Research · Conflicts
Disagreements between public AI sources: the same model, benchmark and setting reported with different numbers or dates by different papers or pages. Each entry quotes every source with its link, the gap and what differs in the setting. Found by checking each numeric claim against its cited source and against the other sources. $0.03 per call.
GET https://research.sevenfourone.studio/research/conflicts
0.03 USDC on Base · payTo 0x86e00a8f8248fb47D8E95D42d51DcA0191dCa4AC
Status: verified · payable
Operator badge: embed this endpoint's live status badge — it reads "Verified Payable" only while the probe record backs it.
Settlement: direct to the seller's payTo — 0% HIVE402 take
Payment routes
{
"q": "MMLU"
}{
"conflicts": [
{
"found": "2026-11-17",
"gap": 13.1,
"id": "cf:gpt-4:humaneval:pass1",
"kind": "conflict",
"sources": [
{
"quote": "HumanEval [43] 67.0% ...",
"setting": "0-shot",
"unit": "%",
"url": "https://arxiv.org/abs/2303.08774",
"value": 67,
"where": "Table 2",
"who": "OpenAI, GPT-4 Technical Report"
},
{
"quote": "... surpassing the previous state-of-the-art GPT-4 that achieves 80%.",
"setting": "pass@1, the paper's own GPT-4 run",
"unit": "%",
"url": "https://arxiv.org/abs/2303.11366",
"value": 80.1,
"where": "abstract; Table 1",
"who": "Shinn et al., Reflexion"
}
],
"subject": "GPT-4 on HumanEval, pass@1",
"summary": "Two papers give GPT-4 scores 13.1 points apart on the same benchmark and metric."
}
],
"count": 1,
"kind": null,
"q": "HumanEval",
"total": 5
}Script Master Labs LLC · SDVOSB · Kinston, NC · Terms · Refunds · Privacy · Contact
SML network: ScriptMasterLabs — the main site · SML Dual Market — the human storefront · VA Ratings — VA disability ratings, free for veterans
Agent intel 
| Trust score | 65 / 100 · breakdown |
|---|---|
| Probe uptime (30d) | 100.0% over 1 probes · daily |
| Avg 402 latency | 794 ms |
| Paid calls (30d, on-chain) | 1 calls · 1 buyers · shared price cohort of 3 |
| Facilitator-reported (30d) | 1 calls · 1 payers (CDP Bazaar) |
How to call
GET https://research.sevenfourone.studio/research/conflicts · input in query · spec from live-challenge
Input schema
{
"type": "object",
"properties": {
"q": {
"type": "string",
"maxLength": 200,
"description": "words to match: a model, benchmark or source"
},
"kind": {
"type": "string",
"enum": [
"conflict",
"setting",
"date"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"default": 50
}
}
}Output schema
{
"type": "object",
"properties": {
"count": {
"type": "integer"
},
"total": {
"type": "integer"
},
"conflicts": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"kind": {
"type": "string",
"description": "conflict | setting | date"
},
"subject": {
"type": "string",
"description": "model, benchmark and setting"
},
"summary": {
"type": "string"
},
"gap": {
"type": [
"number",
"string"
]
},
"found": {
"type": "string"
},
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"value": {
"type": [
"number",
"string"
]
},
"unit": {
"type": "string"
},
"setting": {
"type": "string"
},
"who": {
"type": "string"
},
"url": {
"type": "string"
},
"quote": {
"type": "string"
},
"where": {
"type": "string"
}
}
}
}
},
"required": [
"subject",
"sources"
]
}
}
},
"required": [
"conflicts"
]
}curl -i -X GET 'https://research.sevenfourone.studio/research/conflicts?q=MMLU'
Agents: POST https://hive402.scriptmasterlabs.com/mcp → route_task / proxy_call · SDK /sdk/hive402.mjs