Open Issues Need Help
View All on GitHub chore(ci): add one canonical verifier and require deterministic checks about 2 months ago
documentation enhancement help wanted area: deploy priority: high
enhancement help wanted area: pipeline area: llm priority: medium
chore(dev): make contributor workflows agent-neutral and documentation source-generated about 2 months ago
documentation enhancement help wanted area: deploy area: cli priority: medium
bug help wanted area: pipeline priority: medium
fix(cli): isolate subscription reviewers from ambient agent tools and configuration about 2 months ago
bug help wanted area: llm area: cli security priority: high
Add a higher-quality OCR fallback than Docling about 2 months ago
enhancement help wanted area: extraction priority: low experimental
roadmap: evidence-first Deep Agent, Lean verification, and open evaluation about 2 months ago
enhancement help wanted priority: high roadmap
feat(input): support supplementary documents with source-aware retrieval about 2 months ago
enhancement help wanted area: extraction area: pipeline area: web priority: medium experimental
feat(models): add GLM-5.3 and GLM-5.3 Flash with capability tests about 2 months ago
enhancement help wanted area: llm area: web priority: medium experimental
feat(pipeline): persona-diverse section ensemble about 2 months ago
enhancement help wanted area: pipeline priority: medium
feat(pipeline): claim graph pre-pass and wire orphaned check_assumptions / ContradictionCheckAgent about 2 months ago
enhancement help wanted area: pipeline priority: medium
feat(pipeline): multi-specificity literature retrieval loop about 2 months ago
enhancement help wanted area: pipeline priority: medium
epic(formal): Lean-assisted proof verification for research papers about 2 months ago
enhancement help wanted area: pipeline priority: medium roadmap area: formal verification experimental
enhancement help wanted area: pipeline priority: medium area: formal verification experimental
test(formal): benchmark Lean faithfulness, routing, and alpha usefulness about 2 months ago
enhancement help wanted priority: high area: evaluation area: formal verification experimental
feat(formal): add honest review statuses and UI for Lean evidence about 2 months ago
enhancement help wanted area: pipeline area: web priority: medium area: formal verification experimental
feat(agent): add a bounded tool runtime, paper context broker, and evidence ledger about 2 months ago
enhancement help wanted area: pipeline area: llm priority: high experimental
feat(web): add revision-check workflow backed by review-to-revision evidence about 2 months ago
enhancement help wanted area: pipeline area: web priority: medium experimental
feat(formal): freeze theorem statements and enforce semantic faithfulness about 2 months ago
enhancement help wanted priority: high area: formal verification experimental
feat(formal): add a persistent proof DAG and paper-path verification loop about 2 months ago
enhancement help wanted priority: medium area: formal verification experimental
feat(formal): build pinned Lean/Mathlib domain packs and agent tools about 2 months ago
enhancement help wanted area: deploy priority: medium area: formal verification experimental
feat(eval): add SPOT, SPECS, and ReviewBench adapters with top-K scoring about 2 months ago
enhancement help wanted priority: medium area: evaluation experimental
feat(eval): run exact same-model frontier-max harness ablations about 2 months ago
enhancement help wanted area: llm priority: high area: evaluation experimental
fix(web): replace unsupported comparison claims with reproducible evidence about 2 months ago
bug help wanted good first issue area: web priority: high area: evaluation
feat(eval): add reproducible run manifests and blind expert adjudication about 2 months ago
enhancement help wanted area: pipeline priority: medium area: evaluation
feat(eval): add stage-local GEPA optimization with Pareto held-out gates about 2 months ago
enhancement help wanted area: llm priority: medium area: evaluation experimental
feat(eval): build a review-to-revision substantive-uptake benchmark about 2 months ago
enhancement help wanted priority: medium area: evaluation experimental
feat: support non-English papers and reviews 5 months ago
enhancement help wanted area: pipeline area: llm priority: medium
enhancement help wanted area: cli priority: low
perf(extraction): benchmark cheaper host models for OpenRouter file-parser pass-through 5 months ago
enhancement help wanted area: extraction area: llm performance priority: low
Add OAuth integrations 6 months ago
enhancement help wanted area: web priority: low
documentation enhancement help wanted good first issue area: cli priority: low
feat: Progress indicators when running from the cli 6 months ago
enhancement help wanted good first issue area: cli priority: low
chore: add codex-native review commands 6 months ago
enhancement help wanted area: cli priority: low
can not open codex in windows 10 6 months ago
bug help wanted area: cli priority: low