Research

Research from SamyakJhaveri/loam.

by @samyakjhaveri 18 skills

Skills in this plugin

18
  1. ▌
    Eval Run · samyakjhaveri
    Launches a model evaluation batch with parameter collection, pre-flight checks, execution, and post-run analysis for interactive or foreground runs.
    0 repo stars
  2. ▌
    Rebuttal · samyakjhaveri
    Parses external reviews, enforces coverage and grounding, and drafts a text-only rebuttal under venue limits, managing follow-up rounds.
    0 repo stars
  3. ▌
    Post Eval · samyakjhaveri
    Runs a post-batch analysis pipeline after an eval completes: verifies results, executes analysis scripts, refreshes dashboards, and writes a summary report.
    0 repo stars
  4. ▌
    Cite Check · samyakjhaveri
    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.
    0 repo stars
  5. ▌
    Experiment · samyakjhaveri
    Orchestrates structured experiments end-to-end: initialize, plan, run, and evolve with reproducibility tracking and hypothesis validation.
    0 repo stars
  6. ▌
    Eval Grader · samyakjhaveri
    Grades and classifies evaluation batch results, applying exclusions, diagnosing failure modes, computing pass rates, and generating summary tables for papers.
    0 repo stars
  7. ▌
    Paper Write · samyakjhaveri bundle
    Drafts a LaTeX paper section by section from an outline, with venue-specific templates and citation management.
    0 repo stars
  8. ▌
    Augment Test · samyakjhaveri
    Runs a data augmentation pipeline on a given input and reports pass/fail per transform, diagnosing failures against known issues.
    0 repo stars
  9. ▌
    Citation Audit · samyakjhaveri
    Verifies every bibliographic entry in a paper for existence, metadata accuracy, and contextual support using web/DBLP/arXiv lookups, flagging hallucinated authors, wrong years, fabricated venues, and misattributed citations.
    0 repo stars
  10. ▌
    Grill Research · samyakjhaveri
    Interrogates research plans before evals or published claims, forcing explicit null hypotheses, confound checks, and data verification across four review waves.
    0 repo stars
  11. ▌
    Overnight Eval · samyakjhaveri
    Launches long-running evaluation batches in isolated tmux sessions with pre-flight verification, monitoring, and post-flight analysis for unattended runs.
    0 repo stars
  12. ▌
    Hypothesis Tree · samyakjhaveri
    Structured hypothesis tree manager for multi-step investigations. Use when a "why does X fail" question branches into sub-hypotheses, when an investigation spans several sessions and the reasoning must survive between them, or when falsifiable claims need tracking with linked evidence and dates. Maintains one markdown file with add, update, review, and prune subcommands, each gated on verifying that the cited evidence file actually exists and actually says what the claim says. NOT for a single-session bug hunt, a question answerable by one command, or as a general note-taking file.
    0 repo stars
  13. ▌
    Paper Review Sim · samyakjhaveri
    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.
    0 repo stars
  14. ▌
    Hpc Code Reviewer · samyakjhaveri
    Reviews CUDA, OpenMP, and OpenCL code for parallel correctness, covering data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls.
    0 repo stars
  15. ▌
    Interpret Results · samyakjhaveri
    Analyzes evaluation results by requiring a stated hypothesis before examining data, then compares expectations to actual result files to prevent post-hoc rationalization.
    0 repo stars
  16. ▌
    Paper Claim Audit · samyakjhaveri
    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.
    0 repo stars
  17. ▌
    Cuda Omp Translator · samyakjhaveri
    Reference guide for evaluating LLM-generated translations between CUDA and OpenMP, covering memory model mapping, kernel launch patterns, shared memory, atomics, and common failure modes.
    0 repo stars
  18. ▌
    Auto Paper Improvement Loop · samyakjhaveri
    Iteratively improves a compiled LaTeX paper through two rounds of external LLM review, fix implementation, and recompilation.
    0 repo stars