Preserve corpus bytes across Git checkouts

This commit is contained in:
Nico committed 2026-10-19 23:33:57 +02:00
1 parent 26cd9d3d04
commit d280f001fc
17 files changed
+2290 -2289

No files matched your search

@@ -0,0 +1 @@
** -text
+31 -31
View File
@@ -1,31 +1,31 @@
# Kuratiertes Korpus abgelehnter LLM-Antworten
Diese fünf gezielt ausgewählten Beispiele sind auf ausdrücklichen Nutzerwunsch
langfristig und unabhängig von den vollständigen Testläufen erhalten. Sie liegen
außerhalb von service-data/trials und dessen Bereinigung. Keine vollständigen
Paketgenerationen, Datenbankdumps, Zugangsschlüssel oder Provider-HTTP-Header.
Start: [Fehleranalyse](analysis.md), dann [Fallindex](index.json).
Jedes Beispiel enthält die unveränderte vollständige Kandidatenantwort answer.txt,
den Originalcall samt Metadaten, den ursprünglichen Request, den fachlichen
Validierungskontext, die Ablehnungsnachweise und eine eigene Kurzbewertung.
Bei parsebaren Antworten liegt zusätzlich eine lesbare Darstellung vor;
maßgeblich bleiben answer.txt und call.json. Private Denkinhalte wurden nicht erfasst.
Der Kontext enthält bewusst auch Quellenverzeichnisse, Schema- und Provenienzdaten,
damit sich die bestehenden lokalen Prüfungen später nachvollziehen lassen. Nicht
alle darin genannten Rohdateien liegen bei: Dies ist keine ausführbare vollständige
Fallakte und keine portable Weiterverarbeitung des Cases. Für die beschriebenen
Parser-/Quellenklassen-/Referenzprüfungen sind die ausgewählten Kontexte vorhanden.
Der vollständige Schemastand der verwendeten Requests liegt in request.json;
zusätzliche fachliche Schema-Snapshots liegen unter schemas/.
Die Offline-Gegenproben im Bericht sind menschlich ausgewählte Experimente, keine
bereits implementierten oder als allgemein sicher freigegebenen Reparaturregeln.
Die Originalantworten wurden NICHT durch die experimentell korrigierten Versionen ersetzt.
Die bestehende Validierung bestätigt keine vollständige semantische Wahrheit.
files.sha256 bindet alle Korpusdateien mit ihren relativen Pfaden. index.json enthält
zusätzlich die Herkunft und Hashes der extrahierten Originale. Die Quellpakete werden
zum Lesen des Korpus nicht benötigt. Keine API-Anfrage und kein Tool-/SQL-Aufruf
ist zum Untersuchen dieser Beispiele erforderlich.
# Kuratiertes Korpus abgelehnter LLM-Antworten
Diese fünf gezielt ausgewählten Beispiele sind auf ausdrücklichen Nutzerwunsch
langfristig und unabhängig von den vollständigen Testläufen erhalten. Sie liegen
außerhalb von service-data/trials und dessen Bereinigung. Keine vollständigen
Paketgenerationen, Datenbankdumps, Zugangsschlüssel oder Provider-HTTP-Header.
Start: [Fehleranalyse](analysis.md), dann [Fallindex](index.json).
Jedes Beispiel enthält die unveränderte vollständige Kandidatenantwort answer.txt,
den Originalcall samt Metadaten, den ursprünglichen Request, den fachlichen
Validierungskontext, die Ablehnungsnachweise und eine eigene Kurzbewertung.
Bei parsebaren Antworten liegt zusätzlich eine lesbare Darstellung vor;
maßgeblich bleiben answer.txt und call.json. Private Denkinhalte wurden nicht erfasst.
Der Kontext enthält bewusst auch Quellenverzeichnisse, Schema- und Provenienzdaten,
damit sich die bestehenden lokalen Prüfungen später nachvollziehen lassen. Nicht
alle darin genannten Rohdateien liegen bei: Dies ist keine ausführbare vollständige
Fallakte und keine portable Weiterverarbeitung des Cases. Für die beschriebenen
Parser-/Quellenklassen-/Referenzprüfungen sind die ausgewählten Kontexte vorhanden.
Der vollständige Schemastand der verwendeten Requests liegt in request.json;
zusätzliche fachliche Schema-Snapshots liegen unter schemas/.
Die Offline-Gegenproben im Bericht sind menschlich ausgewählte Experimente, keine
bereits implementierten oder als allgemein sicher freigegebenen Reparaturregeln.
Die Originalantworten wurden NICHT durch die experimentell korrigierten Versionen ersetzt.
Die bestehende Validierung bestätigt keine vollständige semantische Wahrheit.
files.sha256 bindet alle Korpusdateien mit ihren relativen Pfaden. index.json enthält
zusätzlich die Herkunft und Hashes der extrahierten Originale. Die Quellpakete werden
zum Lesen des Korpus nicht benötigt. Keine API-Anfrage und kein Tool-/SQL-Aufruf
ist zum Untersuchen dieser Beispiele erforderlich.
+121 -121
View File
@@ -1,121 +1,121 @@
# Untersuchung verworfener Antworten – 2026-10-19
Offline-Untersuchung von BUG20 joint-planning (Generation 97) und shared-recovery
(Generation 100). Originale und Programmcode unverändert; keine API-Anfragen,
keine Recherchetools/SQL ausgeführt, keine Kandidaten in einen Case übernommen.
`index.json` enthält Call-Referenzen und Hashes; die Call-Dateien enthalten Usage zur Nachvollziehbarkeit.
## 1. Gemeinsame Interpretation: zwei beanstandete Stellen
### observed_behavior/2
Aussage: Reproduktion bestätige, dass Wolpertinger am Testort in Dun Morogh nicht
spawnen. Quellen: F0001 und O0003. F0001 ist ein strukturierter Reproduktionsfakt
`result = reproduced`, O0003 die Beobachtung „Wolpertinger spawnen tatsächlich nicht“.
Die Quelle F0001 ist in dieser Ausgabekategorie nicht zugelassen. Die Aussage hat
jedoch bereits eine passende Beobachtungsquelle. Das ist wesentlich näher an einer
redundanten, falsch einsortierten Quellenangabe als an erfundener Beobachtung.
Ein Fact-Kind allein rechtfertigt weder das Verwerfen der Aussage noch das automatische
Entfernen der Quelle: Aussage, Provenienz und verbleibende Belege müssen erhalten bleiben.
Die Ortsangabe muss im Gesamtkontext bewertet werden; O0003 nennt allein keinen Ort.
### tester_assumptions/0
Die Antwort schreibt dem Tester die Annahme zu, die Brille sei die *alleinige*
Sichtbarkeitsvoraussetzung. O0002 sagt lediglich, dass trotz getragener notwendiger
Brille keine Wolpertinger erscheinen und der Horde-Fall funktioniere. Eine explizite
Behauptung „alleinige Voraussetzung“ steht dort nicht. Das ist eine semantische
Überinterpretation, nicht nur eine falsch etikettierte Quellen-ID. Die Kategorie ist
zusätzlich formal nur für tester_assumption/tester_comment zugelassen, nicht observation.
Diese Passage darf nicht durch bloßes Umetikettieren zu einer Beobachtung werden.
### Offline-Gegenprobe
Nur im Arbeitsspeicher F0001 aus observed_behavior/2 entfernt und den unbelegten
Testerannahmen-Eintrag entfernt: Die bestehende vollständige Interpretationsvalidierung
besteht danach. Dies ist eine menschlich gewählte Gegenprobe, keine automatisch
bewiesene Reparaturregel oder semantische Vollfreigabe der Antwort.
Die drei ursprünglichen Hypothesen verweisen ausschließlich auf unveränderte Stellen:
H1 observed_behavior/1; H2 zusätzlich confirmed_technical_facts/7; H3 zusätzlich
confirmed_technical_facts/6. Keine deklarierten Verweise betreffen die beiden
beanstandeten Stellen. Nach der Gegenprobe lassen sich alle Pointer erneut auflösen
und alle drei Vorschläge bestehen die vorhandene Hypothesenvalidierung.
Das rechtfertigt die Prüfung einer abhängigkeitssensitiven Wiederverwertung statt
pauschaler Neugenerierung. Deklarierte Referenzen beweisen aber nicht, dass jede
implizite inhaltliche Abhängigkeit ausgeschlossen ist.
### Weitere qualitative Schwächen trotz formal gültiger Gegenprobe
- Eine Untersuchungsrichtung bezeichnet 32907 als Netz und 32906 als gefangenes Item,
obwohl die Entity-Einträge selbst ihre Namen/Funktion ausdrücklich als ungeprüft
ausweisen. Die zitierten Questfelder belegen die numerischen Relationen, nicht
diese Namens-/Funktionszuordnung. Das ist eine interne Inkonsistenz.
- H2 nennt für unit_flags 512 eine symbolische Bedeutung, die im bereitgestellten
Case-Kontext nicht belegt ist. Sie vermischt Nicht-Auswählbarkeit und Unsichtbarkeit.
Der allgemeine Sichtbarkeitsverdacht ist sinnvoll; die technische Zuordnung ist
so keine bestätigte Grundlage. Ein Item-Erzeugungsspell ist zudem kein Nachweis
einer bereits verifizierten Detektionsaura.
- H3 formuliert die vermutete Quest-/Phasenabhängigkeit stellenweise zu sehr als
gegebenen Mechanismus. Als ausdrücklich zu prüfende Alternative ist sie zulässig.
Die bestehenden Validatoren prüfen Struktur, Quellenklassen und Referenzen, können
aber nicht die Wahrheit oder vollständige Ableitbarkeit jedes Freitextsatzes beweisen.
## 2. Syntaxfehler der Auftragsproduktion im gemeinsamen Lauf
Eine Human-Dev-Objektklammer endet nach expected_results mit `]` statt `}`.
Eine einzige Ersetzung dieser schließenden Klammer macht die gesamte Antwort
parsebar. Danach besteht sie unverändert die bestehende vollständige
Change-Request-Validierung einschließlich des archivierten Kontexts.
Das ist der klarste Kandidat für eine lokale, durch String-/Containerzustand
abgesicherte Klammerkorrektur. Aktuell wird eine falsche schließende Klammer
noch nicht vom allgemeinen Normalisierer ersetzt.
## 3. Zwei beschädigte Hypothesenantworten im vorigen Lauf
Erster Versuch endet nach dem dritten vollständigen Vorschlag mit `}缸`.
Probeweise ausschließlich das terminale Fremdzeichen durch `]}` ersetzt:
parsebar, und vollständige bestehende Hypothesenvalidierung bestanden.
Der Inhalt der drei Vorschläge bleibt bei dieser Gegenprobe unverändert.
Aktuell ist das bewusst ausgeschlossen: Es müssten fehlende Endklammern ergänzt
werden, was auch eine abgeschnittene Antwort verdecken könnte. STOP/complete,
vollständige Vorschläge, Stackzustand und genau eine zulässige Reparatur wären
notwendige Zulassungskriterien; keine freie Ergänzung beliebiger Fragmente.
Zweiter Versuch endet mit `} syndromes]}`. Probeweise nur das unquotierte Wort
zwischen vollständigem Vorschlag und vorhandenen Endklammern entfernt:
parsebar, vollständige bestehende Hypothesenvalidierung bestanden.
Alle Strings, Werte, Vorschläge und vorhandenen Klammern bleiben dabei erhalten.
Dies spricht für eine eng begrenzte Prüfung von Fremdtext außerhalb von Strings
an Containergrenzen. Es rechtfertigt kein pauschales Entfernen unbekannter Wörter
oder ein Übernehmen beliebig aus Text herausgeschnittener JSON-Teilobjekte.
## 4. Ungültiger Untersuchungsauftrag im vorigen Lauf
Filter: ["!#flatten", "name", "contains", "Glodrak"]. Das Tool erwartet Filterobjekte
mit column/operator/value. Für diese Liste samt Marker ist kein Eingabeformat definiert.
Ein Mensch kann eine Namenssuche vermuten; die vorhandene Software hat aber keinen
Vertrag, der diese Interpretation garantiert. Nicht stillschweigend ausführen.
Zusätzlich erklärt dieselbe Antwort statische Horde-Spawns zu einem Gegenbeweis
gegen dynamisches Spawning allgemein. Das folgt daraus nicht. Es ist somit kein
rein kosmetischer Fehler, bei dem alle Zustandsänderungen ungeprüft erhalten bleiben
sollten. Ein gezielter Korrekturauftrag müsste die Filterstruktur und die gekoppelte
Evidenz-/Confidence-Bewertung berücksichtigen.
## Bewertung und Reihenfolge
1. Beim gemeinsamen Modus bleiben: Quellenkategorien eindeutig rahmen, falsche
Annahmenzuschreibungen gezielt korrigieren und unveränderte Hypothesen nach
erklärter Abhängigkeitsprüfung erneut validieren. Änderungen an Quellen nicht
allein anhand des ID-Präfixes vornehmen. Typ/Provenienz kommt aus dem Kontext.
2. Den eindeutigeren Klammerfehler lokal abfangen, mit Protokoll der exakten Änderung,
unveränderten Literalen, begrenzter Kandidatenzahl und voller anschließender Prüfung.
3. Terminale Fremdtokens/fehlende Abschlussklammern getrennt behandeln. Diese sind
engere, ausdrücklich zu spezifizierende Ausnahmen zur bisherigen Sicherheitsregel.
4. Den Filterlistenfall nicht mit einer pauschalen Formatheuristik retten.
Kein automatischer Reparaturalgorithmus wurde in dieser Untersuchung implementiert.
Eine formal gerettete Antwort ist noch kein Nachweis einwandfreier Analysequalität.
Wirtschaftlich relevant sind die vermiedenen Folgeaufrufe: Die ursprüngliche Antwort
wurde bereits bezahlt; ihre Offline-Reparatur macht diese Tokens nicht rückwirkend kostenlos.
# Untersuchung verworfener Antworten – 2026-10-19
Offline-Untersuchung von BUG20 joint-planning (Generation 97) und shared-recovery
(Generation 100). Originale und Programmcode unverändert; keine API-Anfragen,
keine Recherchetools/SQL ausgeführt, keine Kandidaten in einen Case übernommen.
`index.json` enthält Call-Referenzen und Hashes; die Call-Dateien enthalten Usage zur Nachvollziehbarkeit.
## 1. Gemeinsame Interpretation: zwei beanstandete Stellen
### observed_behavior/2
Aussage: Reproduktion bestätige, dass Wolpertinger am Testort in Dun Morogh nicht
spawnen. Quellen: F0001 und O0003. F0001 ist ein strukturierter Reproduktionsfakt
`result = reproduced`, O0003 die Beobachtung „Wolpertinger spawnen tatsächlich nicht“.
Die Quelle F0001 ist in dieser Ausgabekategorie nicht zugelassen. Die Aussage hat
jedoch bereits eine passende Beobachtungsquelle. Das ist wesentlich näher an einer
redundanten, falsch einsortierten Quellenangabe als an erfundener Beobachtung.
Ein Fact-Kind allein rechtfertigt weder das Verwerfen der Aussage noch das automatische
Entfernen der Quelle: Aussage, Provenienz und verbleibende Belege müssen erhalten bleiben.
Die Ortsangabe muss im Gesamtkontext bewertet werden; O0003 nennt allein keinen Ort.
### tester_assumptions/0
Die Antwort schreibt dem Tester die Annahme zu, die Brille sei die *alleinige*
Sichtbarkeitsvoraussetzung. O0002 sagt lediglich, dass trotz getragener notwendiger
Brille keine Wolpertinger erscheinen und der Horde-Fall funktioniere. Eine explizite
Behauptung „alleinige Voraussetzung“ steht dort nicht. Das ist eine semantische
Überinterpretation, nicht nur eine falsch etikettierte Quellen-ID. Die Kategorie ist
zusätzlich formal nur für tester_assumption/tester_comment zugelassen, nicht observation.
Diese Passage darf nicht durch bloßes Umetikettieren zu einer Beobachtung werden.
### Offline-Gegenprobe
Nur im Arbeitsspeicher F0001 aus observed_behavior/2 entfernt und den unbelegten
Testerannahmen-Eintrag entfernt: Die bestehende vollständige Interpretationsvalidierung
besteht danach. Dies ist eine menschlich gewählte Gegenprobe, keine automatisch
bewiesene Reparaturregel oder semantische Vollfreigabe der Antwort.
Die drei ursprünglichen Hypothesen verweisen ausschließlich auf unveränderte Stellen:
H1 observed_behavior/1; H2 zusätzlich confirmed_technical_facts/7; H3 zusätzlich
confirmed_technical_facts/6. Keine deklarierten Verweise betreffen die beiden
beanstandeten Stellen. Nach der Gegenprobe lassen sich alle Pointer erneut auflösen
und alle drei Vorschläge bestehen die vorhandene Hypothesenvalidierung.
Das rechtfertigt die Prüfung einer abhängigkeitssensitiven Wiederverwertung statt
pauschaler Neugenerierung. Deklarierte Referenzen beweisen aber nicht, dass jede
implizite inhaltliche Abhängigkeit ausgeschlossen ist.
### Weitere qualitative Schwächen trotz formal gültiger Gegenprobe
- Eine Untersuchungsrichtung bezeichnet 32907 als Netz und 32906 als gefangenes Item,
obwohl die Entity-Einträge selbst ihre Namen/Funktion ausdrücklich als ungeprüft
ausweisen. Die zitierten Questfelder belegen die numerischen Relationen, nicht
diese Namens-/Funktionszuordnung. Das ist eine interne Inkonsistenz.
- H2 nennt für unit_flags 512 eine symbolische Bedeutung, die im bereitgestellten
Case-Kontext nicht belegt ist. Sie vermischt Nicht-Auswählbarkeit und Unsichtbarkeit.
Der allgemeine Sichtbarkeitsverdacht ist sinnvoll; die technische Zuordnung ist
so keine bestätigte Grundlage. Ein Item-Erzeugungsspell ist zudem kein Nachweis
einer bereits verifizierten Detektionsaura.
- H3 formuliert die vermutete Quest-/Phasenabhängigkeit stellenweise zu sehr als
gegebenen Mechanismus. Als ausdrücklich zu prüfende Alternative ist sie zulässig.
Die bestehenden Validatoren prüfen Struktur, Quellenklassen und Referenzen, können
aber nicht die Wahrheit oder vollständige Ableitbarkeit jedes Freitextsatzes beweisen.
## 2. Syntaxfehler der Auftragsproduktion im gemeinsamen Lauf
Eine Human-Dev-Objektklammer endet nach expected_results mit `]` statt `}`.
Eine einzige Ersetzung dieser schließenden Klammer macht die gesamte Antwort
parsebar. Danach besteht sie unverändert die bestehende vollständige
Change-Request-Validierung einschließlich des archivierten Kontexts.
Das ist der klarste Kandidat für eine lokale, durch String-/Containerzustand
abgesicherte Klammerkorrektur. Aktuell wird eine falsche schließende Klammer
noch nicht vom allgemeinen Normalisierer ersetzt.
## 3. Zwei beschädigte Hypothesenantworten im vorigen Lauf
Erster Versuch endet nach dem dritten vollständigen Vorschlag mit `}缸`.
Probeweise ausschließlich das terminale Fremdzeichen durch `]}` ersetzt:
parsebar, und vollständige bestehende Hypothesenvalidierung bestanden.
Der Inhalt der drei Vorschläge bleibt bei dieser Gegenprobe unverändert.
Aktuell ist das bewusst ausgeschlossen: Es müssten fehlende Endklammern ergänzt
werden, was auch eine abgeschnittene Antwort verdecken könnte. STOP/complete,
vollständige Vorschläge, Stackzustand und genau eine zulässige Reparatur wären
notwendige Zulassungskriterien; keine freie Ergänzung beliebiger Fragmente.
Zweiter Versuch endet mit `} syndromes]}`. Probeweise nur das unquotierte Wort
zwischen vollständigem Vorschlag und vorhandenen Endklammern entfernt:
parsebar, vollständige bestehende Hypothesenvalidierung bestanden.
Alle Strings, Werte, Vorschläge und vorhandenen Klammern bleiben dabei erhalten.
Dies spricht für eine eng begrenzte Prüfung von Fremdtext außerhalb von Strings
an Containergrenzen. Es rechtfertigt kein pauschales Entfernen unbekannter Wörter
oder ein Übernehmen beliebig aus Text herausgeschnittener JSON-Teilobjekte.
## 4. Ungültiger Untersuchungsauftrag im vorigen Lauf
Filter: ["!#flatten", "name", "contains", "Glodrak"]. Das Tool erwartet Filterobjekte
mit column/operator/value. Für diese Liste samt Marker ist kein Eingabeformat definiert.
Ein Mensch kann eine Namenssuche vermuten; die vorhandene Software hat aber keinen
Vertrag, der diese Interpretation garantiert. Nicht stillschweigend ausführen.
Zusätzlich erklärt dieselbe Antwort statische Horde-Spawns zu einem Gegenbeweis
gegen dynamisches Spawning allgemein. Das folgt daraus nicht. Es ist somit kein
rein kosmetischer Fehler, bei dem alle Zustandsänderungen ungeprüft erhalten bleiben
sollten. Ein gezielter Korrekturauftrag müsste die Filterstruktur und die gekoppelte
Evidenz-/Confidence-Bewertung berücksichtigen.
## Bewertung und Reihenfolge
1. Beim gemeinsamen Modus bleiben: Quellenkategorien eindeutig rahmen, falsche
Annahmenzuschreibungen gezielt korrigieren und unveränderte Hypothesen nach
erklärter Abhängigkeitsprüfung erneut validieren. Änderungen an Quellen nicht
allein anhand des ID-Präfixes vornehmen. Typ/Provenienz kommt aus dem Kontext.
2. Den eindeutigeren Klammerfehler lokal abfangen, mit Protokoll der exakten Änderung,
unveränderten Literalen, begrenzter Kandidatenzahl und voller anschließender Prüfung.
3. Terminale Fremdtokens/fehlende Abschlussklammern getrennt behandeln. Diese sind
engere, ausdrücklich zu spezifizierende Ausnahmen zur bisherigen Sicherheitsregel.
4. Den Filterlistenfall nicht mit einer pauschalen Formatheuristik retten.
Kein automatischer Reparaturalgorithmus wurde in dieser Untersuchung implementiert.
Eine formal gerettete Antwort ist noch kein Nachweis einwandfreier Analysequalität.
Wirtschaftlich relevant sind die vermiedenen Folgeaufrufe: Die ursprüngliche Antwort
wurde bereits bezahlt; ihre Offline-Reparatur macht diese Tokens nicht rückwirkend kostenlos.
+42 -42
View File
@@ -1,42 +1,42 @@
3abdd01f69ca35dd910346c2978cff95c7909b51ed438d4352de8f3d489bbc9e analysis.md
83595a3f84e3975143ae08f3d29454f4c506004ac87789c13f0b7458409897e1 index.json
f122451af078546799ecd23ecb0da1ab28af20e1f1b6b902e732b7dafb7754e4 joint-change-request-closing-bracket/analysis.md
61e732ecd61b5a04790bcef1d2049cf75fb36075df6a4a5c12a63756f1f9d716 joint-change-request-closing-bracket/answer.txt
267554a74192630ddabdcd221cf78e62067b58abce18bf5403e9fcf061bfe74d joint-change-request-closing-bracket/call.json
34536a46d16f0fefe08e370433a36fe1c2a7c82bc32635b40e94781039460d13 joint-change-request-closing-bracket/rejection-records.json
102a8dfbae42f36a98a1397f9b8325e7007761dd043d436b5ed105891937ae41 joint-change-request-closing-bracket/request.json
48d4ec5a7671f42eac599fd3f186a52733bbed9f7aa1a090f228764798547ca4 joint-change-request-closing-bracket/validation-context.json
8e320306d5ef6f4ab740730c6be5341f9ab5456fe4d2ea6401cf3bf217e3b989 joint-interpretation-source-kinds/analysis.md
0f477bb21271863135a96b1628fd4e5b90e629476876bd79921d22a625273c89 joint-interpretation-source-kinds/answer.txt
81b5649c121cf83dc049bac836a5fd607aed4031bf1626f6c0768e1ff19f2fa5 joint-interpretation-source-kinds/call.json
3aff74a41ef50ac6187356a9e4fa01873226aa99e0abdfe7f10c6fd65f80fc34 joint-interpretation-source-kinds/parsed-answer.json
4c0378f533f38ed16cf34dd1aa04a3e82e9ef25dfcc4236a674d257e7cf22792 joint-interpretation-source-kinds/rejection-records.json
8edbe2caf7edc8a7bd70ddc442e94d3bbb776852a6f70415e08fd749e689020d joint-interpretation-source-kinds/request.json
565e3369d71e182f79c7267a7c75ed4e065292e9d33005155ffd4fb0e461f804 joint-interpretation-source-kinds/validation-context.json
1cc600fd998f2a76fef7b579f35e5e3a47a0f9fc14404ece2431242d373cf1a4 README.md
98d31c7606baab28173073588c747e95503f372bb2e8d58adc873ad83245c97b schemas/case-interpretation-context-v1.schema.json
b0b7c630e1ab85d3924fbe17bf909d8644e5256507f0eada5941b54902f23d90 schemas/case-interpretation-output-v1.schema.json
5b91b1b2df3f50554f34659cd254070462e452b28f3658a52cdf73cb182fa408 schemas/case-interpretation-quality-output-v1.schema.json
6dfb2ce19e8694db929fed8e6ca9a2266902095f43ad553ddea0915fb24923e9 schemas/change-request-output-v2.schema.json
78c0642f92bb91335777db7dc9109afe2db4115be702820cf6adf14b4b348ea4 schemas/hypotheses-output-v1.schema.json
c820bd600af6e906c37663cd3e380d1565b165a8739ba5813db3003b256674f2 schemas/hypothesis-context-v1.schema.json
a4388d0f2138c506cff7555c16b42f3a8cb34bb9e53693bfd6cf41f9c993de27 schemas/llm-call-v1.schema.json
cc7bb34d3051ccc4f830605f1262fee04199de9365bd2f630860bcf308d47436 separate-hypotheses-stray-token/analysis.md
bc041ff5810c56a62b28ca95877d404c9d5759fcab708d8187b3d49499378c12 separate-hypotheses-stray-token/answer.txt
5fd4b4625d59cfa6409ffe8bd69d3dbb19a2fcc48dd0ffd08a2c2db08718b781 separate-hypotheses-stray-token/call.json
6848c99604c6cde8679b2cfc6d6eec805650cefd82b4ac6f43267700583e55cd separate-hypotheses-stray-token/rejection-records.json
7805fb5cb286733c015e25fda71ad63fa74109faeb7ee036441cc4299153c1ae separate-hypotheses-stray-token/request.json
2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f separate-hypotheses-stray-token/validation-context.json
10b7afafb5496b68ac0dbba2bdcb37369ab768978f9696ce6d875174925225af separate-hypotheses-terminal-character/analysis.md
b1f8453566dc2f0ed38d48478a4db57906f6cd96ba2e40757887950678317d6a separate-hypotheses-terminal-character/answer.txt
bc380985aadade22f74e06b73d0bac5a5bded15078f9fd44884625971fb98d57 separate-hypotheses-terminal-character/call.json
8c5fd3b22a44deffe99b5f3c600818768b32f39910c3493e7cba2a6630697989 separate-hypotheses-terminal-character/rejection-records.json
2d0c1c94f68b686d0837c7c1f1137e88363b62e3d26f89781b46c9e9881fc900 separate-hypotheses-terminal-character/request.json
2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f separate-hypotheses-terminal-character/validation-context.json
a2eae8053047eaff92d1edd3c9cbfe3dc4153dae272ddb40c4d2871704c12856 separate-investigation-filter-list/analysis.md
0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31 separate-investigation-filter-list/answer.txt
a6a08a0d40b10272895171f82bcd4f28dccf9b6f46cead9e34894f64fa57747a separate-investigation-filter-list/call.json
0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31 separate-investigation-filter-list/parsed-answer.json
aaa0462cf3ce158c307280e4ef9c339222209f97dc58a0451a625a5dcc3a4133 separate-investigation-filter-list/rejection-records.json
f4fe5aca4a013ea1a030e75cb9e3a5d3d024c4ea68a8795fd5178f6557acf52e separate-investigation-filter-list/request.json
e205dcc34b1be5efa05de33ccb8a9984c6867f5d220d68dc0dda1a37696e9956 separate-investigation-filter-list/validation-context.json
3abdd01f69ca35dd910346c2978cff95c7909b51ed438d4352de8f3d489bbc9e analysis.md
83595a3f84e3975143ae08f3d29454f4c506004ac87789c13f0b7458409897e1 index.json
f122451af078546799ecd23ecb0da1ab28af20e1f1b6b902e732b7dafb7754e4 joint-change-request-closing-bracket/analysis.md
61e732ecd61b5a04790bcef1d2049cf75fb36075df6a4a5c12a63756f1f9d716 joint-change-request-closing-bracket/answer.txt
267554a74192630ddabdcd221cf78e62067b58abce18bf5403e9fcf061bfe74d joint-change-request-closing-bracket/call.json
34536a46d16f0fefe08e370433a36fe1c2a7c82bc32635b40e94781039460d13 joint-change-request-closing-bracket/rejection-records.json
102a8dfbae42f36a98a1397f9b8325e7007761dd043d436b5ed105891937ae41 joint-change-request-closing-bracket/request.json
48d4ec5a7671f42eac599fd3f186a52733bbed9f7aa1a090f228764798547ca4 joint-change-request-closing-bracket/validation-context.json
8e320306d5ef6f4ab740730c6be5341f9ab5456fe4d2ea6401cf3bf217e3b989 joint-interpretation-source-kinds/analysis.md
0f477bb21271863135a96b1628fd4e5b90e629476876bd79921d22a625273c89 joint-interpretation-source-kinds/answer.txt
81b5649c121cf83dc049bac836a5fd607aed4031bf1626f6c0768e1ff19f2fa5 joint-interpretation-source-kinds/call.json
3aff74a41ef50ac6187356a9e4fa01873226aa99e0abdfe7f10c6fd65f80fc34 joint-interpretation-source-kinds/parsed-answer.json
4c0378f533f38ed16cf34dd1aa04a3e82e9ef25dfcc4236a674d257e7cf22792 joint-interpretation-source-kinds/rejection-records.json
8edbe2caf7edc8a7bd70ddc442e94d3bbb776852a6f70415e08fd749e689020d joint-interpretation-source-kinds/request.json
565e3369d71e182f79c7267a7c75ed4e065292e9d33005155ffd4fb0e461f804 joint-interpretation-source-kinds/validation-context.json
1cc600fd998f2a76fef7b579f35e5e3a47a0f9fc14404ece2431242d373cf1a4 README.md
98d31c7606baab28173073588c747e95503f372bb2e8d58adc873ad83245c97b schemas/case-interpretation-context-v1.schema.json
b0b7c630e1ab85d3924fbe17bf909d8644e5256507f0eada5941b54902f23d90 schemas/case-interpretation-output-v1.schema.json
5b91b1b2df3f50554f34659cd254070462e452b28f3658a52cdf73cb182fa408 schemas/case-interpretation-quality-output-v1.schema.json
6dfb2ce19e8694db929fed8e6ca9a2266902095f43ad553ddea0915fb24923e9 schemas/change-request-output-v2.schema.json
78c0642f92bb91335777db7dc9109afe2db4115be702820cf6adf14b4b348ea4 schemas/hypotheses-output-v1.schema.json
c820bd600af6e906c37663cd3e380d1565b165a8739ba5813db3003b256674f2 schemas/hypothesis-context-v1.schema.json
a4388d0f2138c506cff7555c16b42f3a8cb34bb9e53693bfd6cf41f9c993de27 schemas/llm-call-v1.schema.json
cc7bb34d3051ccc4f830605f1262fee04199de9365bd2f630860bcf308d47436 separate-hypotheses-stray-token/analysis.md
bc041ff5810c56a62b28ca95877d404c9d5759fcab708d8187b3d49499378c12 separate-hypotheses-stray-token/answer.txt
5fd4b4625d59cfa6409ffe8bd69d3dbb19a2fcc48dd0ffd08a2c2db08718b781 separate-hypotheses-stray-token/call.json
6848c99604c6cde8679b2cfc6d6eec805650cefd82b4ac6f43267700583e55cd separate-hypotheses-stray-token/rejection-records.json
7805fb5cb286733c015e25fda71ad63fa74109faeb7ee036441cc4299153c1ae separate-hypotheses-stray-token/request.json
2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f separate-hypotheses-stray-token/validation-context.json
10b7afafb5496b68ac0dbba2bdcb37369ab768978f9696ce6d875174925225af separate-hypotheses-terminal-character/analysis.md
b1f8453566dc2f0ed38d48478a4db57906f6cd96ba2e40757887950678317d6a separate-hypotheses-terminal-character/answer.txt
bc380985aadade22f74e06b73d0bac5a5bded15078f9fd44884625971fb98d57 separate-hypotheses-terminal-character/call.json
8c5fd3b22a44deffe99b5f3c600818768b32f39910c3493e7cba2a6630697989 separate-hypotheses-terminal-character/rejection-records.json
2d0c1c94f68b686d0837c7c1f1137e88363b62e3d26f89781b46c9e9881fc900 separate-hypotheses-terminal-character/request.json
2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f separate-hypotheses-terminal-character/validation-context.json
a2eae8053047eaff92d1edd3c9cbfe3dc4153dae272ddb40c4d2871704c12856 separate-investigation-filter-list/analysis.md
0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31 separate-investigation-filter-list/answer.txt
a6a08a0d40b10272895171f82bcd4f28dccf9b6f46cead9e34894f64fa57747a separate-investigation-filter-list/call.json
0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31 separate-investigation-filter-list/parsed-answer.json
aaa0462cf3ce158c307280e4ef9c339222209f97dc58a0451a625a5dcc3a4133 separate-investigation-filter-list/rejection-records.json
f4fe5aca4a013ea1a030e75cb9e3a5d3d024c4ea68a8795fd5178f6557acf52e separate-investigation-filter-list/request.json
e205dcc34b1be5efa05de33ccb8a9984c6867f5d220d68dc0dda1a37696e9956 separate-investigation-filter-list/validation-context.json
+246 -246
View File
@@ -1,246 +1,246 @@
{
"format": "viano-rejected-response-corpus",
"format_version": 1,
"created_on": "2026-10-19",
"code_commit": "f979258",
"purpose": "Curated standalone examples explicitly retained at user request; not a full trial archive.",
"entries": [
{
"id": "joint-interpretation-source-kinds",
"trial": "bug20-joint-planning-20261019",
"case_id": "BUG-000020",
"package_id": "trial-joint-planning-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 97,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-60d94dc476555860dafbb6b852fa5a4d763ea432e1f62723280817bafa379d35-r0001-g00000097.zip",
"original_call_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json",
"rejection_code": "INTERPRETATION_SOURCE_KIND",
"protocol_status": "SUCCESS",
"reason": "Two source-category errors: observed_behavior/2 cites a fact in addition to a valid observation; tester_assumptions/0 overstates the tester report as an exclusive prerequisite. Further unverified item labels and a flag-symbol mapping are qualitative findings, not emitted validation codes.",
"files": [
{
"file": "call.json",
"sha256": "81b5649c121cf83dc049bac836a5fd607aed4031bf1626f6c0768e1ff19f2fa5",
"bytes": 24390,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json"
},
{
"file": "request.json",
"sha256": "8edbe2caf7edc8a7bd70ddc442e94d3bbb776852a6f70415e08fd749e689020d",
"bytes": 42493,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/request.json"
},
{
"file": "answer.txt",
"sha256": "0f477bb21271863135a96b1628fd4e5b90e629476876bd79921d22a625273c89",
"bytes": 11841,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json#/outcome/response_capture/text"
},
{
"file": "parsed-answer.json",
"sha256": "3aff74a41ef50ac6187356a9e4fa01873226aa99e0abdfe7f10c6fd65f80fc34",
"bytes": 12921,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json#/outcome/document"
},
{
"file": "validation-context.json",
"sha256": "565e3369d71e182f79c7267a7c75ed4e065292e9d33005155ffd4fb0e461f804",
"bytes": 141003,
"original_ref": "analysis/interpretations/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "4c0378f533f38ed16cf34dd1aa04a3e82e9ef25dfcc4236a674d257e7cf22792",
"bytes": 3009,
"original_ref": null
}
]
},
{
"id": "joint-change-request-closing-bracket",
"trial": "bug20-joint-planning-20261019",
"case_id": "BUG-000020",
"package_id": "trial-joint-planning-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 97,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-60d94dc476555860dafbb6b852fa5a4d763ea432e1f62723280817bafa379d35-r0001-g00000097.zip",
"original_call_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/round-0001.json",
"rejection_code": "LLM_RESPONSE",
"protocol_status": "ERROR",
"reason": "The human_dev object ends with ] instead of }. Replacing that single closing bracket in memory made the full output pass the existing change-request validator. No original content was accepted or modified.",
"files": [
{
"file": "call.json",
"sha256": "267554a74192630ddabdcd221cf78e62067b58abce18bf5403e9fcf061bfe74d",
"bytes": 7005,
"original_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/round-0001.json"
},
{
"file": "request.json",
"sha256": "102a8dfbae42f36a98a1397f9b8325e7007761dd043d436b5ed105891937ae41",
"bytes": 46720,
"original_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/request.json"
},
{
"file": "answer.txt",
"sha256": "61e732ecd61b5a04790bcef1d2049cf75fb36075df6a4a5c12a63756f1f9d716",
"bytes": 4652,
"original_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/round-0001.json#/outcome/response_capture/text"
},
{
"file": "validation-context.json",
"sha256": "48d4ec5a7671f42eac599fd3f186a52733bbed9f7aa1a090f228764798547ca4",
"bytes": 324098,
"original_ref": "analysis/change-requests/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "34536a46d16f0fefe08e370433a36fe1c2a7c82bc32635b40e94781039460d13",
"bytes": 257,
"original_ref": null
}
]
},
{
"id": "separate-hypotheses-terminal-character",
"trial": "bug20-shared-recovery-20261019",
"case_id": "BUG-000020",
"package_id": "trial-shared-recovery-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 100,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-49c833d7194c687b04596c9b9a4bd0f4f021f54171839fb8336fc85296f98ed6-r0001-g00000100.zip",
"original_call_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/round-0001.json",
"rejection_code": "LLM_RESPONSE",
"protocol_status": "ERROR",
"reason": "The response ends after three complete proposal objects with an extraneous character and missing outer closers. Replacing the terminal character with ]} in memory passed the existing hypothesis validator. This is NOT an approved generic repair: completing containers can conceal truncation.",
"files": [
{
"file": "call.json",
"sha256": "bc380985aadade22f74e06b73d0bac5a5bded15078f9fd44884625971fb98d57",
"bytes": 8324,
"original_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/round-0001.json"
},
{
"file": "request.json",
"sha256": "2d0c1c94f68b686d0837c7c1f1137e88363b62e3d26f89781b46c9e9881fc900",
"bytes": 47383,
"original_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/request.json"
},
{
"file": "answer.txt",
"sha256": "b1f8453566dc2f0ed38d48478a4db57906f6cd96ba2e40757887950678317d6a",
"bytes": 6015,
"original_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/round-0001.json#/outcome/response_capture/text"
},
{
"file": "validation-context.json",
"sha256": "2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f",
"bytes": 149529,
"original_ref": "analysis/hypotheses/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "8c5fd3b22a44deffe99b5f3c600818768b32f39910c3493e7cba2a6630697989",
"bytes": 2118,
"original_ref": null
}
]
},
{
"id": "separate-hypotheses-stray-token",
"trial": "bug20-shared-recovery-20261019",
"case_id": "BUG-000020",
"package_id": "trial-shared-recovery-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 100,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-49c833d7194c687b04596c9b9a4bd0f4f021f54171839fb8336fc85296f98ed6-r0001-g00000100.zip",
"original_call_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/round-0001.json",
"rejection_code": "LLM_RESPONSE",
"protocol_status": "ERROR",
"reason": "An unquoted stray word syndromes occurs between the final proposal object and existing ]}. Deleting only this token in memory passed the existing hypothesis validator. A future rule must preserve all literals and reject ambiguous deletions.",
"files": [
{
"file": "call.json",
"sha256": "5fd4b4625d59cfa6409ffe8bd69d3dbb19a2fcc48dd0ffd08a2c2db08718b781",
"bytes": 8302,
"original_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/round-0001.json"
},
{
"file": "request.json",
"sha256": "7805fb5cb286733c015e25fda71ad63fa74109faeb7ee036441cc4299153c1ae",
"bytes": 48375,
"original_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/request.json"
},
{
"file": "answer.txt",
"sha256": "bc041ff5810c56a62b28ca95877d404c9d5759fcab708d8187b3d49499378c12",
"bytes": 6004,
"original_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/round-0001.json#/outcome/response_capture/text"
},
{
"file": "validation-context.json",
"sha256": "2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f",
"bytes": 149529,
"original_ref": "analysis/hypotheses/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "6848c99604c6cde8679b2cfc6d6eec805650cefd82b4ac6f43267700583e55cd",
"bytes": 2118,
"original_ref": null
}
]
},
{
"id": "separate-investigation-filter-list",
"trial": "bug20-shared-recovery-20261019",
"case_id": "BUG-000020",
"package_id": "trial-shared-recovery-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 100,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-49c833d7194c687b04596c9b9a4bd0f4f021f54171839fb8336fc85296f98ed6-r0001-g00000100.zip",
"original_call_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json",
"rejection_code": "INVESTIGATION_OUTPUT",
"protocol_status": "SUCCESS",
"reason": "The tool query uses an undocumented flat filter array with !#flatten instead of column/operator/value objects. The same response also overstates static Horde spawns as disproof of dynamic spawning. Do not repair only the filter and blindly execute coupled confidence/evidence updates.",
"files": [
{
"file": "call.json",
"sha256": "a6a08a0d40b10272895171f82bcd4f28dccf9b6f46cead9e34894f64fa57747a",
"bytes": 5346,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json"
},
{
"file": "request.json",
"sha256": "f4fe5aca4a013ea1a030e75cb9e3a5d3d024c4ea68a8795fd5178f6557acf52e",
"bytes": 51406,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/request.json"
},
{
"file": "answer.txt",
"sha256": "0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31",
"bytes": 1941,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json#/outcome/response_capture/text"
},
{
"file": "parsed-answer.json",
"sha256": "0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31",
"bytes": 1941,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json#/outcome/document"
},
{
"file": "validation-context.json",
"sha256": "e205dcc34b1be5efa05de33ccb8a9984c6867f5d220d68dc0dda1a37696e9956",
"bytes": 393837,
"original_ref": "analysis/investigation/0001/contexts/H3-0001-attempt-0001.json"
},
{
"file": "rejection-records.json",
"sha256": "aaa0462cf3ce158c307280e4ef9c339222209f97dc58a0451a625a5dcc3a4133",
"bytes": 317,
"original_ref": null
}
]
}
]
}
{
"format": "viano-rejected-response-corpus",
"format_version": 1,
"created_on": "2026-10-19",
"code_commit": "f979258",
"purpose": "Curated standalone examples explicitly retained at user request; not a full trial archive.",
"entries": [
{
"id": "joint-interpretation-source-kinds",
"trial": "bug20-joint-planning-20261019",
"case_id": "BUG-000020",
"package_id": "trial-joint-planning-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 97,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-60d94dc476555860dafbb6b852fa5a4d763ea432e1f62723280817bafa379d35-r0001-g00000097.zip",
"original_call_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json",
"rejection_code": "INTERPRETATION_SOURCE_KIND",
"protocol_status": "SUCCESS",
"reason": "Two source-category errors: observed_behavior/2 cites a fact in addition to a valid observation; tester_assumptions/0 overstates the tester report as an exclusive prerequisite. Further unverified item labels and a flag-symbol mapping are qualitative findings, not emitted validation codes.",
"files": [
{
"file": "call.json",
"sha256": "81b5649c121cf83dc049bac836a5fd607aed4031bf1626f6c0768e1ff19f2fa5",
"bytes": 24390,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json"
},
{
"file": "request.json",
"sha256": "8edbe2caf7edc8a7bd70ddc442e94d3bbb776852a6f70415e08fd749e689020d",
"bytes": 42493,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/request.json"
},
{
"file": "answer.txt",
"sha256": "0f477bb21271863135a96b1628fd4e5b90e629476876bd79921d22a625273c89",
"bytes": 11841,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json#/outcome/response_capture/text"
},
{
"file": "parsed-answer.json",
"sha256": "3aff74a41ef50ac6187356a9e4fa01873226aa99e0abdfe7f10c6fd65f80fc34",
"bytes": 12921,
"original_ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/round-0001.json#/outcome/document"
},
{
"file": "validation-context.json",
"sha256": "565e3369d71e182f79c7267a7c75ed4e065292e9d33005155ffd4fb0e461f804",
"bytes": 141003,
"original_ref": "analysis/interpretations/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "4c0378f533f38ed16cf34dd1aa04a3e82e9ef25dfcc4236a674d257e7cf22792",
"bytes": 3009,
"original_ref": null
}
]
},
{
"id": "joint-change-request-closing-bracket",
"trial": "bug20-joint-planning-20261019",
"case_id": "BUG-000020",
"package_id": "trial-joint-planning-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 97,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-60d94dc476555860dafbb6b852fa5a4d763ea432e1f62723280817bafa379d35-r0001-g00000097.zip",
"original_call_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/round-0001.json",
"rejection_code": "LLM_RESPONSE",
"protocol_status": "ERROR",
"reason": "The human_dev object ends with ] instead of }. Replacing that single closing bracket in memory made the full output pass the existing change-request validator. No original content was accepted or modified.",
"files": [
{
"file": "call.json",
"sha256": "267554a74192630ddabdcd221cf78e62067b58abce18bf5403e9fcf061bfe74d",
"bytes": 7005,
"original_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/round-0001.json"
},
{
"file": "request.json",
"sha256": "102a8dfbae42f36a98a1397f9b8325e7007761dd043d436b5ed105891937ae41",
"bytes": 46720,
"original_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/request.json"
},
{
"file": "answer.txt",
"sha256": "61e732ecd61b5a04790bcef1d2049cf75fb36075df6a4a5c12a63756f1f9d716",
"bytes": 4652,
"original_ref": "llm/operations/17917402a4c04bd20ae3b0a2f256a39daa4c026a0afff5f80f408478611d4e03/round-0001.json#/outcome/response_capture/text"
},
{
"file": "validation-context.json",
"sha256": "48d4ec5a7671f42eac599fd3f186a52733bbed9f7aa1a090f228764798547ca4",
"bytes": 324098,
"original_ref": "analysis/change-requests/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "34536a46d16f0fefe08e370433a36fe1c2a7c82bc32635b40e94781039460d13",
"bytes": 257,
"original_ref": null
}
]
},
{
"id": "separate-hypotheses-terminal-character",
"trial": "bug20-shared-recovery-20261019",
"case_id": "BUG-000020",
"package_id": "trial-shared-recovery-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 100,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-49c833d7194c687b04596c9b9a4bd0f4f021f54171839fb8336fc85296f98ed6-r0001-g00000100.zip",
"original_call_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/round-0001.json",
"rejection_code": "LLM_RESPONSE",
"protocol_status": "ERROR",
"reason": "The response ends after three complete proposal objects with an extraneous character and missing outer closers. Replacing the terminal character with ]} in memory passed the existing hypothesis validator. This is NOT an approved generic repair: completing containers can conceal truncation.",
"files": [
{
"file": "call.json",
"sha256": "bc380985aadade22f74e06b73d0bac5a5bded15078f9fd44884625971fb98d57",
"bytes": 8324,
"original_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/round-0001.json"
},
{
"file": "request.json",
"sha256": "2d0c1c94f68b686d0837c7c1f1137e88363b62e3d26f89781b46c9e9881fc900",
"bytes": 47383,
"original_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/request.json"
},
{
"file": "answer.txt",
"sha256": "b1f8453566dc2f0ed38d48478a4db57906f6cd96ba2e40757887950678317d6a",
"bytes": 6015,
"original_ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/round-0001.json#/outcome/response_capture/text"
},
{
"file": "validation-context.json",
"sha256": "2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f",
"bytes": 149529,
"original_ref": "analysis/hypotheses/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "8c5fd3b22a44deffe99b5f3c600818768b32f39910c3493e7cba2a6630697989",
"bytes": 2118,
"original_ref": null
}
]
},
{
"id": "separate-hypotheses-stray-token",
"trial": "bug20-shared-recovery-20261019",
"case_id": "BUG-000020",
"package_id": "trial-shared-recovery-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 100,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-49c833d7194c687b04596c9b9a4bd0f4f021f54171839fb8336fc85296f98ed6-r0001-g00000100.zip",
"original_call_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/round-0001.json",
"rejection_code": "LLM_RESPONSE",
"protocol_status": "ERROR",
"reason": "An unquoted stray word syndromes occurs between the final proposal object and existing ]}. Deleting only this token in memory passed the existing hypothesis validator. A future rule must preserve all literals and reject ambiguous deletions.",
"files": [
{
"file": "call.json",
"sha256": "5fd4b4625d59cfa6409ffe8bd69d3dbb19a2fcc48dd0ffd08a2c2db08718b781",
"bytes": 8302,
"original_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/round-0001.json"
},
{
"file": "request.json",
"sha256": "7805fb5cb286733c015e25fda71ad63fa74109faeb7ee036441cc4299153c1ae",
"bytes": 48375,
"original_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/request.json"
},
{
"file": "answer.txt",
"sha256": "bc041ff5810c56a62b28ca95877d404c9d5759fcab708d8187b3d49499378c12",
"bytes": 6004,
"original_ref": "llm/operations/b58ae687fdde681ed31f46a21147298ced592a1fb391d86a3f346bfd3e648096/round-0001.json#/outcome/response_capture/text"
},
{
"file": "validation-context.json",
"sha256": "2b979744cf039d037887ac9abd4f0154ef1682918959c0139969d2f32867524f",
"bytes": 149529,
"original_ref": "analysis/hypotheses/0001/context.json"
},
{
"file": "rejection-records.json",
"sha256": "6848c99604c6cde8679b2cfc6d6eec805650cefd82b4ac6f43267700583e55cd",
"bytes": 2118,
"original_ref": null
}
]
},
{
"id": "separate-investigation-filter-list",
"trial": "bug20-shared-recovery-20261019",
"case_id": "BUG-000020",
"package_id": "trial-shared-recovery-BUG-000020-20261019",
"analysis_revision": 1,
"source_generation": 100,
"original_package_filename": "897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d-49c833d7194c687b04596c9b9a4bd0f4f021f54171839fb8336fc85296f98ed6-r0001-g00000100.zip",
"original_call_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json",
"rejection_code": "INVESTIGATION_OUTPUT",
"protocol_status": "SUCCESS",
"reason": "The tool query uses an undocumented flat filter array with !#flatten instead of column/operator/value objects. The same response also overstates static Horde spawns as disproof of dynamic spawning. Do not repair only the filter and blindly execute coupled confidence/evidence updates.",
"files": [
{
"file": "call.json",
"sha256": "a6a08a0d40b10272895171f82bcd4f28dccf9b6f46cead9e34894f64fa57747a",
"bytes": 5346,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json"
},
{
"file": "request.json",
"sha256": "f4fe5aca4a013ea1a030e75cb9e3a5d3d024c4ea68a8795fd5178f6557acf52e",
"bytes": 51406,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/request.json"
},
{
"file": "answer.txt",
"sha256": "0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31",
"bytes": 1941,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json#/outcome/response_capture/text"
},
{
"file": "parsed-answer.json",
"sha256": "0def03fad919def538aa1d72ce1d97333364029fcd2ae95e8bad31d9fc550e31",
"bytes": 1941,
"original_ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/round-0001.json#/outcome/document"
},
{
"file": "validation-context.json",
"sha256": "e205dcc34b1be5efa05de33ccb8a9984c6867f5d220d68dc0dda1a37696e9956",
"bytes": 393837,
"original_ref": "analysis/investigation/0001/contexts/H3-0001-attempt-0001.json"
},
{
"file": "rejection-records.json",
"sha256": "aaa0462cf3ce158c307280e4ef9c339222209f97dc58a0451a625a5dcc3a4133",
"bytes": 317,
"original_ref": null
}
]
}
]
}
@@ -1,7 +1,7 @@
# joint-change-request-closing-bracket
Rejection: `LLM_RESPONSE`. Protocol status: `ERROR` (a successful protocol response may still fail its owning phase).
The human_dev object ends with ] instead of }. Replacing that single closing bracket in memory made the full output pass the existing change-request validator. No original content was accepted or modified.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
# joint-change-request-closing-bracket
Rejection: `LLM_RESPONSE`. Protocol status: `ERROR` (a successful protocol response may still fail its owning phase).
The human_dev object ends with ] instead of }. Replacing that single closing bracket in memory made the full output pass the existing change-request validator. No original content was accepted or modified.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
@@ -1,7 +1,7 @@
# joint-interpretation-source-kinds
Rejection: `INTERPRETATION_SOURCE_KIND`. Protocol status: `SUCCESS` (a successful protocol response may still fail its owning phase).
Two source-category errors: observed_behavior/2 cites a fact in addition to a valid observation; tester_assumptions/0 overstates the tester report as an exclusive prerequisite. Further unverified item labels and a flag-symbol mapping are qualitative findings, not emitted validation codes.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
# joint-interpretation-source-kinds
Rejection: `INTERPRETATION_SOURCE_KIND`. Protocol status: `SUCCESS` (a successful protocol response may still fail its owning phase).
Two source-category errors: observed_behavior/2 cites a fact in addition to a valid observation; tester_assumptions/0 overstates the tester report as an exclusive prerequisite. Further unverified item labels and a flag-symbol mapping are qualitative findings, not emitted validation codes.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
@@ -1,138 +1,138 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"format": {
"const": "viano-case-interpretation-context"
},
"format_version": {
"type": "integer",
"const": 1
},
"case_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"case_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"case": {
"type": "object",
"required": [
"case_id",
"package_id",
"analysis_revision"
],
"properties": {
"case_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"package_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"analysis_revision": {
"type": "integer",
"minimum": 1
}
}
},
"expected_behavior_completeness": {
"enum": [
"missing",
"unspecified",
"reported_complete",
"reported_partial",
"conflicting",
"researched_complete",
"researched_partial"
]
},
"expected_behavior_provenance": {
"enum": [
"tester",
"none",
"external_research",
"combined"
]
},
"sources": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"additionalProperties": {
"type": "object",
"required": [
"kind",
"case_pointer",
"data"
],
"properties": {
"kind": {
"enum": [
"report",
"observation",
"tester_comment",
"tester_assumption",
"expectation",
"fact",
"fact_reference",
"reproduction",
"step",
"entity",
"data_quality",
"unread_reference",
"expectation_state"
]
},
"case_pointer": {
"type": "string",
"pattern": "^/"
},
"data": {}
},
"additionalProperties": false
}
},
"model_encoding": {
"const": "shared_json_v1"
},
"context_selection": {
"const": "phase_selection_v1"
},
"joint_generation": {
"type": "object",
"properties": {
"policy": {
"type": "object"
},
"prior_generations": {
"type": "array"
}
},
"required": [
"policy",
"prior_generations"
],
"additionalProperties": false
}
},
"required": [
"format",
"format_version",
"case_ref",
"case_sha256",
"case",
"expected_behavior_completeness",
"expected_behavior_provenance",
"sources"
],
"additionalProperties": false
}
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"format": {
"const": "viano-case-interpretation-context"
},
"format_version": {
"type": "integer",
"const": 1
},
"case_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"case_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"case": {
"type": "object",
"required": [
"case_id",
"package_id",
"analysis_revision"
],
"properties": {
"case_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"package_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"analysis_revision": {
"type": "integer",
"minimum": 1
}
}
},
"expected_behavior_completeness": {
"enum": [
"missing",
"unspecified",
"reported_complete",
"reported_partial",
"conflicting",
"researched_complete",
"researched_partial"
]
},
"expected_behavior_provenance": {
"enum": [
"tester",
"none",
"external_research",
"combined"
]
},
"sources": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"additionalProperties": {
"type": "object",
"required": [
"kind",
"case_pointer",
"data"
],
"properties": {
"kind": {
"enum": [
"report",
"observation",
"tester_comment",
"tester_assumption",
"expectation",
"fact",
"fact_reference",
"reproduction",
"step",
"entity",
"data_quality",
"unread_reference",
"expectation_state"
]
},
"case_pointer": {
"type": "string",
"pattern": "^/"
},
"data": {}
},
"additionalProperties": false
}
},
"model_encoding": {
"const": "shared_json_v1"
},
"context_selection": {
"const": "phase_selection_v1"
},
"joint_generation": {
"type": "object",
"properties": {
"policy": {
"type": "object"
},
"prior_generations": {
"type": "array"
}
},
"required": [
"policy",
"prior_generations"
],
"additionalProperties": false
}
},
"required": [
"format",
"format_version",
"case_ref",
"case_sha256",
"case",
"expected_behavior_completeness",
"expected_behavior_provenance",
"sources"
],
"additionalProperties": false
}
@@ -1,154 +1,154 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"observed_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"expected_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"tester_assumptions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"confirmed_technical_facts": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"contradictions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"unknowns": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"investigation_direction": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"behavior_gap": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"first_known_divergence": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"failure_stage": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"relevant_entities": {
"type": "array",
"items": {
"type": "object",
"required": [
"entity_id",
"reason",
"source_ids"
],
"properties": {
"entity_id": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"reason": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"additionalProperties": false
}
},
"interpretation_summary": {
"$ref": "#/$defs/statement"
}
},
"required": [
"observed_behavior",
"expected_behavior",
"tester_assumptions",
"confirmed_technical_facts",
"contradictions",
"unknowns",
"investigation_direction",
"behavior_gap",
"first_known_divergence",
"failure_stage",
"relevant_entities",
"interpretation_summary"
],
"additionalProperties": false,
"$defs": {
"statement": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"required": [
"text",
"source_ids"
],
"additionalProperties": false
}
}
}
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"observed_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"expected_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"tester_assumptions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"confirmed_technical_facts": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"contradictions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"unknowns": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"investigation_direction": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"behavior_gap": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"first_known_divergence": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"failure_stage": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"relevant_entities": {
"type": "array",
"items": {
"type": "object",
"required": [
"entity_id",
"reason",
"source_ids"
],
"properties": {
"entity_id": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"reason": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"additionalProperties": false
}
},
"interpretation_summary": {
"$ref": "#/$defs/statement"
}
},
"required": [
"observed_behavior",
"expected_behavior",
"tester_assumptions",
"confirmed_technical_facts",
"contradictions",
"unknowns",
"investigation_direction",
"behavior_gap",
"first_known_divergence",
"failure_stage",
"relevant_entities",
"interpretation_summary"
],
"additionalProperties": false,
"$defs": {
"statement": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"required": [
"text",
"source_ids"
],
"additionalProperties": false
}
}
}
@@ -1,230 +1,230 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"observed_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"expected_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"tester_assumptions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"confirmed_technical_facts": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"contradictions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"unknowns": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"investigation_direction": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"behavior_gap": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"first_known_divergence": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"failure_stage": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"relevant_entities": {
"type": "array",
"items": {
"type": "object",
"required": [
"entity_id",
"reason",
"source_ids"
],
"properties": {
"entity_id": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"reason": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"additionalProperties": false
}
},
"interpretation_summary": {
"$ref": "#/$defs/statement"
},
"described_behavior": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
},
"basis": {
"const": "local_description"
},
"verification": {
"const": "not_independently_verified"
}
},
"required": [
"text",
"source_ids",
"basis",
"verification"
],
"additionalProperties": false
}
},
"provisional_behavior_gap": {
"anyOf": [
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
},
"basis": {
"const": "local_description"
},
"status": {
"const": "provisional"
}
},
"required": [
"text",
"source_ids",
"basis",
"status"
],
"additionalProperties": false
},
{
"type": "null"
}
]
}
},
"required": [
"observed_behavior",
"expected_behavior",
"tester_assumptions",
"confirmed_technical_facts",
"contradictions",
"unknowns",
"investigation_direction",
"behavior_gap",
"first_known_divergence",
"failure_stage",
"relevant_entities",
"interpretation_summary",
"described_behavior",
"provisional_behavior_gap"
],
"additionalProperties": false,
"$defs": {
"statement": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"required": [
"text",
"source_ids"
],
"additionalProperties": false
}
}
}
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"observed_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"expected_behavior": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"tester_assumptions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"confirmed_technical_facts": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"contradictions": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"unknowns": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"investigation_direction": {
"type": "array",
"items": {
"$ref": "#/$defs/statement"
}
},
"behavior_gap": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"first_known_divergence": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"failure_stage": {
"anyOf": [
{
"$ref": "#/$defs/statement"
},
{
"type": "null"
}
]
},
"relevant_entities": {
"type": "array",
"items": {
"type": "object",
"required": [
"entity_id",
"reason",
"source_ids"
],
"properties": {
"entity_id": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"reason": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"additionalProperties": false
}
},
"interpretation_summary": {
"$ref": "#/$defs/statement"
},
"described_behavior": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
},
"basis": {
"const": "local_description"
},
"verification": {
"const": "not_independently_verified"
}
},
"required": [
"text",
"source_ids",
"basis",
"verification"
],
"additionalProperties": false
}
},
"provisional_behavior_gap": {
"anyOf": [
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
},
"basis": {
"const": "local_description"
},
"status": {
"const": "provisional"
}
},
"required": [
"text",
"source_ids",
"basis",
"status"
],
"additionalProperties": false
},
{
"type": "null"
}
]
}
},
"required": [
"observed_behavior",
"expected_behavior",
"tester_assumptions",
"confirmed_technical_facts",
"contradictions",
"unknowns",
"investigation_direction",
"behavior_gap",
"first_known_divergence",
"failure_stage",
"relevant_entities",
"interpretation_summary",
"described_behavior",
"provisional_behavior_gap"
],
"additionalProperties": false,
"$defs": {
"statement": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
}
},
"required": [
"text",
"source_ids"
],
"additionalProperties": false
}
}
}
@@ -1,273 +1,273 @@
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"additionalProperties": false,
"required": [
"status",
"problem_summary",
"affected_scope",
"required_change",
"implementation_intent",
"implementation_guidance",
"constraints",
"preserve",
"forbidden_changes",
"do_not_fix_by",
"validation_requirements",
"missing_information",
"reason",
"human_dev",
"placeholders"
],
"properties": {
"status": {
"enum": [
"ready",
"template",
"none"
]
},
"problem_summary": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"affected_scope": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"kind",
"source_ref",
"evidence_refs"
],
"properties": {
"kind": {
"enum": [
"source",
"database"
]
},
"source_ref": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"evidence_refs": {
"type": "array",
"items": {
"type": "string",
"pattern": "^E[0-9]{6,}$"
},
"minItems": 1,
"maxItems": 100,
"uniqueItems": true
}
}
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"required_change": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"implementation_intent": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"implementation_guidance": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"constraints": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"preserve": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"forbidden_changes": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"do_not_fix_by": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"validation_requirements": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"description",
"evidence_refs"
],
"properties": {
"description": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"evidence_refs": {
"type": "array",
"items": {
"type": "string",
"pattern": "^E[0-9]{6,}$"
},
"minItems": 1,
"maxItems": 100,
"uniqueItems": true
}
}
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"missing_information": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"reason": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"human_dev": {
"type": "object",
"additionalProperties": false,
"required": [
"status",
"title",
"reason",
"instructions",
"expected_results"
],
"properties": {
"status": {
"enum": [
"assigned",
"none"
]
},
"title": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"reason": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"instructions": {
"type": "array",
"maxItems": 100,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
}
},
"expected_results": {
"type": "array",
"maxItems": 100,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
}
}
}
},
"placeholders": {
"type": "array",
"maxItems": 100,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"token",
"description"
],
"properties": {
"token": {
"type": "string",
"pattern": "^\\{\\{[A-Z][A-Z0-9_]*\\}\\}$"
},
"description": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
}
}
}
}
}
}
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"additionalProperties": false,
"required": [
"status",
"problem_summary",
"affected_scope",
"required_change",
"implementation_intent",
"implementation_guidance",
"constraints",
"preserve",
"forbidden_changes",
"do_not_fix_by",
"validation_requirements",
"missing_information",
"reason",
"human_dev",
"placeholders"
],
"properties": {
"status": {
"enum": [
"ready",
"template",
"none"
]
},
"problem_summary": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"affected_scope": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"kind",
"source_ref",
"evidence_refs"
],
"properties": {
"kind": {
"enum": [
"source",
"database"
]
},
"source_ref": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"evidence_refs": {
"type": "array",
"items": {
"type": "string",
"pattern": "^E[0-9]{6,}$"
},
"minItems": 1,
"maxItems": 100,
"uniqueItems": true
}
}
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"required_change": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"implementation_intent": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"implementation_guidance": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"constraints": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"preserve": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"forbidden_changes": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"do_not_fix_by": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"validation_requirements": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"description",
"evidence_refs"
],
"properties": {
"description": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"evidence_refs": {
"type": "array",
"items": {
"type": "string",
"pattern": "^E[0-9]{6,}$"
},
"minItems": 1,
"maxItems": 100,
"uniqueItems": true
}
}
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"missing_information": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"minItems": 0,
"maxItems": 100,
"uniqueItems": true
},
"reason": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"human_dev": {
"type": "object",
"additionalProperties": false,
"required": [
"status",
"title",
"reason",
"instructions",
"expected_results"
],
"properties": {
"status": {
"enum": [
"assigned",
"none"
]
},
"title": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"reason": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
},
"instructions": {
"type": "array",
"maxItems": 100,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
}
},
"expected_results": {
"type": "array",
"maxItems": 100,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
}
}
}
},
"placeholders": {
"type": "array",
"maxItems": 100,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"token",
"description"
],
"properties": {
"token": {
"type": "string",
"pattern": "^\\{\\{[A-Z][A-Z0-9_]*\\}\\}$"
},
"description": {
"type": "string",
"minLength": 1,
"maxLength": 8000,
"pattern": "\\S"
}
}
}
}
}
}
@@ -1,104 +1,104 @@
{
"type": "object",
"properties": {
"hypotheses": {
"type": "array",
"minItems": 1,
"items": {
"$ref": "#/$defs/proposal"
}
}
},
"required": [
"hypotheses"
],
"additionalProperties": false,
"$defs": {
"proposal": {
"type": "object",
"properties": {
"title": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"mechanism": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"rationale": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"distinction": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
},
"interpretation_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^I[0-9]{4,}$"
}
},
"expected_evidence": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
}
},
"falsifying_evidence": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
}
},
"open_questions": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
}
}
},
"required": [
"title",
"mechanism",
"rationale",
"distinction",
"source_ids",
"interpretation_ids",
"expected_evidence",
"falsifying_evidence",
"open_questions"
],
"additionalProperties": false
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
{
"type": "object",
"properties": {
"hypotheses": {
"type": "array",
"minItems": 1,
"items": {
"$ref": "#/$defs/proposal"
}
}
},
"required": [
"hypotheses"
],
"additionalProperties": false,
"$defs": {
"proposal": {
"type": "object",
"properties": {
"title": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"mechanism": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"rationale": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"distinction": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"source_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
}
},
"interpretation_ids": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"pattern": "^I[0-9]{4,}$"
}
},
"expected_evidence": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
}
},
"falsifying_evidence": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
}
},
"open_questions": {
"type": "array",
"minItems": 1,
"uniqueItems": true,
"items": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
}
}
},
"required": [
"title",
"mechanism",
"rationale",
"distinction",
"source_ids",
"interpretation_ids",
"expected_evidence",
"falsifying_evidence",
"open_questions"
],
"additionalProperties": false
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
@@ -1,276 +1,276 @@
{
"type": "object",
"properties": {
"format": {
"const": "viano-hypothesis-context"
},
"format_version": {
"type": "integer",
"const": 1
},
"case_context": {
"type": "object",
"properties": {
"format": {
"const": "viano-case-interpretation-context"
},
"format_version": {
"type": "integer",
"const": 1
},
"case_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"case_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"case": {
"type": "object",
"required": [
"case_id",
"package_id",
"analysis_revision"
],
"properties": {
"case_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"package_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"analysis_revision": {
"type": "integer",
"minimum": 1
}
}
},
"expected_behavior_completeness": {
"enum": [
"missing",
"unspecified",
"reported_complete",
"reported_partial",
"conflicting",
"researched_complete",
"researched_partial"
]
},
"expected_behavior_provenance": {
"enum": [
"tester",
"none",
"external_research",
"combined"
]
},
"sources": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"additionalProperties": {
"type": "object",
"required": [
"kind",
"case_pointer",
"data"
],
"properties": {
"kind": {
"enum": [
"report",
"observation",
"tester_comment",
"tester_assumption",
"expectation",
"fact",
"fact_reference",
"reproduction",
"step",
"entity",
"data_quality",
"unread_reference",
"expectation_state"
]
},
"case_pointer": {
"type": "string",
"pattern": "^/"
},
"data": {}
},
"additionalProperties": false
}
},
"model_encoding": {
"const": "shared_json_v1"
},
"context_selection": {
"const": "phase_selection_v1"
},
"joint_generation": {
"type": "object",
"properties": {
"policy": {
"type": "object"
},
"prior_generations": {
"type": "array"
}
},
"required": [
"policy",
"prior_generations"
],
"additionalProperties": false
}
},
"required": [
"format",
"format_version",
"case_ref",
"case_sha256",
"case",
"expected_behavior_completeness",
"expected_behavior_provenance",
"sources"
],
"additionalProperties": false
},
"interpretation_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"interpretation_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"interpretation_sources": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^I[0-9]{4,}$"
},
"additionalProperties": {
"type": "object",
"properties": {
"kind": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"interpretation_pointer": {
"type": "string",
"pattern": "^/interpretation/"
},
"data": {}
},
"required": [
"kind",
"interpretation_pointer",
"data"
],
"additionalProperties": false
}
},
"policy": {
"type": "object",
"properties": {
"format": {
"const": "viano-hypothesis-policy"
},
"format_version": {
"type": "integer",
"const": 1
},
"min_hypotheses": {
"type": "integer",
"minimum": 1
},
"max_hypotheses": {
"type": "integer",
"minimum": 1
},
"initial_budget": {
"type": "integer",
"minimum": 1
},
"budget_unit": {
"const": "investigation_units"
}
},
"required": [
"format",
"format_version",
"min_hypotheses",
"max_hypotheses",
"initial_budget",
"budget_unit"
],
"additionalProperties": false,
"$schema": "https://json-schema.org/draft/2020-12/schema"
},
"prior_generations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"analysis_revision": {
"type": "integer",
"minimum": 1
},
"hypotheses_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"hypotheses_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"initial_proposals": {
"type": "array",
"items": {
"type": "object"
}
}
},
"required": [
"analysis_revision",
"hypotheses_ref",
"hypotheses_sha256",
"initial_proposals"
],
"additionalProperties": false
}
},
"prompt_version": {
"enum": [
"hypotheses_v2",
"hypotheses_v3",
"hypotheses_v4"
]
}
},
"required": [
"format",
"format_version",
"case_context",
"interpretation_ref",
"interpretation_sha256",
"interpretation_sources",
"policy",
"prior_generations"
],
"additionalProperties": false,
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
{
"type": "object",
"properties": {
"format": {
"const": "viano-hypothesis-context"
},
"format_version": {
"type": "integer",
"const": 1
},
"case_context": {
"type": "object",
"properties": {
"format": {
"const": "viano-case-interpretation-context"
},
"format_version": {
"type": "integer",
"const": 1
},
"case_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"case_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"case": {
"type": "object",
"required": [
"case_id",
"package_id",
"analysis_revision"
],
"properties": {
"case_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"package_id": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"analysis_revision": {
"type": "integer",
"minimum": 1
}
}
},
"expected_behavior_completeness": {
"enum": [
"missing",
"unspecified",
"reported_complete",
"reported_partial",
"conflicting",
"researched_complete",
"researched_partial"
]
},
"expected_behavior_provenance": {
"enum": [
"tester",
"none",
"external_research",
"combined"
]
},
"sources": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^[A-Z][0-9]{4,}$"
},
"additionalProperties": {
"type": "object",
"required": [
"kind",
"case_pointer",
"data"
],
"properties": {
"kind": {
"enum": [
"report",
"observation",
"tester_comment",
"tester_assumption",
"expectation",
"fact",
"fact_reference",
"reproduction",
"step",
"entity",
"data_quality",
"unread_reference",
"expectation_state"
]
},
"case_pointer": {
"type": "string",
"pattern": "^/"
},
"data": {}
},
"additionalProperties": false
}
},
"model_encoding": {
"const": "shared_json_v1"
},
"context_selection": {
"const": "phase_selection_v1"
},
"joint_generation": {
"type": "object",
"properties": {
"policy": {
"type": "object"
},
"prior_generations": {
"type": "array"
}
},
"required": [
"policy",
"prior_generations"
],
"additionalProperties": false
}
},
"required": [
"format",
"format_version",
"case_ref",
"case_sha256",
"case",
"expected_behavior_completeness",
"expected_behavior_provenance",
"sources"
],
"additionalProperties": false
},
"interpretation_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"interpretation_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"interpretation_sources": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^I[0-9]{4,}$"
},
"additionalProperties": {
"type": "object",
"properties": {
"kind": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"interpretation_pointer": {
"type": "string",
"pattern": "^/interpretation/"
},
"data": {}
},
"required": [
"kind",
"interpretation_pointer",
"data"
],
"additionalProperties": false
}
},
"policy": {
"type": "object",
"properties": {
"format": {
"const": "viano-hypothesis-policy"
},
"format_version": {
"type": "integer",
"const": 1
},
"min_hypotheses": {
"type": "integer",
"minimum": 1
},
"max_hypotheses": {
"type": "integer",
"minimum": 1
},
"initial_budget": {
"type": "integer",
"minimum": 1
},
"budget_unit": {
"const": "investigation_units"
}
},
"required": [
"format",
"format_version",
"min_hypotheses",
"max_hypotheses",
"initial_budget",
"budget_unit"
],
"additionalProperties": false,
"$schema": "https://json-schema.org/draft/2020-12/schema"
},
"prior_generations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"analysis_revision": {
"type": "integer",
"minimum": 1
},
"hypotheses_ref": {
"type": "string",
"minLength": 1,
"pattern": "\\S"
},
"hypotheses_sha256": {
"type": "string",
"pattern": "^[0-9a-f]{64}$"
},
"initial_proposals": {
"type": "array",
"items": {
"type": "object"
}
}
},
"required": [
"analysis_revision",
"hypotheses_ref",
"hypotheses_sha256",
"initial_proposals"
],
"additionalProperties": false
}
},
"prompt_version": {
"enum": [
"hypotheses_v2",
"hypotheses_v3",
"hypotheses_v4"
]
}
},
"required": [
"format",
"format_version",
"case_context",
"interpretation_ref",
"interpretation_sha256",
"interpretation_sources",
"policy",
"prior_generations"
],
"additionalProperties": false,
"$schema": "https://json-schema.org/draft/2020-12/schema"
}
File diff suppressed because it is too large. Load diff
@@ -1,7 +1,7 @@
# separate-hypotheses-stray-token
Rejection: `LLM_RESPONSE`. Protocol status: `ERROR` (a successful protocol response may still fail its owning phase).
An unquoted stray word syndromes occurs between the final proposal object and existing ]}. Deleting only this token in memory passed the existing hypothesis validator. A future rule must preserve all literals and reject ambiguous deletions.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
# separate-hypotheses-stray-token
Rejection: `LLM_RESPONSE`. Protocol status: `ERROR` (a successful protocol response may still fail its owning phase).
An unquoted stray word syndromes occurs between the final proposal object and existing ]}. Deleting only this token in memory passed the existing hypothesis validator. A future rule must preserve all literals and reject ambiguous deletions.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
@@ -1,7 +1,7 @@
# separate-hypotheses-terminal-character
Rejection: `LLM_RESPONSE`. Protocol status: `ERROR` (a successful protocol response may still fail its owning phase).
The response ends after three complete proposal objects with an extraneous character and missing outer closers. Replacing the terminal character with ]} in memory passed the existing hypothesis validator. This is NOT an approved generic repair: completing containers can conceal truncation.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
# separate-hypotheses-terminal-character
Rejection: `LLM_RESPONSE`. Protocol status: `ERROR` (a successful protocol response may still fail its owning phase).
The response ends after three complete proposal objects with an extraneous character and missing outer closers. Replacing the terminal character with ]} in memory passed the existing hypothesis validator. This is NOT an approved generic repair: completing containers can conceal truncation.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
@@ -1,7 +1,7 @@
# separate-investigation-filter-list
Rejection: `INVESTIGATION_OUTPUT`. Protocol status: `SUCCESS` (a successful protocol response may still fail its owning phase).
The tool query uses an undocumented flat filter array with !#flatten instead of column/operator/value objects. The same response also overstates static Horde spawns as disproof of dynamic spawning. Do not repair only the filter and blindly execute coupled confidence/evidence updates.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.
# separate-investigation-filter-list
Rejection: `INVESTIGATION_OUTPUT`. Protocol status: `SUCCESS` (a successful protocol response may still fail its owning phase).
The tool query uses an undocumented flat filter array with !#flatten instead of column/operator/value objects. The same response also overstates static Horde spawns as disproof of dynamic spawning. Do not repair only the filter and blindly execute coupled confidence/evidence updates.
See the German overall analysis in ../analysis.md for evidence, offline counterprobes and limits.