_REQUIREDVIOLATIONyesokllm
G182REVIEW_REQUIREDVIOLATIONyesokllm
G183PASSCLEANnooknone
G184REVIEW_REQUIREDVIOLATIONyesokboth
G185PASSCLEANnooknone
G186PASSCLEANnooknone
G187PASSCLEANnooknone
G188PASSCLEANnooknone
G189BLOCKVIOLATIONyesokdeterministic
G190BLOCKVIOLATIONyesokllm
G191REVIEW_REQUIREDVIOLATIONyesokllm
G192REVIEW_REQUIREDVIOLATIONyesokllm
G193PASSCLEANnooknone
G194BLOCKVIOLATIONyesokdeterministic
G195PASSCLEANnooknone
G196REVIEW_REQUIREDCLEANnounnecessary reviewnone
G197PASSCLEANnooknone
G198REVIEW_REQUIREDCLEANnounnecessary reviewnone
G199REVIEW_REQUIREDCLEANnounnecessary reviewnone
G200PASSCLEANnooknone
G201PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G202BLOCKVIOLATIONyesokboth
G203BLOCKCLEANnounnecessary reviewnone
G204REVIEW_REQUIREDVIOLATIONyesokllm
G205BLOCKVIOLATIONyesokboth
G206PASS_WITH_NOTESCLEANnooknone
G207PASSCLEANnooknone
G208PASS_WITH_NOTESCLEANnooknone
G209PASSCLEANnooknone
G210PASSCLEANnooknone
G211REVIEW_REQUIREDVIOLATIONyesokboth
G212PASS_WITH_NOTESCLEANnooknone
G213PASSCLEANnooknone
G214BLOCKVIOLATIONyesokboth
G215PASSCLEANnooknone
G216REVIEW_REQUIREDVIOLATIONyesokllm
G217PASSCLEANnooknone
G218PASSCLEANnooknone
G219PASSCLEANnooknone
G220REVIEW_REQUIREDCLEANnounnecessary reviewnone
G221PASSCLEANnooknone
G222BLOCKCLEANnounnecessary reviewnone
G223BLOCKVIOLATIONyesokdeterministic
G224REVIEW_REQUIREDVIOLATIONyesokdeterministic
G225PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G226PASSCLEANnooknone
G227PASSCLEANnooknone
G228REVIEW_REQUIREDVIOLATIONyesokllm
G229REVIEW_REQUIREDVIOLATIONyesokboth
G230PASSCLEANnooknone
G231PASSCLEANnooknone
G232PASSCLEANnooknone
G233PASSCLEANnooknone
G234PASSCLEANnooknone
G235REVIEW_REQUIREDVIOLATIONyesokllm
G236REVIEW_REQUIREDVIOLATIONyesokdeterministic
G237REVIEW_REQUIREDVIOLATIONyesokllm
G238BLOCKVIOLATIONyesokboth
G239PASSCLEANnooknone
G240PASSCLEANnooknone
G241PASS_WITH_NOTESCLEANnooknone
G242PASSCLEANnooknone
G243PASSCLEANnooknone
G244PASS_WITH_NOTESCLEANnooknone
G245PASS_WITH_NOTESCLEANnooknone
G246PASSCLEANnooknone
G247BLOCKVIOLATIONyesokdeterministic
G248PASSCLEANnooknone
G249PASSCLEANnooknone
G250REVIEW_REQUIREDVIOLATIONyesokllm
G251REVIEW_REQUIREDVIOLATIONyesokdeterministic
G252PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G253PASSCLEANnooknone
G254PASSCLEANnooknone
G255PASSCLEANnooknone
G256REVIEW_REQUIREDVIOLATIONyesokdeterministic
G257BLOCKVIOLATIONyesokdeterministic
G258PASSCLEANnooknone
G259REVIEW_REQUIREDVIOLATIONyesokboth
G260REVIEW_REQUIREDVIOLATIONyesokllm
G261REVIEW_REQUIREDVIOLATIONyesokboth
G262PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G263PASSCLEANnooknone
G264PASSCLEANnooknone
G265REVIEW_REQUIREDVIOLATIONyesokboth
G266PASSCLEANnooknone
G267PASSCLEANnooknone
G268REVIEW_REQUIREDVIOLATIONyesokllm
G269BLOCKVIOLATIONyesokdeterministic
G270BLOCKVIOLATIONyesokboth
G271BLOCKVIOLATIONyesokdeterministic
G272PASSCLEANnooknone
G273PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G274PASSCLEANnooknone
G275PASSCLEANnooknone
G276PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G277PASSCLEANnooknone
G278PASSCLEANnooknone
G279PASSCLEANnooknone
G280REVIEW_REQUIREDVIOLATIONyesokllm
G281BLOCKVIOLATIONyesokdeterministic
G282PASSCLEANnooknone
G283REVIEW_REQUIREDVIOLATIONyesokboth
G284PASSCLEANnooknone
G285REVIEW_REQUIREDVIOLATIONyesokdeterministic
G286REVIEW_REQUIREDVIOLATIONyesokllm
G287PASSCLEANnooknone
G288REVIEW_REQUIREDVIOLATIONyesokllm
G289PASSCLEANnooknone
G290PASSCLEANnooknone
G291REVIEW_REQUIREDVIOLATIONyesokllm
G292PASSCLEANnooknone
G293BLOCKVIOLATIONyesokboth
G294PASSCLEANnooknone
G295REVIEW_REQUIREDVIOLATIONyesokllm
G296REVIEW_REQUIREDVIOLATIONyesokdeterministic
G297PASSCLEANnooknone
G298BLOCKVIOLATIONyesokboth
G299REVIEW_REQUIREDVIOLATIONyesokllm
G300PASSCLEANnooknone
G301PASSCLEANnooknone
G302PASSCLEANnooknone
G303BLOCKVIOLATIONyesokdeterministic
G304BLOCKVIOLATIONyesokboth
G305PASSCLEANnooknone
G306PASSCLEANnooknone
G307REVIEW_REQUIREDVIOLATIONyesokboth
G308REVIEW_REQUIREDVIOLATIONyesokllm
G309BLOCKVIOLATIONyesokllm
G310PASSCLEANnooknone
G311BLOCKVIOLATIONyesokdeterministic
G312PASSCLEANnooknone
G313PASSCLEANnooknone
G314REVIEW_REQUIREDCLEANnounnecessary reviewnone
G315PASSCLEANnooknone
G316REVIEW_REQUIREDVIOLATIONyesokllm
G317BLOCKVIOLATIONyesokdeterministic
G318BLOCKVIOLATIONyesokdeterministic
G319PASSCLEANnooknone
G320REVIEW_REQUIREDVIOLATIONyesokllm
G321PASS_WITH_NOTESCLEANnooknone
G322PASSCLEANnooknone
G323PASSCLEANnooknone
G324PASSCLEANnooknone
G325PASSCLEANnooknone
G326REVIEW_REQUIREDVIOLATIONyesokboth
G327PASSCLEANnooknone
G328PASS_WITH_NOTESCLEANnooknone
G329REVIEW_REQUIREDVIOLATIONyesokllm
G330BLOCKVIOLATIONyesokboth
G331REVIEW_REQUIREDVIOLATIONyesokdeterministic
G332PASSCLEANnooknone
G333PASSCLEANnooknone
G334REVIEW_REQUIREDVIOLATIONyesokllm
G335PASSCLEANnooknone
G336PASSCLEANnooknone
G337REVIEW_REQUIREDVIOLATIONyesokdeterministic
G338REVIEW_REQUIREDVIOLATIONyesokllm
G339BLOCKVIOLATIONyesokboth
G340PASSCLEANnooknone
G341PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G342REVIEW_REQUIREDCLEANnounnecessary reviewnone
G343REVIEW_REQUIREDVIOLATIONyesokllm
G344PASS_WITH_NOTESCLEANnooknone
G345BLOCKVIOLATIONyesokboth
G346REVIEW_REQUIREDVIOLATIONyesokboth
G347PASSCLEANnooknone
G348REVIEW_REQUIREDVIOLATIONyesokllm
G349BLOCKVIOLATIONyesokboth
G350PASSCLEANnooknone
G351REVIEW_REQUIREDCLEANnounnecessary reviewnone
G352PASSCLEANnooknone
G353REVIEW_REQUIREDVIOLATIONyesokdeterministic
G354PASSCLEANnooknone
G355PASSCLEANnooknone
G356BLOCKVIOLATIONyesokdeterministic
G357PASSCLEANnooknone
G358PASS_WITH_NOTESCLEANnooknone
G359REVIEW_REQUIREDVIOLATIONyesokboth
G360REVIEW_REQUIREDVIOLATIONyesokllm
G361PASSCLEANnooknone
G362BLOCKVIOLATIONyesokdeterministic
G363BLOCKCLEANnounnecessary reviewnone
G364BLOCKVIOLATIONyesokllm
G365PASSCLEANnooknone
G366PASSCLEANnooknone
G367PASSCLEANnooknone
G368PASS_WITH_NOTESVIOLATIONyesmedium silent errordeterministic
G369REVIEW_REQUIREDVIOLATIONyesokboth
G370PASSCLEANnooknone
G371BLOCKVIOLATIONyesokdeterministic
G372PASSCLEANnooknone
G373REVIEW_REQUIREDVIOLATIONyesokllm
G374BLOCKVIOLATIONyesokboth
G375PASSCLEANnooknone
G376REVIEW_REQUIREDVIOLATIONyesokllm
G377PASSCLEANnooknone
G378BLOCKCLEANnounnecessary reviewnone
G379PASSCLEANnooknone
G380PASSCLEANnooknone
G381REVIEW_REQUIREDVIOLATIONyesokdeterministic
G382BLOCKVIOLATIONyesokdeterministic
G383PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G384PASSCLEANnooknone
G385PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G386PASSCLEANnooknone
G387REVIEW_REQUIREDVIOLATIONyesokboth
G388PASSCLEANnooknone
G389PASSCLEANnooknone
G390BLOCKVIOLATIONyesokdeterministic
G391REVIEW_REQUIREDVIOLATIONyesokboth
G392PASSCLEANnooknone
G393BLOCKVIOLATIONyesokllm
G394BLOCKVIOLATIONyesokdeterministic
G395PASSCLEANnooknone
G396PASS_WITH_NOTESCLEANnooknone
G397REVIEW_REQUIREDVIOLATIONyesokllm
G398REVIEW_REQUIREDVIOLATIONyesokdeterministic
G399PASSCLEANnooknone
G400BLOCKVIOLATIONyesokboth
G401PASSCLEANnooknone
G402BLOCKVIOLATIONyesokboth
G403PASSCLEANnooknone
G404PASSCLEANnooknone
G405REVIEW_REQUIREDVIOLATIONyesokdeterministic
G406REVIEW_REQUIREDVIOLATIONyesokllm
G407PASS_WITH_NOTESCLEANnooknone
G408REVIEW_REQUIREDVIOLATIONyesokllm
G409BLOCKCLEANnounnecessary reviewnone
G410REVIEW_REQUIREDCLEANnounnecessary reviewnone
G411PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G412PASSCLEANnooknone
G413BLOCKVIOLATIONyesokboth
G414PASSCLEANnooknone
G415REVIEW_REQUIREDVIOLATIONyesokdeterministic
G416PASSCLEANnooknone
G417REVIEW_REQUIREDVIOLATIONyesokllm
G418REVIEW_REQUIREDVIOLATIONyesokllm
G419BLOCKVIOLATIONyesokboth
G420PASSCLEANnooknone
G421PASS_WITH_NOTESCLEANnooknone
G422PASSCLEANnooknone
G423PASSCLEANnooknone
G424REVIEW_REQUIREDVIOLATIONyesokllm
G425PASSCLEANnooknone
G426PASSCLEANnooknone
G427BLOCKVIOLATIONyesokboth
G428REVIEW_REQUIREDVIOLATIONyesokdeterministic
G429REVIEW_REQUIREDVIOLATIONyesokllm
G430PASSCLEANnooknone
G431PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G432BLOCKVIOLATIONyesokdeterministic
G433PASSCLEANnooknone
G434REVIEW_REQUIREDVIOLATIONyesokdeterministic
G435PASSCLEANnooknone
G436PASSCLEANnooknone
G437REVIEW_REQUIREDCLEANnounnecessary reviewnone
G438REVIEW_REQUIREDVIOLATIONyesokllm
G439PASSCLEANnooknone
G440PASSCLEANnooknone
G441REVIEW_REQUIREDVIOLATIONyesokdeterministic
G442PASSCLEANnooknone
G443REVIEW_REQUIREDVIOLATIONyesokboth
G444PASSCLEANnooknone
G445PASS_WITH_NOTESVIOLATIONyesmedium silent errorboth
G446PASSCLEANnooknone
G447REVIEW_REQUIREDVIOLATIONyesokllm
G448PASSCLEANnooknone
G449PASSCLEANnooknone
G450REVIEW_REQUIREDVIOLATIONyesokllm
G451BLOCKVIOLATIONyesokdeterministic
G452REVIEW_REQUIREDVIOLATIONyesokllm
G453PASSCLEANnooknone
G454REVIEW_REQUIREDVIOLATIONyesokdeterministic
G455PASSCLEANnooknone
G456REVIEW_REQUIREDCLEANnounnecessary reviewnone
G457PASS_WITH_NOTESVIOLATIONyesmedium silent errorllm
G458PASSCLEANnooknone
G459PASSCLEANnooknone
G460BLOCKVIOLATIONyesokboth

Not measured