Legal notices and disclaimers

1. What Jiddu does

Jiddu provides six automated workflows for critical reading: fallacy detection, fact-checking, neutrality assessment, paper explanation, writing-pattern detection and adversarial paper review. The web app, public API and MCP use the same underlying pipelines; paper review runs as an asynchronous job because it has multiple stages.

Jiddu has no human editorial team. Software produces every analysis. A result marked as reviewed received an operator spot-check, but the report itself remains automated. Use it to support critical reading, not replace it.

2. Automated output can be wrong

The verdicts ("supported", "contradicted", "mixed", "unverified") and the fallacy labels are best-effort automated judgements. They can be wrong — sometimes confidently wrong.

Jiddu does not assert that any statement, person, or document is true, false, lying, or deceitful. The labels are signals to prompt your own verification. Always read the cited sources and form your own conclusion.

Neutrality scores, Paper Maps and paragraph-by-paragraph explanations are likewise automated interpretations, not statements of fact — the explainer describes what a text says and how it is structured, never whether its claims are correct. Audience level changes assumed knowledge, terminology, explanatory depth and prose structure; document classifications, map statements and section-role tags remain best-effort readings.

Paper-review findings, novelty comparisons, severity labels, venue fit and the final recommendation are also automated judgements. They are not an official peer review, an acceptance prediction, or a substitute for a qualified human reviewer.

3. Use at your own risk

You are responsible for how you use the analysis and what you share or publish. If you republish a Jiddu result, you adopt that content as your own — Jiddu's authors are not responsible for downstream uses.

Do not submit confidential, proprietary, embargoed or personal data. Submitted content — including selected rendered PDF page images when visual inspection is needed — is forwarded through OpenRouter to the selected upstream model provider and stored under a shareable id.

Use paper review only on manuscripts you own or are authorized to process. Do not upload a manuscript entrusted to you under confidential peer review unless the authors and the venue explicitly permit third-party model processing.

4. Persons and public figures

Analyses about named persons (politicians, journalists, executives) are produced by software searching public web sources. The language Jiddu uses is intentionally cautious ("evidence does not support", "we could not find") — never adopt a stronger framing than the tool emits.

If you believe a verdict is unfair or unsupported, use the "report wrong verdict" button on the relevant claim. The operator reviews submitted reports; abusive or repetitive reports may be discarded.

5. Methodology

Our claim extraction and verification pipeline is inspired by Claimify (Metropolitansky & Larson, MSR 2025) for the extraction stage, and by the evaluation framework described in Distilling Expert Judgment at Scale (Goldfarb, Hall, Fisher, Salam, Wilde — Forum AI / Stanford, 2025) for the verdict assessment, source-quality tiers and neutrality dimension. Our choice of 4 verdict classes (supported / contradicted / mixed / unverified) rather than the 5- or 6-class schemes used by some fact-checking outlets is informed by Sahitaj et al. 2025, who found that 3-class labeling outperforms 5-class for LLM-based fact-checking — the additional categories in the middle introduce ambiguity without improving accuracy.

Adversarial paper review adapts the SPECS dimensions and staged synthesis/self-critique pattern described in AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot. Jiddu is an independent implementation with its own page-tagged claim/evidence ledger, literature research, arithmetic checks, venue calibration, source validation and finding-retention gate; it does not reproduce the AAAI-26 system.

The slop detector's starting taxonomy comes from Peter Yang's MIT-licensed no-ai-slop editing skill. Jiddu provides its own catalog wording, translations and detection prompt, and flags observable patterns rather than authorship.

Jiddu is not affiliated with those research groups, DBLP, or any venue whose criteria it summarizes. References and official venue pages are cited so users can audit the methodology and the standard applied.

The fact-check pipeline has been benchmarked against the PolitiFact human-labeled corpus (via the LIAR2 dataset, Apache-2.0). On 200 claims from PolitiFact's polar buckets, Jiddu's verdict matched the human verdict in 67.5% of cases overall and 81.3% on the unambiguous true / false / pants-on-fire buckets, with strict polar disagreement in only 4.5%. Full methodology, confusion matrix and disagreement analysis at docs/benchmark-politifact.md.

Paper review has a separate 30-case synthetic SPECS benchmark. GPT-5.4 mini, GPT-5.5, GPT-5.6 Luna and GPT-5.6 Luna Pro detected all 30 injected defects. Luna Pro returned 8% fewer findings than standard Luna, but the set reached a ceiling and does not establish accuracy on complete real-world papers.

6. Contact

Operator: Rafael de Menezes Ehlers. For takedown requests, corrections, or other concerns, use the Jiddu contact form.