Upside Down Research · Est. MMXXIIIEngine online · UDR-HC-02
HousecarlArbiter
LoginGet started
How it works

Documentation

How the reasoning engine works, and a full worked example.

Ready-to-use prompt

Extract claims from any text

Hand /content/extract.txtto a coding agent (Claude Code, Cursor, an MCP subagent, or any chat) along with your source text — article, transcript, court filing, earnings call, memo — and it will produce a complete Housecarl Arbiter investigation JSON ready to submit. Covers actor reliability anchors, predicate sharing for contradiction detection, valence rules, evidence weighting, and a validation checklist.

Open prompt

How it works

The problem

You have a question. Multiple sources are telling you different things. Some are trustworthy, some aren’t. Some claims are old, some are fresh. Some directly contradict each other. You need to know: what should I actually believe, and how confident should I be?

What the engine does

Housecarl Arbiter runs your investigation through four formal reasoning systems:

Source weightingEach source gets an effective credibility score based on their reliability, source type, competence on the specific topic, and any conflicts of interest. An SEC regulator with 0.85 reliability carries more weight than an anonymous tipster at 0.15.
Time awarenessOlder claims lose weight automatically. The decay rate depends on the domain (financial data goes stale in months, scientific findings persist for decades), the source type (institutional research ages slower than social media), and the claim’s maturity (established findings resist decay, unverified speculation decays fast). Independent corroboration resets the clock. When a newer claim explicitly replaces an older one, the older claim is defeated — it stays visible in the output but loses its influence on the conclusions.
Opinion fusionClaims are fused using formal opinion mathematics. First within each source (so one source making the same claim twice doesn’t double-count), then across independent sources (so corroboration from separate sources strengthens confidence). The result is a three-part score: belief, disbelief, and uncertainty — always summing to 1.0.
Conflict resolutionWhen claims contradict each other, the engine builds a formal conflict model. It finds every coherent interpretation — every consistent subset of claims that survives all challenges — and shows you who supports each one. Each interpretation gets a coherence score showing how well it hangs together as a narrative. Claims that measure different things (e.g. “global” vs “US” revenue) are not treated as contradictions. Walk the interpretation tree to trace exactly why the engine believes what it believes.

What you get back

Subject resultsPer-subject verdicts: belief, disbelief, uncertainty (sum to 1.0), expected probability (single bottom-line number), and truth status (True, False, Both, or Neither).
Ranked claimsEvery claim sorted by net evidence strength. Five-level gradient: “strong” (high confidence), “moderate” (good evidence), “contested” (conflicting evidence), “weak” (thin evidence or high uncertainty), “refuted” (low belief, low uncertainty).
Interpretation treesFor each subject, every coherent reading of the evidence. Each interpretation shows which claims are accepted, who made them, their credibility scores, and the attack/support edges between them. Walk the tree to follow the reasoning. Each interpretation includes a coherence score (0–1) measuring how well the accepted claims hang together as a narrative.
Claim detailsPer-claim breakdown: belief/disbelief/uncertainty, temporal decay factor (1.0 = fresh, 0.5 = six months old), assertion time, evidence counts.
Sensitivity analysisAbductive reasoning: for each subject, what evidence would most shift the conclusions? Shows potential probability shifts, whether the predicate is contested, and which specific claims discriminate between competing interpretations. Use this to decide what to investigate next.

Worked example

A financial fraud investigation using characters from Arthur Conan Doyle’s Sherlock Holmes stories (public domain).

The scenario

Moriarty Enterprises Ltd is a London-based consulting firm run by Professor James Moriarty. It also manages the Reichenbach Investment Fund. Multiple sources have raised concerns about fabricated revenue and fund insolvency. The research question: “Is Moriarty Enterprises engaged in financial fraud?”

The sources

Sherlock Holmes
Expert · reliability 0.92
Private consulting detective. Deep forensic analysis of financial records.
Dr. John Watson
Journalist · reliability 0.75
Medical doctor and chronicler. Accompanied Holmes during the ledger review.
Inspector Lestrade
Regulator · reliability 0.8
Scotland Yard inspector. Represents the official regulatory inquiry.
Irene Adler
Insider · reliability 0.65
Former portfolio manager at the Reichenbach Fund. Terminated, claims whistleblower status.
Prof. James Moriarty
Institutional · reliability 0.3
CEO of Moriarty Enterprises. The subject of the investigation. Reliability rated low due to conflict of interest.
The Times of London
Journalist · reliability 0.7
London's paper of record. Holmes's preferred broadsheet. Reporting based on City sources.
The Daily Telegraph
Journalist · reliability 0.65
National broadsheet. Independent investigative reporting on investor withdrawal failures.

What makes this interesting

Conflicting claims: Holmes, Watson, Adler, and Lestrade all say something is wrong. Moriarty says everything is fine. The engine doesn’t pick a side — it weighs each source’s credibility and shows you every coherent interpretation.

Varying reliability: Holmes (0.92 Expert) carries far more weight than Moriarty (0.30 Institutional, subject of investigation). Watson (0.75 Journalist) corroborates but adds less independent weight because his claim is evaluative, not factual.

Temporal spread: Claims range from January to March 2026. The earliest (Adler’s insider report) has slightly more decay than the latest (Lestrade’s fund freeze). The engine shows you the decay factor on each.

Supporting evidence: Holmes’s claims are backed by physical ledgers and court-ordered bank statements (high weight). Moriarty’s rebuttal cites an audit by “Milverton & Associates” (low weight — 0.5).

Full investigation input

This is exactly what you’d submit to the Housecarl Arbiter API or MCP tool. Copy it and try it yourself.

{
  "research_question": "Is Moriarty Enterprises engaged in financial fraud?",
  "domain": "Finance",
  "dependent_refresh_factor": 0.5,
  "actors": [
    {
      "id": "holmes",
      "name": "Sherlock Holmes",
      "source_type": "Expert",
      "base_reliability": 0.92
    },
    {
      "id": "watson",
      "name": "Dr. John Watson",
      "source_type": "Journalist",
      "base_reliability": 0.75
    },
    {
      "id": "lestrade",
      "name": "Inspector Lestrade",
      "source_type": "Regulator",
      "base_reliability": 0.8
    },
    {
      "id": "adler",
      "name": "Irene Adler",
      "source_type": "Insider",
      "base_reliability": 0.65
    },
    {
      "id": "moriarty",
      "name": "Prof. James Moriarty",
      "source_type": "Institutional",
      "base_reliability": 0.3
    },
    {
      "id": "times",
      "name": "The Times of London",
      "source_type": "Journalist",
      "base_reliability": 0.7
    },
    {
      "id": "telegraph",
      "name": "The Daily Telegraph",
      "source_type": "Journalist",
      "base_reliability": 0.65
    }
  ],
  "subjects": [
    {
      "id": "moriarty-ent",
      "name": "Moriarty Enterprises Ltd",
      "subject_type": "Company"
    },
    {
      "id": "reichenbach-fund",
      "name": "Reichenbach Investment Fund",
      "subject_type": "Financial Instrument"
    }
  ],
  "claims": [
    {
      "id": "c1",
      "actor_id": "holmes",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "fabricated",
      "content": "After examining the ledgers obtained from the Diogenes Club, the reported revenue of Moriarty Enterprises bears no correlation to actual client payments. At least 40% of stated revenue traces to circular transactions between shell entities.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "assertion_time": "2026-02-15T10:00:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z",
      "corroboration_events": [
        {
          "time": "2026-02-16T14:00:00Z",
          "actor_id": "watson",
          "description": "Watson independently confirmed ledger discrepancies during joint review"
        },
        {
          "time": "2026-02-28T06:00:00Z",
          "actor_id": "times",
          "description": "The Times reported industry observers could not reconcile stated revenue with known engagements"
        }
      ]
    },
    {
      "id": "c2",
      "actor_id": "watson",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "fabricated",
      "content": "I accompanied Holmes during the ledger review. The discrepancies he identified are real, though I cannot independently verify the 40% figure. The pattern of circular billing is consistent with what I have seen in other fraud cases I have reported on.",
      "valence": "Supports",
      "claim_type": "Evaluative",
      "epistemic_status": "hypothesis",
      "assertion_time": "2026-02-16T14:00:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c3",
      "actor_id": "lestrade",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "under-investigation",
      "content": "Scotland Yard has opened a preliminary inquiry into Moriarty Enterprises' financial statements following a referral from the Serious Fraud Office. We cannot confirm or deny specific allegations at this time, but the inquiry is active.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "hypothesis",
      "assertion_time": "2026-03-01T09:00:00Z"
    },
    {
      "id": "c4",
      "actor_id": "moriarty",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "legitimate",
      "content": "Our accounts are audited annually by a reputable firm. All revenue is from legitimate consulting engagements. The so-called discrepancies reflect complex multi-party arrangements that an untrained eye might misinterpret.",
      "valence": "Refutes",
      "claim_type": "Factual",
      "assertion_time": "2026-03-05T11:00:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c5",
      "actor_id": "adler",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "insolvent",
      "content": "I was employed by Moriarty Enterprises as a portfolio manager for the Reichenbach Fund from 2024 to 2025. The fund's reported assets are overstated by at least 60%. Client redemptions are being paid from new investor deposits, not returns.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "assertion_time": "2026-01-20T08:00:00Z",
      "corroboration_events": [
        {
          "time": "2026-02-10T07:00:00Z",
          "actor_id": "telegraph",
          "description": "Telegraph independently confirmed investor withdrawal failures starting November 2025"
        },
        {
          "time": "2026-02-20T16:00:00Z",
          "actor_id": "holmes",
          "description": "Holmes obtained bank records confirming deposit-to-redemption routing"
        }
      ],
      "event_start_time": "2024-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c6",
      "actor_id": "holmes",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "insolvent",
      "content": "The Reichenbach Fund is a Ponzi scheme. Bank records show deposits from new investors being directly routed to redemption accounts. The fund has held no actual securities positions since Q2 2024.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "assertion_time": "2026-02-20T16:00:00Z",
      "event_start_time": "2024-04-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c7",
      "actor_id": "moriarty",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "solvent",
      "content": "The Reichenbach Fund returned 18% to investors in 2025 and maintains full reserves. Ms. Adler was terminated for cause and her claims are retaliatory. We welcome any audit.",
      "valence": "Refutes",
      "claim_type": "Factual",
      "assertion_time": "2026-03-05T11:30:00Z",
      "event_start_time": "2025-01-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c8",
      "actor_id": "lestrade",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "under-investigation",
      "content": "The Financial Conduct Authority has frozen the Reichenbach Fund pending investigation. Investor withdrawals are suspended.",
      "valence": "Supports",
      "claim_type": "Factual",
      "epistemic_status": "theory",
      "supersedes_claim_id": "c3",
      "assertion_time": "2026-03-10T09:00:00Z"
    },
    {
      "id": "c9",
      "actor_id": "times",
      "subject_id": "moriarty-ent",
      "predicate": "revenue",
      "value": "questionable",
      "content": "Sources within the City suggest that Moriarty Enterprises has been the subject of quiet inquiries by multiple creditors. The firm's reported consulting revenue is difficult to reconcile with the scale of its known client engagements, according to industry observers.",
      "valence": "Supports",
      "claim_type": "Evaluative",
      "epistemic_status": "conjecture",
      "assertion_time": "2026-02-28T06:00:00Z",
      "corroboration_events": [
        {
          "time": "2026-03-01T09:00:00Z",
          "actor_id": "lestrade",
          "description": "Scotland Yard confirmed an active inquiry, corroborating reports of creditor concerns"
        }
      ],
      "event_start_time": "2025-06-01T00:00:00Z",
      "event_end_time": "2025-12-31T23:59:59Z"
    },
    {
      "id": "c10",
      "actor_id": "telegraph",
      "subject_id": "reichenbach-fund",
      "predicate": "solvency",
      "value": "concerns-raised",
      "content": "The Daily Telegraph can reveal that at least three prominent investors in the Reichenbach Fund have been unable to withdraw their capital since November. Prof. Moriarty has attributed the delays to 'administrative restructuring' but has not provided a timeline for resolution.",
      "valence": "Supports",
      "claim_type": "Factual",
      "assertion_time": "2026-02-10T07:00:00Z",
      "event_start_time": "2025-11-01T00:00:00Z",
      "event_end_time": "2026-02-10T00:00:00Z"
    },
    {
      "id": "c11",
      "actor_id": "telegraph",
      "subject_id": "moriarty-ent",
      "predicate": "reputation",
      "value": "deteriorating",
      "content": "Several former associates of Prof. Moriarty have distanced themselves from the firm in recent months. The Diogenes Club has reportedly revoked his membership, an unusual step for the notoriously discreet institution.",
      "valence": "Supports",
      "claim_type": "Evaluative",
      "epistemic_status": "conjecture",
      "assertion_time": "2026-03-02T07:00:00Z"
    }
  ],
  "evidence": [
    {
      "id": "e1",
      "claim_id": "c1",
      "content": "Ledger photocopies from the Diogenes Club showing circular transactions",
      "valence": "Supports",
      "weight": 1.2
    },
    {
      "id": "e2",
      "claim_id": "c5",
      "content": "Adler's employment contract and internal fund reports",
      "valence": "Supports",
      "weight": 1
    },
    {
      "id": "e3",
      "claim_id": "c6",
      "content": "Bank statements obtained via court order showing deposit-to-redemption routing",
      "valence": "Supports",
      "weight": 1.5
    },
    {
      "id": "e4",
      "claim_id": "c4",
      "content": "Annual audit report from Milverton & Associates LLP",
      "valence": "Supports",
      "weight": 0.5
    }
  ]
}

What the engine returns

When you submit this investigation, the engine produces:

Subject: Moriarty Enterprises — revenue

High belief that revenue is fabricated. Holmes (Expert, 0.92) and Watson (Journalist, 0.75) both support this. Lestrade (Regulator, 0.80) confirms an active investigation. Moriarty’s denial carries little weight at 0.30. Truth status: Both(contradicted — there is evidence on both sides, but the “fabricated” interpretation dominates).

Subject: Reichenbach Fund — solvency

Very high belief the fund is insolvent. Adler (Insider, 0.65) provides firsthand testimony. Holmes (Expert, 0.92) corroborates with bank records (court-ordered, weight 1.5). Lestrade confirms the fund is frozen. Moriarty claims 18% returns but his low reliability and the absence of corroborating evidence make this the weakest claim in the ranking. Truth status: Both.

Ranked claims (top to bottom)
  1. Strong — Holmes: Reichenbach Fund is a Ponzi scheme (backed by bank statements)
  2. Strong — Holmes: Revenue is fabricated (backed by ledger photocopies)
  3. Strong — Lestrade: FCA has frozen the Reichenbach Fund
  4. Strong — Adler: Fund assets overstated by 60%
  5. Strong — Lestrade: Scotland Yard inquiry is active
  6. Moderate — Watson: Circular billing pattern is consistent with fraud
  7. Moderate — The Times: Revenue difficult to reconcile with known engagements
  8. Moderate — The Telegraph: Investors unable to withdraw since November
  9. Moderate — The Telegraph: Former associates distancing, Diogenes Club membership revoked
  10. Weak — Moriarty: Milverton & Associates audit found no irregularities (low-weight evidence)
  11. Refuted — Moriarty: Revenue is legitimate
  12. Refuted — Moriarty: Fund returned 18% and maintains reserves
Interpretation trees

The argumentation analysis finds two coherent interpretations:

Interpretation 1 (dominant, coherence: 0.85)Accepts Holmes, Watson, Adler, and Lestrade. Rejects Moriarty’s denials. Holmes’s claims attack Moriarty’s via direct contradiction. Adler’s insider testimony supports Holmes’s Ponzi finding.
Interpretation 2 (weak, coherence: 0.30)Accepts Moriarty’s denials and Lestrade’s neutral “under investigation” status. Rejects Holmes and Adler. This interpretation survives formally but has far lower aggregate credibility.
Try it yourself

Copy the JSON above and submit it via the dashboard, API, or MCP tool.

Open dashboard
No code required

Use it from Claude

The fastest way in: connect Housecarl Arbiter to Claude on the web or your phone, then ask in plain language. Works on the free plan.

Add the connector

Housecarl Arbiter is a custom connector (a remote MCP server). Claude’s free plan lets you add one, which is all you need. In Claude — on the web (claude.ai) or in the mobile app:

1.Open Settings → Connectors (depending on your version this may read Customize → Connectors).
2.Click Add custom connector, name it Housecarl Arbiter, and paste the Server URL below. Leave the advanced / OAuth fields blank.
3.Click Add. The first time you use it, Claude opens a sign-in window — approve it and you’re connected.
https://api.summereyes.vip/mcp/v1

The connector is tied to your Claude account, so adding it on the web makes it available in the mobile app too — and the other way round. No API key is needed for this path; sign-in is handled for you.

Then just ask

In any conversation, tap + Connectors and switch on Housecarl Arbiter. The first time Claude reaches for a Housecarl Arbiter tool it asks your permission — allow it. Then talk to it normally:

“Use Housecarl Arbiter to investigate whether remote work lowers team productivity. Find the strongest sources on each side, weigh them, and give me a judged verdict.”

“Read https://en.wikipedia.org/wiki/Cold_fusion, pull out the claims and the evidence it cites, run it through Housecarl Arbiter, and tell me where the verdict is shaky.”

Each investigation lands in your dashboard under Sessions, where you can walk the reasoning tree and read the scored verdict. Building your own tool instead? The REST / MCP API is right below.

Connect your tool

Everything you need to call Housecarl Arbiter from your own software — the developer path.

Two ways to call

The engine has one core operation — submit an investigation, get back a scored verdict — exposed two equivalent ways. Both use the same request shape and the same credentials; pick whichever fits what you’re building.

REST / JSON over HTTPSA plain POST with a JSON body. Best for a backend service, a script, or any non-AI tool. Start here.
MCPThe Model Context Protocol endpoint at /mcp/v1 (Streamable HTTP, JSON-RPC 2.0). Best if your tool is an AI agent that already speaks MCP.

Authenticate

Sign in, open the dashboard, and create an API key. It starts with se-and is shown once at creation — store it as a secret. Send it on every request in the x-api-key header:

x-api-key: se-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

OAuth 2.0 / JWT bearer tokens are also accepted via the Authorization: Bearer header, but a user API key is the simplest path for a standalone integration.

Quickstart

The smallest useful call — one source, one subject, one claim. The response is a full investigation result: a per-subject verdict, ranked claims, conflict analysis, and sensitivity analysis.

curl -sS -X POST https://api.summereyes.vip/api/v1/investigations/analyze \
  -H "x-api-key: se-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "research_question": "Is Acme Corp solvent?",
    "domain": "Finance",
    "actors": [
      { "id": "auditor", "name": "Big Four Auditor",
        "source_type": "Regulator", "base_reliability": 0.9 }
    ],
    "subjects": [
      { "id": "acme", "name": "Acme Corp", "subject_type": "company" }
    ],
    "claims": [
      { "id": "c1", "actor_id": "auditor", "subject_id": "acme",
        "predicate": "solvency", "value": "solvent",
        "content": "Audited financials show a 2:1 current ratio.",
        "valence": "Supports", "assertion_time": "2026-02-01T10:00:00Z" }
    ]
  }'

Core endpoints

Base URL https://api.summereyes.vip. All paths require authentication.

POST/api/v1/investigations/analyzeOne-shot analysis
POST/api/v1/sessionsCreate a persistent session
PATCH/api/v1/sessions/{id}Merge in new actors / claims / evidence
POST/api/v1/sessions/{id}/judgeRe-run the engine on the session
PUT/api/v1/sessions/{id}/sharePublish a read-only snapshot

Use /investigations/analyze for one-off questions. If your system accumulates evidence over time, create a session, merge in claims as you learn them, and re-judge on demand instead of resubmitting the whole payload.

Good to know

  • Always set each claim’s valence (Supports / Refutes) and assertion_time — they drive the result more than anything else.
  • Inconsistent inputs (e.g. an anonymous source rated 0.95) come back as non-fatal warnings; the run still succeeds. An empty warnings list means clean input.
  • Set summary_mode: true for a compact result when your consumer has a limited context window.
  • Up to 1,024 sessions per user; payloads up to 10 MB; sessions expire after 365 days of inactivity.
  • A 429 means your plan quota is exhausted; a 504 means the input was too large — split it up.

API reference

Interactive API documentation with request/response schemas, authentication details, and the full OpenAPI spec.

api.summereyes.vip/openapi-docs