Verify claims against the corpus
verify_claimsFact-check 1 to 25 natural-language claims against a peer-reviewed corpus in one call. Each claim receives a verdict with a verified quote, confidence, and reasoning.
Instructions
Fact-check 1 to 25 natural-language claims against Lune's peer-reviewed corpus in ONE call. For each claim the server retrieves the most relevant passages and an LLM judges the claim ONLY against those passages (never outside knowledge), returning one verdict per claim: supported, unsupported, or insufficient_evidence. Use this to ground a draft before you assert it, to vet a user's claim, or to check your own answer against the literature instead of stating things from memory. Every verdict carries a verbatim_quote copied EXACTLY from a retrieved passage (or null when nothing could be quoted, e.g. an insufficient_evidence verdict) plus supporting_paper_ids (the corpus papers the verdict relied on); both are verified server-side, the quote is guaranteed to be a real substring of a retrieved passage and the ids are guaranteed to be real retrieved candidates, so you can cite the quote directly without re-checking. Also returns a confidence (0..1) and short reasoning per claim. Filters (conference, year, year_min, year_max, venues) scope the evidence search and are shared across every claim; context is optional shared framing for the judge. paper_ids are fetch handles for get_paper_fulltext, not for showing to the user, cite papers by title, authors, and venue.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| year | No | Restrict the evidence search to a single publication year. | |
| claims | Yes | 1 to 25 natural-language factual claims to fact-check against the corpus in ONE call. Phrase each as a complete, self-contained assertion (e.g. "LoRA fine-tuning matches full fine-tuning on GLUE while training far fewer parameters"), not a keyword bag. Each claim is retrieved and judged independently, so you get one grounded verdict per claim. | |
| venues | No | Restrict the evidence search to these conference short names (e.g. ["NeurIPS", "ICML"]). Shared across every claim. | |
| context | No | Optional shared framing passed to the judge for every claim, e.g. the surrounding paragraph or the question the claims answer. Use it to disambiguate terse claims; it does not change what is retrieved. | |
| year_max | No | Restrict the evidence search to this publication year or earlier. Shared across every claim. | |
| year_min | No | Restrict the evidence search to this publication year or later. Shared across every claim. | |
| conference | No | Restrict the evidence search to this conference short name, e.g. "CCS", "NeurIPS". Shared across every claim. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| verdicts | Yes | One grounded verdict per input claim, in input order. | |
| claims_processed | Yes | Total claims judged; equals verdicts.length. |