Files
codebase-memory-mcp/graph-ui/verification/w6/evalcheck.json
T
Martin VogelandBernhard Jackiewicz 722a2424db docs(ui): CodeAtlasWeb proof artifacts, verbatim
The recorded proof runs of CodeAtlasWeb at 1825f9c850ac794066e02606012508b9d393c6aa:
screenshots, contact sheets, two screen recordings and the JSON reports
of every cycle's smoke run, gate run and audit (227 files, 65 MB).
Bernhard Jackiewicz's work, imported unchanged.

They sit in their own commit on purpose: his frozen acceptance checks
read them (tests/scaffold), his help page points readers at them, and
the maintainer may still decide to keep this history out of the public
tree. Dropping this commit removes exactly the artifacts and nothing
else; the four acceptance checks that bind the report to his
repository's own commits are not part of the CI gate either way.

Co-authored-by: Bernhard Jackiewicz <bj@techport.io>
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
2026-09-05 20:38:59 +02:00

2379 lines
61 KiB
JSON

{
"evalCheckPass": true,
"reasons": [],
"temperature": 0,
"seed": 42,
"questionCount": 44,
"modelsRun": 2,
"passRateTolerance": 0.05,
"bounds": {
"passRate": 0.6,
"citationCompliance": 0.9,
"appliesTo": "der Sieger JEDER Modellklasse, nicht das Feld im Schnitt",
"source": "docs/adr/0001-modellwahl.md (Abschnitt Entscheidung), tests/scaffold/w5b.test.mjs Zeilen 51 und 53, PLAN.md Abschnitt 5"
},
"baselineFile": "verification/w5/eval.json",
"comparisons": [
{
"modelClass": "A",
"name": "Qwen3.5-2B",
"recordedPassRate": 0.682,
"measuredPassRate": 0.682,
"passRateDelta": 0,
"improved": false,
"recordedCitation": 0.932,
"measuredCitation": 0.932,
"citationBound": 0.9,
"withinTolerance": true,
"reasons": []
},
{
"modelClass": "B",
"name": "gemma-4-E4B",
"recordedPassRate": 0.841,
"measuredPassRate": 0.841,
"passRateDelta": 0,
"improved": false,
"recordedCitation": 1,
"measuredCitation": 1,
"citationBound": 0.9,
"withinTolerance": true,
"reasons": []
}
],
"measured": [
{
"modelClass": "A",
"name": "Qwen3.5-2B",
"file": "Qwen3.5-2B-Q4_K_M.gguf",
"contextTokens": 3072,
"quantisation": "Q4_K - Medium",
"port": 4400,
"readyMs": 20923,
"questions": 44,
"passRate": 0.682,
"citationCompliance": 0.932,
"citationMeasured": 44,
"citationUnmeasured": 0,
"meanTokPerSec": 86.236,
"failedQuestions": [
"who-01-de",
"what-04-en",
"what-05-de",
"what-08-en",
"what-09-de",
"what-10-en",
"err-05-de",
"err-06-en",
"if-01-de",
"if-02-en",
"if-06-en",
"entry-03-de",
"entry-04-en",
"cmp-02-en"
],
"totalMs": 53763
},
{
"modelClass": "B",
"name": "gemma-4-E4B",
"file": "gemma-4-E4B-it-Q4_K_M.gguf",
"contextTokens": 8192,
"quantisation": "Q4_K - Medium",
"port": 4400,
"readyMs": 3224,
"questions": 44,
"passRate": 0.841,
"citationCompliance": 1,
"citationMeasured": 44,
"citationUnmeasured": 0,
"meanTokPerSec": 32.074,
"failedQuestions": [
"what-01-de",
"what-07-de",
"what-08-en",
"err-05-de",
"entry-03-de",
"entry-04-en",
"cmp-04-en"
],
"totalMs": 53873
}
],
"leftoverProcesses": 0,
"leftoverPortsChecked": [
4360,
4400,
4400
],
"sidecarPort": {
"port": 4141,
"sockets": 2,
"usedByThisRun": false,
"affectsResult": false,
"note": "Der Produktport. Dieser Lauf startet dort nichts und beendet dort nichts. Die Zahl zaehlt jeden Prozess mit einem Socket auf dem Port, Server wie Client (lsof -ti), und beschreibt den Rechner, nicht diesen Lauf."
},
"method": "Nur die zwei in verification/w5/eval.json aufgezeichneten Klassensieger, alle Fragen aus eval/questions.json, dieselben Karten aus dem Produkt-Compiler, Temperatur 0 und Seed 42 (beides in src/chat/chat-client.ts). Verglichen wird die Trefferquote gegen die Aufzeichnung mit Toleranz 0.05 und die Zitattreue hart gegen die Grenze 0.9. Eine GESTIEGENE Trefferquote ist kein Fehler.",
"generatedAt": "2026-08-31T13:55:50.886Z",
"totalMs": 125004,
"error": null,
"extras": {
"leftovers": [
{
"port": 4360,
"listeners": 0
},
{
"port": 4400,
"listeners": 0
},
{
"port": 4400,
"listeners": 0
}
],
"perQuestion": [
{
"name": "Qwen3.5-2B",
"results": [
{
"id": "who-01-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K3",
"K1",
"K4",
"K5",
"K6",
"K7",
"K8",
"K9",
"K10",
"K11"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"registerUserRoutes"
],
"forbiddenHits": [],
"answerChars": 122,
"tokensPerSecond": 63.246
},
{
"id": "who-02-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K4",
"K5"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 210,
"tokensPerSecond": 91.275
},
{
"id": "who-03-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K4",
"K5"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 60,
"tokensPerSecond": 72.674
},
{
"id": "who-04-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K3",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 103,
"tokensPerSecond": 85.011
},
{
"id": "who-05-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 167,
"tokensPerSecond": 93.06
},
{
"id": "who-06-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 103,
"tokensPerSecond": 84.599
},
{
"id": "who-07-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K5",
"K6"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 186,
"tokensPerSecond": 92.905
},
{
"id": "who-08-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 62,
"tokensPerSecond": 76.696
},
{
"id": "what-01-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K11",
"K5",
"K6",
"K7",
"K8"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 257,
"tokensPerSecond": 93.714
},
{
"id": "what-02-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K7"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 140,
"tokensPerSecond": 84.991
},
{
"id": "what-03-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K5"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 159,
"tokensPerSecond": 96.667
},
{
"id": "what-04-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": false,
"cited": [
"K4",
"K2"
],
"unknown": [],
"violations": [
{
"line": "No card covers it, and no other cards answer the question about what symbols hotspotScan calls.",
"reason": "no-citation"
}
],
"noCardOnly": false,
"measured": true
},
"citationOk": false,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 224,
"tokensPerSecond": 100
},
{
"id": "what-05-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K5",
"K6",
"K7"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"loadConfig",
"createApp"
],
"forbiddenHits": [],
"answerChars": 58,
"tokensPerSecond": 73.034
},
{
"id": "what-06-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K7"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 243,
"tokensPerSecond": 93.702
},
{
"id": "what-07-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 252,
"tokensPerSecond": 103.75
},
{
"id": "what-08-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"validate.ts"
],
"forbiddenHits": [],
"answerChars": 128,
"tokensPerSecond": 93.182
},
{
"id": "what-09-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": false,
"cited": [
"K1"
],
"unknown": [],
"violations": [
{
"line": "Calls `createUser` at line 41 in body order.",
"reason": "no-citation"
},
{
"line": "Calls `createUser` at line 23 via `create`.",
"reason": "no-citation"
},
{
"line": "No error type raised by `create`.",
"reason": "no-citation"
}
],
"noCardOnly": false,
"measured": true
},
"citationOk": false,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 154,
"tokensPerSecond": 94.518
},
{
"id": "what-10-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"getOrder"
],
"forbiddenHits": [],
"answerChars": 223,
"tokensPerSecond": 98.485
},
{
"id": "err-01-de",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K8",
"K9"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 76,
"tokensPerSecond": 61.503
},
{
"id": "err-02-en",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K5",
"K3"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 183,
"tokensPerSecond": 91.76
},
{
"id": "err-03-de",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K4",
"K5"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 198,
"tokensPerSecond": 93.19
},
{
"id": "err-04-en",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 29,
"tokensPerSecond": 44.643
},
{
"id": "err-05-de",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K8",
"K9"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"DB_URL"
],
"forbiddenHits": [],
"answerChars": 140,
"tokensPerSecond": 69.307
},
{
"id": "err-06-en",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [],
"unknown": [],
"violations": [],
"noCardOnly": true,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"insert"
],
"forbiddenHits": [],
"answerChars": 22,
"tokensPerSecond": 43.478
},
{
"id": "if-01-de",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K11",
"K9",
"K5"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"registerUserRoutes"
],
"forbiddenHits": [],
"answerChars": 428,
"tokensPerSecond": 99.019
},
{
"id": "if-02-en",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"registerUserRoutes"
],
"forbiddenHits": [],
"answerChars": 268,
"tokensPerSecond": 96.894
},
{
"id": "if-03-de",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 240,
"tokensPerSecond": 98.25
},
{
"id": "if-04-en",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K1",
"K3",
"K5",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 283,
"tokensPerSecond": 102.564
},
{
"id": "if-05-de",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K2",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 397,
"tokensPerSecond": 103.563
},
{
"id": "if-06-en",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K5",
"K6"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"createApp"
],
"forbiddenHits": [],
"answerChars": 449,
"tokensPerSecond": 105.442
},
{
"id": "entry-01-de",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 290,
"tokensPerSecond": 97.866
},
{
"id": "entry-02-en",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 93,
"tokensPerSecond": 58.947
},
{
"id": "entry-03-de",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"src/server.ts"
],
"forbiddenHits": [],
"answerChars": 262,
"tokensPerSecond": 96.829
},
{
"id": "entry-04-en",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": false,
"cited": [],
"unknown": [],
"violations": [
{
"line": "src/config.ts:11 loadConfig src/config.ts:20 isProduction src/repo/db.ts:17 query src/repo/db.ts:31 insert src/routes/orders.ts:8 registerOrderRoutes src/routes/users.ts:7 registerUserRoutes",
"reason": "no-citation"
}
],
"noCardOnly": false,
"measured": true
},
"citationOk": false,
"truncated": false,
"missing": [
"src/server.ts"
],
"forbiddenHits": [],
"answerChars": 190,
"tokensPerSecond": 77.713
},
{
"id": "entry-05-de",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 290,
"tokensPerSecond": 93.662
},
{
"id": "cmp-01-de",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K10",
"K4",
"K8",
"K9"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 556,
"tokensPerSecond": 108.323
},
{
"id": "cmp-02-en",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"validateId"
],
"forbiddenHits": [],
"answerChars": 265,
"tokensPerSecond": 84.848
},
{
"id": "cmp-03-de",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K3",
"K4",
"K2",
"K6"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 215,
"tokensPerSecond": 86.957
},
{
"id": "cmp-04-en",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K4",
"K3"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 177,
"tokensPerSecond": 100.45
},
{
"id": "over-01-de",
"klass": "overview",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 348,
"tokensPerSecond": 96.522
},
{
"id": "over-02-en",
"klass": "overview",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 212,
"tokensPerSecond": 86.735
},
{
"id": "over-03-de",
"klass": "overview",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 348,
"tokensPerSecond": 95.116
},
{
"id": "honest-01-de",
"klass": "other",
"deterministic": true,
"check": {
"ok": true,
"cited": [],
"unknown": [],
"violations": [],
"noCardOnly": true,
"measured": true
},
"citationOk": true,
"missing": [],
"forbiddenHits": []
},
{
"id": "honest-02-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [],
"unknown": [],
"violations": [],
"noCardOnly": true,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 18,
"tokensPerSecond": 23.077
}
]
},
{
"name": "gemma-4-E4B",
"results": [
{
"id": "who-01-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 91,
"tokensPerSecond": 18.409
},
{
"id": "who-02-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 149,
"tokensPerSecond": 36.594
},
{
"id": "who-03-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 45,
"tokensPerSecond": 22.047
},
{
"id": "who-04-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 75,
"tokensPerSecond": 32.338
},
{
"id": "who-05-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 50,
"tokensPerSecond": 22.631
},
{
"id": "who-06-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 114,
"tokensPerSecond": 37.333
},
{
"id": "who-07-de",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 50,
"tokensPerSecond": 22.695
},
{
"id": "who-08-en",
"klass": "who-calls",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 57,
"tokensPerSecond": 31.847
},
{
"id": "what-01-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"insert"
],
"forbiddenHits": [],
"answerChars": 147,
"tokensPerSecond": 29.094
},
{
"id": "what-02-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K7",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 89,
"tokensPerSecond": 32.895
},
{
"id": "what-03-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K2",
"K5",
"K6"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 195,
"tokensPerSecond": 43.632
},
{
"id": "what-04-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 77,
"tokensPerSecond": 36.446
},
{
"id": "what-05-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K5",
"K7",
"K6"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 74,
"tokensPerSecond": 30.414
},
{
"id": "what-06-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K5",
"K6",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 196,
"tokensPerSecond": 42.459
},
{
"id": "what-07-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"loadConfig"
],
"forbiddenHits": [],
"answerChars": 23,
"tokensPerSecond": 24.164
},
{
"id": "what-08-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"validate.ts"
],
"forbiddenHits": [],
"answerChars": 73,
"tokensPerSecond": 33.422
},
{
"id": "what-09-de",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K4",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 76,
"tokensPerSecond": 30.837
},
{
"id": "what-10-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K5",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 152,
"tokensPerSecond": 41.009
},
{
"id": "err-01-de",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K8"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 87,
"tokensPerSecond": 19.979
},
{
"id": "err-02-en",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 44,
"tokensPerSecond": 17.889
},
{
"id": "err-03-de",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 83,
"tokensPerSecond": 27.397
},
{
"id": "err-04-en",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 41,
"tokensPerSecond": 16.722
},
{
"id": "err-05-de",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K8"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"DB_URL"
],
"forbiddenHits": [],
"answerChars": 91,
"tokensPerSecond": 21.234
},
{
"id": "err-06-en",
"klass": "why-error",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 89,
"tokensPerSecond": 33.257
},
{
"id": "if-01-de",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 91,
"tokensPerSecond": 25.294
},
{
"id": "if-02-en",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 149,
"tokensPerSecond": 36.458
},
{
"id": "if-03-de",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 114,
"tokensPerSecond": 37.07
},
{
"id": "if-04-en",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 45,
"tokensPerSecond": 22.436
},
{
"id": "if-05-de",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 75,
"tokensPerSecond": 27.083
},
{
"id": "if-06-en",
"klass": "what-if",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K6",
"K5"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 131,
"tokensPerSecond": 33.79
},
{
"id": "entry-01-de",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 97,
"tokensPerSecond": 27.697
},
{
"id": "entry-02-en",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 97,
"tokensPerSecond": 48.223
},
{
"id": "entry-03-de",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"src/server.ts"
],
"forbiddenHits": [],
"answerChars": 299,
"tokensPerSecond": 53.657
},
{
"id": "entry-04-en",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"src/server.ts"
],
"forbiddenHits": [],
"answerChars": 299,
"tokensPerSecond": 53.756
},
{
"id": "entry-05-de",
"klass": "where-entry",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K6"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 142,
"tokensPerSecond": 28.233
},
{
"id": "cmp-01-de",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K3",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 173,
"tokensPerSecond": 30.112
},
{
"id": "cmp-02-en",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K6",
"K7",
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 148,
"tokensPerSecond": 32.527
},
{
"id": "cmp-03-de",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2",
"K3",
"K4"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 216,
"tokensPerSecond": 36.113
},
{
"id": "cmp-04-en",
"klass": "compare",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K1"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [
"query"
],
"forbiddenHits": [],
"answerChars": 75,
"tokensPerSecond": 34.82
},
{
"id": "over-01-de",
"klass": "overview",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 226,
"tokensPerSecond": 37.255
},
{
"id": "over-02-en",
"klass": "overview",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 226,
"tokensPerSecond": 51.63
},
{
"id": "over-03-de",
"klass": "overview",
"deterministic": false,
"check": {
"ok": true,
"cited": [
"K2"
],
"unknown": [],
"violations": [],
"noCardOnly": false,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 184,
"tokensPerSecond": 50.874
},
{
"id": "honest-01-de",
"klass": "other",
"deterministic": true,
"check": {
"ok": true,
"cited": [],
"unknown": [],
"violations": [],
"noCardOnly": true,
"measured": true
},
"citationOk": true,
"missing": [],
"forbiddenHits": []
},
{
"id": "honest-02-en",
"klass": "what-is",
"deterministic": false,
"check": {
"ok": true,
"cited": [],
"unknown": [],
"violations": [],
"noCardOnly": true,
"measured": true
},
"citationOk": true,
"truncated": false,
"missing": [],
"forbiddenHits": [],
"answerChars": 17,
"tokensPerSecond": 7.396
}
]
}
],
"baseline": {
"generatedAt": "2026-08-29T00:15:39.440Z",
"temperature": 0,
"seed": 42,
"questionCount": 44
},
"indexed": {
"nodes": 76,
"edges": 179
},
"compilerModules": 23,
"classes": [
{
"id": "who-01-de",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "who-02-en",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "who-03-de",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "who-04-en",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "who-05-de",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "who-06-en",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "who-07-de",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "who-08-en",
"declared": "who-calls",
"compiled": "who-calls"
},
{
"id": "what-01-de",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-02-en",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-03-de",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-04-en",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-05-de",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-06-en",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-07-de",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-08-en",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-09-de",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "what-10-en",
"declared": "what-is",
"compiled": "what-is"
},
{
"id": "err-01-de",
"declared": "why-error",
"compiled": "why-error"
},
{
"id": "err-02-en",
"declared": "why-error",
"compiled": "why-error"
},
{
"id": "err-03-de",
"declared": "why-error",
"compiled": "why-error"
},
{
"id": "err-04-en",
"declared": "why-error",
"compiled": "why-error"
},
{
"id": "err-05-de",
"declared": "why-error",
"compiled": "why-error"
},
{
"id": "err-06-en",
"declared": "why-error",
"compiled": "why-error"
},
{
"id": "if-01-de",
"declared": "what-if",
"compiled": "what-if"
},
{
"id": "if-02-en",
"declared": "what-if",
"compiled": "what-if"
},
{
"id": "if-03-de",
"declared": "what-if",
"compiled": "what-if"
},
{
"id": "if-04-en",
"declared": "what-if",
"compiled": "what-if"
},
{
"id": "if-05-de",
"declared": "what-if",
"compiled": "what-if"
},
{
"id": "if-06-en",
"declared": "what-if",
"compiled": "what-if"
},
{
"id": "entry-01-de",
"declared": "where-entry",
"compiled": "where-entry"
},
{
"id": "entry-02-en",
"declared": "where-entry",
"compiled": "where-entry"
},
{
"id": "entry-03-de",
"declared": "where-entry",
"compiled": "where-entry"
},
{
"id": "entry-04-en",
"declared": "where-entry",
"compiled": "where-entry"
},
{
"id": "entry-05-de",
"declared": "where-entry",
"compiled": "where-entry"
},
{
"id": "cmp-01-de",
"declared": "compare",
"compiled": "compare"
},
{
"id": "cmp-02-en",
"declared": "compare",
"compiled": "compare"
},
{
"id": "cmp-03-de",
"declared": "compare",
"compiled": "compare"
},
{
"id": "cmp-04-en",
"declared": "compare",
"compiled": "compare"
},
{
"id": "over-01-de",
"declared": "overview",
"compiled": "overview"
},
{
"id": "over-02-en",
"declared": "overview",
"compiled": "overview"
},
{
"id": "over-03-de",
"declared": "overview",
"compiled": "overview"
},
{
"id": "honest-01-de",
"declared": "other",
"compiled": "other"
},
{
"id": "honest-02-en",
"declared": "what-is",
"compiled": "what-is"
}
],
"classDrift": []
}
}