docxology

Maintain and extend the docxology public GitHub Pages static site (danielarifriedman.com)

We study a minimal Active Inference stack on toy models: a Bernoulli–Ising analytical oracle, a pymdp T-maze rollout, and a sheaf-indexed compose contract that binds 34 fragment tracks into 12 flat IMRAD sections. The methodological contribution is a...

<p>Synthetic Analytic Tradecraft (AGEINT, or Agentic Intelligence), is a local curriculum-and-assurance atlas for teaching bounded AI-agent support inside intelligence education by making the machinery of Synthetic Analytic Tradecraft visible on the ...

Use for Autopoietic Project Generation, a paired GitHub and Zenodo publication with DOI 10.5281/zenodo.21227869.

CogSecSkills is a defensive, harness-neutral agent-interface library that turns the human doctrine of cognitive security and analytic tradecraft into dependable, inspectable, agent-usable skills, distributed as an open repository from github.com/docx...

This paper presents a convergence study of fixed-step gradient descent on a convex quadratic, framed as the computational exemplar of the Research Project Template (https://github.com/docxology/template). The implementation lives in projects/template...

This paper describes a small, tested domain language for specifying controlled methods — the methods-paper exemplar of the Research Project Template (https://github.com/docxology/template). Unlike a results paper, this manuscript's subject is the met...

Use for DuckRabbit: Typed Multimodal Illusion Generator, a paired GitHub and Zenodo publication with DOI 10.5281/zenodo.21419693.

METAINFORMANT rules for directory config/amalgkit. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

METAINFORMANT rules for directory config/config_base. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

METAINFORMANT rules for directory config/eqtl. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

METAINFORMANT rules for directory config/gwas. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

METAINFORMANT rules for directory config/life_events. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

METAINFORMANT rules for directory config/longread. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

METAINFORMANT rules for directory config/multiomics. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

METAINFORMANT rules for directory config/ncbi. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

Skill for the core infrastructure module providing logging, configuration, exception handling, progress tracking, checkpoints, retry logic, pipeline execution, performance monitoring, security, file operations, and multi-project orchestration. Use when setting up logging, loading config, handling errors, running pipelines, or monitoring performance.

Skill for the documentation infrastructure module providing figure management, image handling, markdown integration, and API glossary generation. Use when managing research figures, inserting images into manuscripts, auto-numbering figures, or generating API documentation.

Skill for the LLM infrastructure module providing local Large Language Model integration via Ollama. Covers client initialization, prompt templates, output validation, manuscript review generation, conversation context, and CLI usage. Use when querying LLMs, generating manuscript reviews, validating LLM outputs, or managing Ollama models.

Python CLI and menu orchestration for pipeline runs — project slug validation, interactive picker, PipelineRunner wrapping PipelineExecutor, per-stage logs, secure pipeline wrapper. Use when extending run.sh behavior, fixing menu/CLI routing, or testing discovery helpers.

Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.

Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub Pages / Cloudflare Pages / Netlify, multi-target long-horizon archival (IPFS Pinata, Web3.Storage, Software Heritage), a central platform registry, and publication readiness validation. Use when publishing research, generating citations, minting DOIs, distributing Python packages, deploying documentation sites, or preparing archival submissions.

Skill for the rendering infrastructure module providing multi-format output generation including PDF manuscripts, HTML web pages, and Beamer/Reveal.js slides. Use when rendering research outputs, converting markdown to PDF, generating slides, or configuring LaTeX rendering.

Skill for the reporting infrastructure module providing pipeline reporting, error aggregation, executive summaries, dashboard generation, test reporting, and multi-project reports. Use when generating build reports, aggregating errors, creating visual dashboards, or producing executive summaries across projects.

Distinguish manufactured grassroots activity from organic engagement.

Map which beliefs of a target audience are most exposed to manipulation and why.

Segment an audience by susceptibility to specific manipulation vectors (defensive use).

Stage a cognitive attack (recon→delivery→exploitation→persistence) to plan defenses per stage.

Scan an analysis or decision for the specific biases most likely to distort it.

Design ethical counter-messaging that corrects without amplifying the original falsehood.

Triage suspected synthetic media for tell-tales and provenance signals (defensive, non-forensic).

Decompose a campaign's objectives, narratives, TTPs, and amplification structure.

Linguistic case formally typed as an analytic category — CaseRole, Morphism, AlignmentFunctor, MonoidalFunctor, Natural Transformations. Crucial for §2 core topology, downstream §7c DAIF alignment, and §9b adversarial injection formal verification.

Scalar active inference on case diagrams — beliefs, variational free energy, belief updates, prediction error, EFE, N400/P600 proxies. Use for §7; use src.daif for distributional returns and full ERP pipeline (§7c).

Distributional Active Inference — push-forward returns, quantile/IQN updates, VMP/Bethe FE, distributional case assignment, policy G(π), ERP profiles, convergence metrics. Use for manuscript §7c and quantitative DAIF results.

DisCoCat/DisCoCirc-style string diagrams, complexity metrics, ditransitive constructions, discourse-level prompt scanning. Use for manuscript §3–§4c (and cross-links to §5b magnitude homology metrics, §9b protocol-level checks where `Discourse` is used).

[0,1]-enriched categories, standard proximity matrix, categorical magnitude helpers. Use for §5 distributional proximity and enrichment that feeds cognitive/security modules.

POVM-based quantum case assignment — CasePOVM, case probabilities, crisp/graded/fluid-S POVM factories, semantic state helpers. Use for §8 and §8b quantum semantics.

Cognitive security — type violations, CaseFrameValidator, injection scoring, topological robustness, semantic integrity. Use for §9b adversarial and type-checking narratives.

Hub skill for cognitive_case_diagrams Layer-2 src — case categories, diagrams, enriched/topos semantics, scalar and distributional active inference, quantum POVMs, security validators, and figure generation. Use when editing or importing from projects/cognitive_case_diagrams/src.

Full-spectrum coding workspace skill providing ~610 production MCP `@mcp_tool` lines across 130 top-level modules. USE WHEN user says 'verify codomyrmex', 'codomyrmexVerify', 'audit codomyrmex', 'trust codomyrmex', 'codomyrmexTrust', 'trust tools', 'enable destructive tools', 'check pai status', 'codomyrmex tools', 'codomyrmex analyze', 'codomyrmex search', 'codomyrmex memory', 'codomyrmex docs', 'codomyrmex status', 'codomyrmex git', 'codomyrmex security', 'codomyrmex ai', 'codomyrmex code', 'codomyrmex data', 'codomyrmex deploy', 'codomyrmex test', or uses any 'codomyrmex' automation tools.

Full-spectrum coding workspace skill providing 610 production MCP `@mcp_tool` lines across 129 top-level modules. USE WHEN user says 'verify codomyrmex', 'codomyrmexVerify', 'audit codomyrmex', 'trust codomyrmex', 'codomyrmexTrust', 'trust tools', 'enable destructive tools', 'check pai status', 'codomyrmex tools', 'codomyrmex analyze', 'codomyrmex search', 'codomyrmex memory', 'codomyrmex docs', 'codomyrmex status', 'codomyrmex git', 'codomyrmex security', 'codomyrmex ai', 'codomyrmex code', 'codomyrmex data', 'codomyrmex deploy', 'codomyrmex test', or uses any 'codomyrmex' automation tools.

A powerful orchestration skill for breaking down high-level objectives into hierarchical task graphs and resolving them through isolated multi-agent execution in dedicated worktrees.

Full-spectrum coding workspace skill — PAI MCP bridge, ~600 production @mcp_tool lines, trust/verify workflows. USE WHEN user says verify codomyrmex, codomyrmexTrust, audit tools, codomyrmex tools, or any codomyrmex automation surface.

Recursive task decomposition with git worktrees per leaf; MCP tool orchestrate_fractal_task. USE WHEN the user needs fractal orchestration, isolated worktrees for parallel subtasks, or massive composite goals that need hierarchical planning.

Improves codebase quality via the desloppify CLI — install, exclude noise, scan, and drive the next/resolve execution loop to raise strict score. Use when the user invokes /desloppify, asks for tech-debt cleanup, desloppify, strict score, or codebase health scanning.

Improves codebase quality via the desloppify CLI — install, exclude noise, scan, and drive the next/resolve execution loop to raise strict score. Use when the user invokes /desloppify, asks for tech-debt cleanup, desloppify, strict score, or codebase health scanning.

Core inference logic, prompt construction, and RDF/Nanopublication serialization.

Core orchestration guidelines and MCP interactions for the src/ library.

Literature meta-analysis exemplar — multi-engine retrieval, dedup, full-text, bibliometrics, embeddings, optional knowledge graph. Default term: modafinil.

Orchestration for bibliometrics, topological network analysis, and hypothesis scoring.

Operations for federated API querying across OpenAlex, Semantic Scholar, and arXiv.

Tooling for injecting JSON/CSV statistics into Markdown evaluation templates.

Orchestrates matplotlib and seaborn pipelines for rendering figures.

Extend the typed multimodal audio, image, video, and audiovisual illusion generator.

Modular fillable textbook scaffold — parts/chapters/labs/question banks from config.yaml, auto-numbering, deterministic figures, structural contract enforcement.

Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.

SIA (Self-Improvement Agent) harness exemplar — Meta/Target/Feedback loops, public/private splits, fixture replay, fail-closed validation.

Registered-report exemplar for preregistration locking, deviation ledgers, replication, and confirmatory claim boundaries.