trading-system-docs/tolaria/c4b-search-service/test_corpus_v1.1.json

370 lines
No EOL
11 KiB
JSON

{
"schema": "tolaria-c4a-ground-truth-v1.1",
"source_of_truth": "Forgejo clone HEAD=35446c0 (MIGRATED=81, DEFERRED=1, DO_NOT_TOUCH=2, TOTAL=84)",
"ground_truth_keyed_by": "object_id",
"note": "IDs korrigiert gegen SoT-Frontmatter (Forgejo HEAD). v1.0 bleibt als Evidence erhalten. Semantische Intention unverändert.",
"corpus_size": 22,
"verified_object_ids": {
"modul-09-canonical": "object/ffa8db13-8aa6-d4a4-6756-69eabd0c8d77",
"modul-09-source": "object/48bd264f-607b-15f1-5f73-3e922af9b19d",
"modul-12-canonical": "object/47b8029c-5874-e73f-0279-d335785b359a",
"modul-12-source": "object/302e9929-e186-c930-2406-ad4a8f17c6fd",
"modul-03-canonical": "object/cf54abfc-4c8b-7477-1b4f-21e76ca7b055",
"modul-03-source": "object/1761a726-55af-f97b-d509-84aa4577f102",
"modul-01-pg-canonical": "object/ebdc6b2b-4b30-c839-729b-c240ad433a60",
"modul-02-rabbitmq-canonical": "object/b909ccbc-f7cf-7f71-46ea-817f0b697d35",
"modul-15-design-canonical": "object/5f28e1fd-19f4-e5af-1c92-a17ec80b08f0",
"modul-15-impl-canonical": "object/42b89fc3-4572-b493-c05e-dfb85a639df2",
"infra-source": "object/f4e559f5-403c-f241-be50-0962d8174644",
"infra-canonical": "object/5fcf4885-a361-f49f-2164-f4e10709da34",
"historical-phase8-canonical": "object/ac1df780-019b-bb11-cb91-4edaa49e1843",
"phase10a-canonical": "object/086b7673-c183-6ca2-52fc-6f394107c9cf",
"vps-infra-standalone": "object/9bd5b7db-bb0f-ae22-3a65-9410b77ad3de"
},
"cases": [
{
"id": "c01-exact-title",
"query": "Modul-09-Execution-Service",
"mode": "exact",
"filters": {},
"expected_top": [
"object/ffa8db13-8aa6-d4a4-6756-69eabd0c8d77"
],
"expected_allowed": [
"object/48bd264f-607b-15f1-5f73-3e922af9b19d"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "Exakter Title-Treffer, canonical bevorzugt, source erlaubt, historical nicht top."
},
{
"id": "c02-keyword",
"query": "Intrabar Execution Gap Realism",
"mode": "keyword",
"filters": {},
"expected_top": [],
"expected_allowed": [
"object/47b8029c-5874-e73f-0279-d335785b359a",
"object/302e9929-e186-c930-2406-ad4a8f17c6fd"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [
"object/ac1df780-019b-bb11-cb91-4edaa49e1843"
],
"why": "modul-12 enthält Phase 10e Intrabar/Gap; historical phase8 NICHT top ohne explizit historical"
},
{
"id": "c03-phrase",
"query": "deterministischer Execution-Service",
"mode": "keyword",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/ffa8db13-8aa6-d4a4-6756-69eabd0c8d77"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "Phrase aus modul-09-Body"
},
{
"id": "c04-metadata-only",
"query": "",
"mode": "metadata",
"filters": {
"type": "arch",
"role": "module"
},
"expected_top": [],
"expected_allowed": [
"object/ebdc6b2b-4b30-c839-729b-c240ad433a60",
"object/ffa8db13-8aa6-d4a4-6756-69eabd0c8d77"
],
"expected_rep": "any",
"expected_state": "current",
"must_not_top": [
"object/f4e559f5-403c-f241-be50-0962d8174644"
],
"why": "role=module arch; reference ausgeschlossen"
},
{
"id": "c05-canonical-source-pair",
"query": "Infrastructure",
"mode": "hybrid",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/5fcf4885-a361-f49f-2164-f4e10709da34",
"object/f4e559f5-403c-f241-be50-0962d8174644"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [
"object/f4e559f5-403c-f241-be50-0962d8174644"
],
"why": "collapse: canonical bevorzugt, source zusätzlich, nie 2 unabhängige Fakten"
},
{
"id": "c06-current-historical",
"query": "M12 DatasetGate",
"mode": "keyword",
"filters": {
"include_historical": false
},
"expected_top": [],
"expected_allowed": [],
"expected_rep": "any",
"expected_state": "historical",
"must_not_top": [
"object/ac1df780-019b-bb11-cb91-4edaa49e1843"
],
"why": "historical nur bei include_historical oder niedrig gerankt"
},
{
"id": "c07-readme-explicit",
"query": "README",
"mode": "keyword",
"filters": [],
"expected_top": [
"README-root",
"README-system-docs"
],
"expected_allowed": [],
"expected_rep": "index/overview",
"expected_state": "current",
"must_not_top": [],
"why": "README su-schbar (DO_NOT_MUTATE != DO_NOT_INDEX); gezielte Query findet sie"
},
{
"id": "c08-overview-downrank",
"query": "Infrastruktur Betrieb",
"mode": "hybrid",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/5fcf4885-a361-f49f-2164-f4e10709da34",
"object/f4e559f5-403c-f241-be50-0962d8174644"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [
"README"
],
"why": "overview/index bei Fach-Query NICHT dominieren"
},
{
"id": "c09-crosslang-de-en",
"query": "Marktdaten",
"mode": "semantic",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/cf54abfc-4c8b-7477-1b4f-21e76ca7b055"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "DE-Term -> EN Object (modul-03 Market-Data)"
},
{
"id": "c10-crosslang-en-de",
"query": "market data",
"mode": "semantic",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/cf54abfc-4c8b-7477-1b4f-21e76ca7b055"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "EN->DE multilingual"
},
{
"id": "c11-semantic-paraphrase",
"query": "Wie werden Orders ausgeführt",
"mode": "semantic",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/ffa8db13-8aa6-d4a4-6756-69eabd0c8d77"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "Paraphrase Execution-Service; Semantic muss Mehrwert ggü keyword zeigen"
},
{
"id": "c12-ambiguous",
"query": "Modul 15",
"mode": "keyword",
"filters": [],
"expected_top": [
"object/5f28e1fd-19f4-e5af-1c92-a17ec80b08f0",
"object/42b89fc3-4572-b493-c05e-dfb85a639df2"
],
"expected_allowed": [],
"expected_rep": "any",
"expected_state": "current",
"must_not_top": [],
"why": "zwei Objekte (design+impl) -> collapse/group"
},
{
"id": "c13-no-result",
"query": "xyzzy-foobar-42",
"mode": "keyword",
"filters": [],
"expected_top": [],
"expected_allowed": [],
"expected_rep": "-",
"expected_state": "-",
"must_not_top": [],
"why": "kein Treffer -> leeres Ergebnis, no-result correctness"
},
{
"id": "c14-module-number",
"query": "Modul 15",
"mode": "keyword",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/5f28e1fd-19f4-e5af-1c92-a17ec80b08f0",
"object/42b89fc3-4572-b493-c05e-dfb85a639df2"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "Modulnummer-Auflösung"
},
{
"id": "c15-ticker-acronym",
"query": "OHLCV",
"mode": "keyword",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/cf54abfc-4c8b-7477-1b4f-21e76ca7b055",
"object/ebdc6b2b-4b30-c839-729b-c240ad433a60"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "Ticker/Akronym-Token"
},
{
"id": "c16-env-config-token",
"query": "POSTGRES_DB",
"mode": "keyword",
"filters": {},
"expected_top": [],
"expected_allowed": [
"object/ebdc6b2b-4b30-c839-729b-c240ad433a60"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "Env-/Config-Token via Keyword-Index; code-chunks nicht sem-embed"
},
{
"id": "c17-relationship",
"query": "ADR Modul 09",
"mode": "keyword",
"filters": {
"relation": "related_to"
},
"expected_top": [],
"expected_allowed": [
"object/ffa8db13-8aa6-d4a4-6756-69eabd0c8d77"
],
"expected_rep": "any",
"expected_state": "current",
"must_not_top": [],
"why": "Relation-Direct-Stufe (belongs_to/derived_from/related_to)"
},
{
"id": "c18-historical-explicit",
"query": "historical phase8",
"mode": "keyword",
"filters": {
"include_historical": true
},
"expected_top": [
"object/ac1df780-019b-bb11-cb91-4edaa49e1843"
],
"expected_allowed": [],
"expected_rep": "canonical",
"expected_state": "historical",
"must_not_top": [],
"why": "explizit historical -> phase8-Obj erreichbar"
},
{
"id": "c19-source-only",
"query": "source infrastructure",
"mode": "keyword",
"filters": {
"representation": "source"
},
"expected_top": [],
"expected_allowed": [
"object/f4e559f5-403c-f241-be50-0962d8174644"
],
"expected_rep": "source",
"expected_state": "current",
"must_not_top": [
"object/5fcf4885-a361-f49f-2164-f4e10709da34"
],
"why": "source-only Filter"
},
{
"id": "c20-canonical-only",
"query": "infrastructure",
"mode": "keyword",
"filters": {
"representation": "canonical"
},
"expected_top": [],
"expected_allowed": [
"object/5fcf4885-a361-f49f-2164-f4e10709da34"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [
"object/f4e559f5-403c-f241-be50-0962d8174644"
],
"why": "canonical-only Filter"
},
{
"id": "c21-config-code",
"query": "OLLAMA_API_KEY",
"mode": "keyword",
"filters": {
"type": "code"
},
"expected_top": [],
"expected_allowed": [],
"expected_rep": "-",
"expected_state": "-",
"must_not_top": [],
"why": "kein sekret-Index; pre-index scan filtert secrets"
},
{
"id": "c22-trading-term",
"query": "RabbitMQ vhost",
"mode": "hybrid",
"filters": [],
"expected_top": [],
"expected_allowed": [
"object/b909ccbc-f7cf-7f71-46ea-817f0b697d35"
],
"expected_rep": "canonical",
"expected_state": "current",
"must_not_top": [],
"why": "Trading-/Architektur-Begriff multilingual"
}
],
"corpus_version_old": "1.0",
"corpus_version_new": "1.1",
"erratum": "C4A_GROUND_TRUTH_ERRATUM.md"
}