Results for “ir-evidence”

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

Drafts U.S. internal legal memoranda using IRAC structure to analyze issues, synthesize authority, assess risks, and recommend strategy. Use when asked to draft a research memo, internal memo, issue analysis, case strategy memo, or any IRAC-based legal analysis.

Orchestrates evidence-based research across local PDFs, scholarly search, citation-context tools, web sources, and code repositories to produce traceable syntheses with counterevidence audits.

research-synthesis

Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.

Routes UI evidence, comparisons, critiques, references, best practices, and design research to one research workflow.

Verify the article’s factual, product, citation, and link integrity before visual production.

Interrogates research plans before evals or published claims, forcing explicit null hypotheses, confound checks, and data verification across four review waves.

Verifies that every number, comparison, and scope claim in a research paper matches raw result files, using a fresh cross-model reviewer with no prior context to prevent confirmation bias.

Retrieve deterministic search results, metadata, and full-document Markdown from arXiv, PubMed/PMC, and US policy corpora with daily freshness checks.

Audits a paper draft by tracing every numeric claim and assertion back to result files on disk, flagging untraced, mismatched, stale, uncited, and phantom references.

Verify academic citations against CrossRef, Semantic Scholar, and OpenAlex. Detects AI-hallucinated references, chimeric citations, and suspicious patterns.