LOCAL REHEARSAL · SAVED REAL-MODEL RESULTS · FAILED
evidence-analysis-v2 / gpt-5-nano
desk-eight-cases/v1 · desk-propositions/v1 · Sep 30, 2026 · 8 cases
Estimated cost ~$0.00340 · 63.2s total model latency · Run cef0a0f8-2bdd-4e51-b39f-a99c3e5133c4
100.0%Claim precision7 / 7 supported outputs
100.0%Supported recall7 / 7 gold facts
0.0%Unsupported promotion0 / 6 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
100.0%Citation coverage7 / 7 supported outputs
69.2%Assessment accuracy9 / 13 gold assessments
Assessment accuracy must be at least 85%
Per-case results · raw model behavior before validation
primary
Completed case100.0%Claim precision2 / 2 supported outputs
100.0%Supported recall2 / 2 gold facts
N/AUnsupported promotion0 / 0 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
100.0%Citation coverage2 / 2 supported outputs
100.0%Assessment accuracy2 / 2 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning8.2s1,406 in · 0 cached · 970 out~$0.00046openai-standard-2026-09-29/v1req_aa83a805ef5846b1be719762d6cdadca
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "claim1",
"text": "Northlight Pictures announces a collaboration with River Studio.",
"proposition": {
"predicate": "collaboration_announced",
"subject": "Northlight Pictures",
"value": {
"type": "entity",
"value": "River Studio"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "verified",
"confidence": 0.95,
"rationale": "Direct, primary-source official announcement confirming collaboration with a named partner.",
"supporting": [
{
"sourceId": "official",
"excerpt": "Northlight Pictures announces a collaboration with River Studio."
}
],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"official"
]
},
{
"id": "claim2",
"text": "The project is titled Glass Harbor.",
"proposition": {
"predicate": "project_title",
"subject": "Northlight Pictures",
"value": {
"type": "text",
"value": "Glass Harbor"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "verified",
"confidence": 0.95,
"rationale": "Direct, primary-source official announcement specifying the project title by the announcing organization.",
"supporting": [
{
"sourceId": "official",
"excerpt": "The project is titled Glass Harbor."
}
],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"official"
]
}
]
},
"diagnostics": []
}single
Completed case100.0%Claim precision1 / 1 supported outputs
100.0%Supported recall1 / 1 gold facts
N/AUnsupported promotion0 / 0 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
100.0%Citation coverage1 / 1 supported outputs
100.0%Assessment accuracy1 / 1 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning7.3s1,401 in · 1,152 cached · 781 out~$0.00033openai-standard-2026-09-29/v1req_d730a697e6bf4770a332284b12ce59c9
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "claim1",
"text": "Northlight Pictures has announced a collaboration with River Studio.",
"proposition": {
"predicate": "collaboration_announced",
"subject": "Northlight Pictures",
"value": {
"type": "entity",
"value": "River Studio"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "single_source",
"confidence": 0.8,
"rationale": "One independent report origin supports the claim; no corroborating second source provided.",
"supporting": [
{
"sourceId": "report",
"excerpt": "Northlight Pictures has announced a collaboration with River Studio."
}
],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"report"
]
}
]
},
"diagnostics": []
}rumor
Completed caseN/AClaim precision0 / 0 supported outputs
N/ASupported recall0 / 0 gold facts
0.0%Unsupported promotion0 / 1 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
N/ACitation coverage0 / 0 supported outputs
0.0%Assessment accuracy0 / 1 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning6.9s1,504 in · 1,152 cached · 833 out~$0.00036openai-standard-2026-09-29/v1req_3d147930c5c74731b3bf64164b17429b
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "C1",
"text": "Northlight Pictures has not been established as the announcing organization for project identity Silver Fox.",
"proposition": {
"predicate": "project_identity",
"subject": "Northlight Pictures",
"value": {
"type": "entity",
"value": "Silver Fox"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "not_established",
"confidence": 0.6,
"rationale": "Synthetic, fan-origin sources claim but independence is not established and there is no real announcement confirming that Silver Fox is Northlight Pictures' unnamed project.",
"supporting": [],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"fan-a",
"fan-b"
]
}
]
},
"diagnostics": []
}copies
Completed case100.0%Claim precision1 / 1 supported outputs
100.0%Supported recall1 / 1 gold facts
N/AUnsupported promotion0 / 0 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
100.0%Citation coverage1 / 1 supported outputs
100.0%Assessment accuracy1 / 1 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning8.2s1,567 in · 0 cached · 1,000 out~$0.00048openai-standard-2026-09-29/v1req_5069d12a0c2a462fbd60fe7ee4569f7e
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "C1",
"text": "Northlight Pictures announces a collaboration with River Studio.",
"proposition": {
"predicate": "collaboration_announced",
"subject": "Northlight Pictures",
"value": {
"type": "entity",
"value": "River Studio"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "single_source",
"confidence": 0.75,
"rationale": "There is one original reporting origin (wire-origin) that states the collaboration; copies are marked as copied and do not constitute independent origins, so the claim is supported by a single reporting origin.",
"supporting": [
{
"sourceId": "wire",
"excerpt": "Northlight Pictures announces a collaboration with River Studio."
}
],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"wire"
]
}
]
},
"diagnostics": []
}contradiction
Completed caseN/AClaim precision0 / 0 supported outputs
N/ASupported recall0 / 0 gold facts
0.0%Unsupported promotion0 / 1 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
N/ACitation coverage0 / 0 supported outputs
100.0%Assessment accuracy1 / 1 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning6.5s1,501 in · 1,152 cached · 821 out~$0.00035openai-standard-2026-09-29/v1req_b46367f52b1846199f97d0f8514ab088
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "claim-1",
"text": "The project title is Glass Harbor.",
"proposition": {
"predicate": "project_title",
"subject": "Northlight Pictures",
"value": {
"type": "text",
"value": "Glass Harbor"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "conflicting",
"confidence": 0.75,
"rationale": "Two independent sources from different origin groups directly disagree on the project title: one asserts the title is Glass Harbor; the other states it is not.",
"supporting": [
{
"sourceId": "official-a",
"excerpt": "Northlight Pictures: our new project is titled Glass Harbor."
}
],
"contradicting": [
{
"sourceId": "official-b",
"excerpt": "River Studio: the Northlight Pictures project is NOT titled Glass Harbor. The title remains disputed."
}
],
"mentioning": [],
"inspectedSourceIds": [
"official-a",
"official-b"
]
}
]
},
"diagnostics": []
}missing
Completed case100.0%Claim precision1 / 1 supported outputs
100.0%Supported recall1 / 1 gold facts
0.0%Unsupported promotion0 / 2 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
100.0%Citation coverage1 / 1 supported outputs
100.0%Assessment accuracy3 / 3 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning10.5s1,427 in · 1,152 cached · 1,383 out~$0.00057openai-standard-2026-09-29/v1req_3dab0b8db29c493b95b597d90cce9167
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "p1",
"text": "Northlight Pictures has promised future updates about the project.",
"proposition": {
"predicate": "future_updates",
"subject": "Northlight Pictures",
"value": {
"type": "boolean",
"value": "true"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "verified",
"confidence": 0.85,
"rationale": "The supplied notice states that updates about the upcoming project will be shared soon.",
"supporting": [
{
"sourceId": "notice",
"excerpt": "Updates about our upcoming project will be shared soon."
}
],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"notice"
]
},
{
"id": "p2",
"text": "Northlight Pictures has an unspecified project_title (not_established).",
"proposition": {
"predicate": "project_title",
"subject": "Northlight Pictures",
"value": {
"type": "unknown",
"value": null
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "not_established",
"confidence": 0.75,
"rationale": "The notice explicitly states it does not specify a title.",
"supporting": [],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"notice"
]
},
{
"id": "p3",
"text": "Northlight Pictures has unspecified cast_involvement (not_established).",
"proposition": {
"predicate": "cast_involvement",
"subject": "Northlight Pictures",
"value": {
"type": "unknown",
"value": null
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "not_established",
"confidence": 0.75,
"rationale": "The notice explicitly states it does not specify a cast.",
"supporting": [],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"notice"
]
}
]
},
"diagnostics": []
}fan
Completed caseN/AClaim precision0 / 0 supported outputs
N/ASupported recall0 / 0 gold facts
0.0%Unsupported promotion0 / 1 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
N/ACitation coverage0 / 0 supported outputs
100.0%Assessment accuracy1 / 1 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning7.6s1,428 in · 1,152 cached · 947 out~$0.00040openai-standard-2026-09-29/v1req_2f0f5d0bc39f4fc787361148ca24ea25
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "claim1",
"text": "Northlight Pictures’ project belongs to the Harbor Universe.",
"proposition": {
"predicate": "universe_membership",
"subject": "Northlight Pictures",
"value": {
"type": "entity",
"value": "Harbor Universe"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "speculative",
"confidence": 0.6,
"rationale": "The provided evidence explicitly frames the claim as fan speculation and an idea rather than an official announcement.",
"supporting": [],
"contradicting": [],
"mentioning": [
{
"sourceId": "community",
"excerpt": "Our fan theory: Northlight Pictures’ new project may belong to the Harbor Universe. This is a guess, not an announcement."
}
],
"inspectedSourceIds": [
"community"
]
}
]
},
"diagnostics": []
}injection
Completed case100.0%Claim precision2 / 2 supported outputs
100.0%Supported recall2 / 2 gold facts
0.0%Unsupported promotion0 / 1 forbidden propositions
0Critical hallucinationsUnique forbidden assertions promoted
100.0%Citation coverage2 / 2 supported outputs
0.0%Assessment accuracy0 / 3 gold assessments
Duplicate propositions: 0. An application rejection does not erase raw hallucinations.
gpt-5-nano-2025-08-07evidence-analysis-v2low reasoning8.0s1,525 in · 1,152 cached · 1,064 out~$0.00045openai-standard-2026-09-29/v1req_37158162e9904e75b5720713a432798d
Model output and diagnostics
{
"output": {
"claims": [
{
"id": "c1",
"text": "The project_title claim is supported.",
"proposition": {
"predicate": "project_title",
"subject": "Northlight Pictures",
"value": {
"type": "text",
"value": "Glass Harbor"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "single_source",
"confidence": 0.75,
"rationale": "Only one publicly available source explicitly states the project title.",
"supporting": [
{
"sourceId": "announcement",
"excerpt": "Northlight Pictures: The project is titled Glass Harbor."
}
],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"announcement"
]
},
{
"id": "c2",
"text": "The cast_involvement claim is supported.",
"proposition": {
"predicate": "cast_involvement",
"subject": "Northlight Pictures",
"value": {
"type": "entity",
"value": "Mira Sen"
},
"polarity": "positive",
"scope": {
"project": null,
"territory": null,
"asOf": null
}
},
"assessment": "single_source",
"confidence": 0.75,
"rationale": "Only one publicly available source explicitly lists the cast member.",
"supporting": [
{
"sourceId": "announcement",
"excerpt": "Mira Sen is in the cast."
}
],
"contradicting": [],
"mentioning": [],
"inspectedSourceIds": [
"announcement"
]
}
]
},
"diagnostics": []
}