io.github.xngg1021/academic-research-kernel
You can use this MCP server as a deterministic academic-research verification and evidence-state toolkit.
Validate and ingest research artifact envelopes with SHA-256 payload checks, receipt replay, content payload limits, dry-run planning, and optional initial state.
Verify receipts and resolve bibliographic/identity records into equivalence judgments.
Validate and trace lineage graphs, claim-evidence graphs, and decision ledgers, including causal ancestry and lifecycle history.
Recompute statistical results: t/F/chi-square/z p-values, effect sizes, odds/risk ratios, confidence intervals, power, sample-size/df/SD feasibility, partition conservation, ablation regularity, and storage/bandwidth bounds.
Check whether reported percentages and counts can mathematically arise from a sample size.
Probe local CUDA, ROCm, MPS, and XPU hardware/execution environments.
Lint LaTeX manuscripts for venue rules, double-blind anonymity, CEG claim bindings, and academic style; scan for anonymity leaks.
Audit tables for partition totals, constant-offset ablations, and physical storage/latency limits.
Run fixed/random-effects meta-analysis with heterogeneity, sensitivity, Egger regression, and trim-and-fill.
Normalize/verify DOIs, arXiv IDs, PMIDs, OpenAlex IDs, and Crossref/OpenAlex metadata; audit OpenReview notes/venue records offline.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.xngg1021/academic-research-kernel Generate a claim-evidence graph for this research paper"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
academic-research-kernel (v3.0.0)
Standalone scholarly verification, LaTeX submission gates, and transactional evidence state (CLI + MCP + 7 Agent Skills).
Large language models summarize papers fluently yet fail predictably on exact arithmetic and external ground truth: they repeat miscalculated $p$-values, miss rounding-impossible percentages, cite retracted or fabricated DOIs, leave author metadata inside double-blind PDFs, and lose track of which source table backs which claim.
academic-research-kernel (3.0.0) separates semantic reading from deterministic checks. Run it directly from your terminal or wire it into any MCP / SKILL.md agent workflow:
uv tool install "academic-research-kernel[research]==3.0.0"
academic-research-kernel verify-work "10.1038/nature14539" --normalize-only
# -> {"input": "10.1038/nature14539", "type": "doi", "value": "10.1038/nature14539", "canonical": "https://doi.org/10.1038/nature14539"}Empirical case study included: Reproducible SHA-256 receipts across four AI conference series and five frozen public snapshots (
74,637primary-cohort submissions across75,574raw mirror submissions,248,174official reviews; see Section 4 and peer-review-forensics-2025-2027-v1.json).
Author: Junfu Shi (SJF, xngg1021). License: Source Lineage License 1.0. Architecture: docs/kernel-architecture.md.
1. Two-Minute Quick Start: Three Entry Modes & Dependencies
Install uv, then choose how you want to invoke the kernel (Python 3.10–3.14, ~25 ms CLI cold start):
Mode A: Direct Command-Line Tool (Human Researchers, CI & Shell Scripts)
uv tool install "academic-research-kernel[research]==3.0.0"
academic-research-kernel doctor
academic-research-kernel lint-submission ./manuscript/main.tex --venue iclr --phase submissionMode B: Universal stdio MCP Server (Claude Code, Codex, Cursor, Gemini CLI)
Exposes 24 deterministic MCP tools over bounded-frame stdio JSON-RPC 2.0 (2024-11-05 through 2026-07-28):
# Claude Code CLI
claude mcp add academic-research-kernel -- uvx --from "academic-research-kernel[research]==3.0.0" academic-research-kernel mcp
# OpenAI Codex CLI
codex mcp add academic-research-kernel -- uvx --from "academic-research-kernel[research]==3.0.0" academic-research-kernel mcpMode C: Agent Skills (Hermes Agent or Any SKILL.md-Compatible Harness)
# Install the 7-skill plugin in Hermes Agent
hermes plugins install xngg1021/academic-research-kernel --no-enable
hermes plugins enable academic-skills
# Or export the standalone audit-paper skill + JSON schemas to any local folder
academic-research-kernel research skill --output ./audit-paperDependency layout: State management (SQLite STRICT + WAL), CLI dispatch, and MCP protocol control use Python's standard library, importing declared scientific and schema packages (jsonschema, numpy, scipy, statsmodels) lazily on demand. The [research] extra installs pypdf==7.0.0 and fonttools==4.65.0 for isolated subprocess PDF text/metadata scanning; details in docs/distribution-release.md.
Related MCP server: Warranted
2. Seven Workflow Skills & Task Routing
v3.0.0 consolidates all 14 legacy v2.4.2 skill directories into seven task-oriented skills:
Skill Directory | Concrete Task & Scope Boundary | Key CLI Commands & MCP Tools |
Check statistics, tables, source locators, and reproducibility checklists in an external/paired paper (emits item-level checks, not blanket truth verdicts) |
| |
Verify DOIs/metadata, monitor Crossref/OpenAlex retractions in SQLite, merge corpora, and locate legal OA PDFs (existence $\neq$ claim support) |
| |
Analyze offline OpenReview score/length/unanimity distributions and companion repos (descriptive forensics, not AI-authorship proof) |
| |
Pool fixed/random effects ( |
| |
Gate your own draft before submission: multi-file LaTeX, venue limits, double-blind PDF/source anonymity, |
| |
Coordinate live multi-model blind review, anonymous |
| |
Probe CPU/GPU/BLAS/thread environments, emit schema-validated |
|
Quick Disambiguation: Which Review/Check Skill Do I Need?
Object in Hand | Entry Skill | Primary Output |
An external paper you want to audit |
| Locator-bound statistical, table, and reproducibility check results |
Your own manuscript draft before submission |
| Format, page-limit, anonymity, and |
Published OpenReview conference records |
| Cohort score/word-count distributions and screening statistics |
A claim/spec needing live multi-model review |
| Clustered findings and SHA-bound challenge synthesis receipt |
How academic-research-kernel fits alongside peer open-source tools: Broad domain skill collections (such as Scientific Agent Skills) and discovery/RAG systems (AI-Scientist, PaperQA) focus on literature synthesis and draft generation, while specialized verifiers focus on single axes such as multi-provider bibliography GUI/CLI validation (RefChecker, evaluated on benchmarks like HALLMARK), APA test-statistic rounding (statcheck), or Claude-Code/Codex reviewer workflows (Anti-Autoresearch). academic-research-kernel focuses on a host-neutral CLI/MCP verification & SQLite state kernel that links author-side multi-file LaTeX/anonymity submission gates and auditor-side statistical, retraction, meta-analysis, and OpenReview snapshot receipts under a single transactional schema contract.
3. End-to-End Workflows, Verified Scope & Known Limits
Workflow A: Audit an External Paper, Citation List, or Meta-Analysis
# 1. Prepare a PDF/LaTeX bundle, validate extracted stats, and check table partition conservation
academic-research-kernel research prepare ./paper.pdf --project ./paper-state
academic-research-kernel research finish --project ./paper-state --candidate ./candidate.json
academic-research-kernel table-forensics --input ./table-spec.json
# 2. Verify citations, locate legal Open Access full text, and monitor retractions in SQLite
academic-research-kernel verify-work "10.1038/nature14539" --check-updates
academic-research-kernel locate-oa "10.1038/nature14539" --email "you@example.edu" --fallback-openalex
academic-research-kernel retraction-watch --dois "10.1038/nature14539" --state-db ./watch.sqlite3 --live
# 3. Pool multi-study effect sizes (fixed & DerSimonian-Laird random effects + Q / I^2 / tau^2 + Egger + trim-and-fill)
academic-research-kernel meta-analyze --input ./studies.jsonWorkflow B: Pre-Submission Gate for Your Own LaTeX & PDF Manuscript
# 1. Inspect venue rules (ICLR, NeurIPS, ICML, ACL, etc.) or export verified CEG claim anchors
academic-research-kernel check-venue --list-venues
academic-research-kernel check-venue --export-ceg-anchors ./ceg.json
# 2. Render verified JSON experiment receipts into Decimal-rounded booktabs LaTeX tables
academic-research-kernel generate-table ./results-receipt.json --caption "Main Results" --label "tab:main"
# 3. Scan multi-file TeX, BibTeX, and compiled PDF (/Info + XMP streams in isolated worker) for anonymity leaks
academic-research-kernel sanitize-submission ./submission-dir --forbidden-token "Alice Smith"
# 4. Run full pre-submission gate (nested \input/\subfile/\import, declared .bib scope, shared-page limit, CEG binding)
academic-research-kernel lint-submission ./submission-dir/main.tex \
--venue iclr --phase submission --pdf ./submission-dir/main.pdf \
--ceg ./ceg.json --require-ceg-binding --check-academic-styleDevelopment regression summary & known limitations:
On the 30-case offline development regression suite (real-world-audit-benchmark-v1.json:
16frozen-snapshot DOI/retraction cases +12published Nuijten/Bakker statistical cases +2repository gate cases),v3.0.0replaysTP = 10, TN = 6, FP = 0, FN = 0on bibliographic/retraction checks andTP = 8, TN = 5, FP = 1, FN = 0(TP = 18, TN = 11, FP = 1, FN = 0overall).Disclosed rounding limitation (
S14):recompute.pycurrently evaluates exact reported test statistics against reported $p$-value rounding intervals rather than intervalizing coarse 1-decimal test statistics (t(15) = 2.3, p = .033yields the single disclosedFP), so numerical flags require human verification of input rounding before claiming a manuscript error. In double-blind checks, generic third-party repository URLs emit reviewwarningitems rather than hard blocks unless paired with--forbidden-tokenor explicit self-repository phrasing.
4. Case Study: OpenReview Snapshots Across Four AI Conference Series (2025–2027)
Running run_peer_review_and_incidence_benchmarks.py over frozen papercopilot/paperlists@181a85021c63ab26745c42ed70a9d9ea7b57ad7e metadata mirrors (74,637 unique submissions in explicit primary cohorts across 75,574 total mirror submissions, 72,289 scored papers, and 248,174 positive official reviews; full SHA-256 receipt and excluded-track breakdowns in peer-review-forensics-2025-2027-v1.json) surfaces three descriptive snapshot patterns:
Snapshot & Explicit Primary Cohort ( | Scored Papers ($N$) | Positive Reviews (Mean / Paper) | Paper Mean Score (Valid Scale) | Review Words Median ( | Unanimous Rate ( |
ICLR 2026 (all public; | 19,454 | 74,540 ( |
|
| 8.13% ( |
ICLR 2027 (public rebuttal snapshot; | 40,801 | 126,369 ( |
|
| 23.90% ( |
ICML 2026 ( | 6,341 | 24,378 ( |
|
| 16.53% ( |
NeurIPS 2025 ( | 5,275 | 21,301 ( |
|
| 14.01% ( |
COLM 2025 ( | 418 | 1,586 ( |
|
| 7.89% ( |
*Cohort transparency: The raw nips/nips2025.json mirror (6,212 records) mixes main (5,526, including 251 opted-in public Reject), Datasets & Benchmarks (591, including 94 Reject), and Position (95, including 55 Reject and all 125 ratings > 6 across 74 Position papers); all 937 non-primary records are preserved in mirror_cohort_breakdown inside the receipt rather than dropped silently.
Scale compression, reviewer-count shift & unanimity: In
ICLR 2027(42,790submissions), compressing the scale to1–4(57.36%at score2) alongside a lower mean review count per scored paper (3.10, modal3, vs.3.83, modal4inICLR 2026) shifts the empirical-marginal independent-sampling unanimity baseline $\sum_k p_k^m$ from5.07%to19.80%under that null model alongside the observed change from8.13%to23.90%. This null-model comparison provides a structural reference rather than causal attribution of cross-year differences, and unanimous-score rates must not be equated with AI-reviewing or collusion rates.Self-reported confidence & review length: Across all four snapshots with word counts, self-reported
confidence = 2reviews have lower median word counts thanconfidence = 4reviews (328vs409inICLR 2026,298vs364inICML 2026,330.5vs409.5inNeurIPS 2025mainaccepted, and405vs451inICLR 2027). Separately,ICML 2026program chairs officially sanctioned398reciprocal-review LLM-policy violators (497desk rejections).Polarity-blind topic-mention screening (
ICLR 2026): Across19,473joined scoredICLR 2026submissions and75,769official reviews (iclr2026-openreview-incidence-receipt.json, verified againstinsomnia7/iclr2026_stats@50507ab3), regex topic screening overWeaknessesandQuestionsmatches at least one of five check families in48.2%of Oral,54.0%of Poster,59.8%of Rejected, and63.6%of Desk-Rejected papers (59.0%overall; measures topic-term mention prevalence rather than confirmed defect rate).
5. Architecture, Security Guardrails, Local QA & License
Transactional
SQLite STRICT + WALstate (state_db.py,_stdlib.py,mcp_server.py): Replaces legacy multi-file JSON lockfiles with foreign-keyedSTRICTtables,SAVEPOINTatomic batches,application_id = 0x41524B33/user_version = 4migration guards, mandatory schema validation across all26artifact kinds, single-claim outer binding target verification onquantitative_audit/evidence_receiptingestion, cycle-checked provenance graphs, and dual-sequence (applied_seq+confirmed_seq) retraction state.Untrusted PDF & network isolation (
research/sources.py,double_blind_sanitizer.py): Every PDF read executes inside a boundedpython -I -cworker subprocess (pypdf==7.0.0,fonttools==4.65.0). Outbound HTTP (controlled_urlopen) disables ambient proxies, pins resolved public DNS addresses to block DNS-rebinding TOCTOU attacks, and enforces byte caps. MCPacademic_double_blind_sanitizeredacts matched strings (matched="[REDACTED]").External API etiquette & local QA gates:
doctornever makes network calls (OPENALEX_API_KEYoptional for higher quotas;Unpaywalluses--email/UNPAYWALL_EMAILor--fallback-openalex). Legacy2.4.xCLI aliases remain supported (retraction-watch --import-legacy-json old-watch.json --state-db watch.sqlite3migrates watch files; see CHANGELOG.md).
uv lock --check
uv run --frozen --extra qa --extra research pytest -q tests
uv build --no-create-gitignore
uv run --frozen --extra qa --no-editable python -m twine check --strict dist/*
PYTHONPATH=src python -m academic_research_kernel.release_gate --package-acceptance --dist distLicense
Covered material in this repository is licensed under the Source Lineage License 1.0 (LicenseRef-Source-Lineage-1.0) within the scope stated in LICENSE-APPLICATION.md; provenance and preserved-MIT upstream boundaries (SLL-APPLICATION.json) are documented in SOURCE-LINEAGE.md, LICENSE-HISTORY.md, and REPOSITORY-IDENTITY.md. SLL 1.0 permits free academic and commercial use, modification, redistribution, and proprietary extensions provided required license and lineage notices are preserved; network service use without distributing copies does not trigger attribution obligations, and third-party files such as tests/upstream/LICENSE remain under their original licenses.
Available Tools
18 toolsacademic_check_percentageC
Check if a reported percentage and count can mathematically arise from a sample size.
Inputs: count (required), percent (required), sample_size.
academic_double_blind_sanitizeA
Read-only scan of a manuscript or reproduction directory for double-blind anonymity leaks (PDF metadata, local paths, Git credentials, unblinded acks, forbidden tokens). Never modifies files and redacts matched forbidden tokens in output.
Inputs: target_path (required), forbidden_tokens.
academic_meta_analyzeC
Run deterministic fixed-effect and DerSimonian-Laird random-effects meta-analysis, heterogeneity (Q, I2, tau2), leave-one-out sensitivity, Egger regression, and Duval-Tweedie trim-and-fill.
Inputs: studies (required).
academic_openreview_auditB
Audit OpenReview submission status, ratings, review word counts, or macro venue acceptance/rating distributions from offline notes or mirror records.
Inputs: notes, forum_id, topic_regex, venue_records.
academic_pre_submission_lintB
Audit a LaTeX manuscript against venue formatting rules, required sections, double-blind package options, statistical dispersion, CEG claim bindings, and optional academic prose style checks.
Inputs: tex_path (required), phase, venue, ceg_path, +4 more.
academic_recompute_statisticsB
Recompute t/F/chi2/z p-values, two-group Cohen's d and Hedges' g, 2x2 OR/RR, CI consistency, statistical power, SD bounds, and df-implied sample sizes. Optional reported p-value comparison uses decimal round-half-up intervals; input or partial execution failures are tool errors, statistical mismatches are successful results.
Inputs: df, n1, n2, se, +61 more.
academic_scfabric_hardware_probeB
Probe local hardware accelerators (CUDA, ROCm, MPS, XPU) and execution environments.
Inputs: no named parameters.
academic_table_forensicsC
Audit AI/CS paper tables for partition conservation, constant-offset ablation regularity, and physical storage/bandwidth lower bounds.
Inputs: partition, ablation_tol, ablation_matrix, ablation_min_rows, +2 more.
academic_verify_sourceB
Normalize scholarly identifiers (DOI, arXiv, PMID, PMCID, OpenAlex) and cross-verify metadata across OpenAlex and Crossref records.
Inputs: identifier (required), offline, normalize_only, crossref_record, +1 more.
claim_evidence_traceB
Trace all supporting and refuting evidence anchors and attached receipts for a given claim.
Inputs: graph (required), claim_id (required), receipts, content_payloads.
claim_evidence_validateB
Validate the structural integrity, cycles, and cryptographic receipt bindings of a ClaimEvidenceGraph snapshot.
Inputs: graph (required), receipts, content_payloads.
decision_ledger_validateC
Execute complete four-gate verification over a Decision Ledger export dictionary.
Inputs: ledger (required), receipts, content_payloads.
decision_traceB
Trace causal ancestry, basis dependencies, outcome corrections, and lifecycle state history for a decision.
Inputs: ledger (required), decision_id (required), receipts, content_payloads.
research_artifact_ingestC
Deterministically ingest a scholarly artifact envelope into kernel state (ResearchObjects, CEG, and Ledger).
Inputs: envelope (required), state, dry_run, bindings, +1 more.
research_artifact_validateC
Validate a ResearchArtifactEnvelope against its schema and verify its cryptographic payload SHA-256 without side effects.
Inputs: envelope (required), state, bindings, receipts, +1 more.
research_lineage_traceC
Trace backward provenance ancestry for a specified entity within a LineageGraph snapshot.
Inputs: lineage_graph (required), target_entity_id (required).
research_object_resolveC
Resolve and aggregate candidate bibliographic/identity records into discrete five-state equivalence judgments.
Inputs: records (required).
research_receipt_verifyC
Verify an AcademicEvidenceReceipt or LineageReceipt against a strongly typed ReceiptRef.
Inputs: receipt_ref (required), receipt_payload (required), content_payloads.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools are clearly separated by target resource: artifacts, receipts, objects, lineage graphs, claim-evidence graphs, decision ledgers, and academic auditing tasks. There is some conceptual overlap between research_artifact_validate, claim_evidence_validate, and decision_ledger_validate, and between the various trace tools, but the descriptions make the distinct domains reasonably clear.
Names consistently use snake_case with domain-prefixed namespaces such as research_, claim_evidence_, decision_, and academic_. The pattern is generally predictable, though action ordering varies slightly between entity_action forms like research_artifact_validate and academic_verify_source.
Eighteen tools is slightly above the ideal compact range, but the server covers a broad academic research kernel with validation, lineage, statistics, manuscript auditing, and meta-analysis. Each tool appears to serve a distinct purpose rather than duplicating functionality.
The surface covers validation, ingestion, tracing, receipt verification, statistical recomputation, manuscript linting, source verification, and meta-analysis, which is substantial for the apparent verification/audit domain. There are minor gaps around creation/update/query utilities for research objects, but the core lifecycle is well represented.
Maintenance
Related MCP Connectors
Plan and verify evidence-aware research workflows with specialist execution receipts.
Deterministic research automation with live OpenAlex search and reusable workflow programs.
Machine-native research commons for agent evidence, discovery, rooms, and bounded research quests.
Shared workspace for AI artifacts: your agents publish, search and cite each other's work.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn autonomous academic research and publishing platform that enables AI agents to submit papers, conduct peer reviews, and manage scholarly reputations. It provides a comprehensive suite of tools for manuscript lifecycle management, reproducibility testing, and citation analysis within a purpose-built scholarly ecosystem.25MIT
- AlicenseNot gradedqualityBmaintenanceMakes AI research agents accountable by giving every conclusion a traceable argument graph. Provides a persistent argument graph where claims require grounds and warrants for auditable, verifiable reasoning.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables creation and invocation of reusable research workflow programs derived from demonstrations, with live scholarly data search and workspace automation via multiple protocols.MIT
- AlicenseNot gradedqualityCmaintenanceGives existing agents controlled access to a local Neo4j research memory, letting them import papers and notes, record models, experiments, evidence and decisions, search full text plus graph neighbors, and resume bounded research sessions with checkpoints and provenance. Twelve stdio tools and seven companion skills turn reading, extraction and handoffs into auditable, revision-checked records.3MIT