Research / Research Automation

RESEARCH PROGRAMME

AutoResearch

Leave a trail. Keep research moving.

From worthwhile questions to research that can continue.

AutoResearch brings question discovery, literature preparation, idea exploration, critical review, structural recombination and evidence communication into one research programme. Each module retains its own responsibilities and maturity.

Original AutoResearch concept illustration: a question, evidence cards and research actions.
Questions, sources and actions belong to one line of inquiry.

Connected research workstreams

Each workstream has its own responsibility, implementation status and entry. Their relationships are introduced here; each tool keeps its own version record.

Wenjie · Hilbertforge

01 / Question discovery and research portfolios

Wenjie · Hilbertforge

Before choosing a solution, establish why an opportunity deserves pursuit and produce a question with a minimally discriminating envelope.

Architecture and protocol design · v1.0 package

Read the full introduction
Daedalus concept artwork

02 / Idea and research-action exploration

Innovation Generator · Ariadne

Move from questions, primary text and rivals to subsequent actions in a bounded loop of proposals, host observations and failure records.

Structural transfer and tool synthesis · current v7.4.0

Read the full introduction
Lancer Fusion

03 / Structural recombination of questions and ideas

Lancer Fusion

Compile multiple parents into scientific graphs, make bridges and necessity explicit, and select one inspectable fused result.

Standalone structural-kernel prototype · v0.2.0

Read the full introduction
Research Hub

04 / Evidence workbench and frozen experiments

Research Hub

Connect assets, literature, candidates, refutation and experiments, preserving progress through provenance and state.

Local workspace and bounded experimental loop

Read the full introduction
LSMFC

05 / Evidence-constrained manuscript and figure compilation

LSMFC

Give prose, figures, captions and conclusions one factual basis, with dependency checks after experiments change.

CPU-first toolchain · v2.0.0

Read the full introduction
Themis Court

06 / Contribution review & author-guided writing

Themis Court

The contribution-review and writing module in AutoResearch, connecting lens routing, independent critique, evidence profiles, and deterministic checks with research taste and author-guided writing.

v14.3.0-alpha · Offline scaffold

Read the full introduction
Literature Review

07 / Literature & evidence preparation

Literature Review

A structured route through source discovery, record processing, staged screening, thematic synthesis, and citation review, supporting evidence preparation within AutoResearch.

Workflow & utilities · K-Dense toolkit

Read the full introduction
InkTide original editorial artwork

WRITING & FIGURES

InkTide

InkTide brings inspected paper lessons, author evidence, original prose and figure design into a connected writing workflow, with a separate review of the result.

Explore the module →

PROGRAMME / REFERENCE MAP

Different tools. One line of inquiry.

A map of responsibilities. The catalogue includes design protocols, local tools and external utilities; it does not imply a single deployed runtime.

Connecting the stages

01Question & literature02Ideas & criticism03Experimental evidence04Prose & figuresQuestions can return to any stage as evidence changes.
Dashed connections show conceptual handoffs. The modules are not one deployed runtime.Swipe to inspect the full diagram.

Wenjie certificates provide value goals and discriminating envelopes; the Innovation Generator explores concrete mechanisms and subsequent actions.

Fusion can recombine parents, but its necessity predictions require experiments and independent review.

Research Hub records sources, frozen plans, observations and failures; LSMFC compiles manuscripts and figures from checked claims and facts.

Teaching and human understanding are parallel goals. The architecture keeps responsibilities independent; teaching satisfaction is not agent experimental gain, and the full teaching service remains unintegrated.

Literature Review prepares traceable sources; Themis Court examines contribution identity, evidence and objections. These are proposed handoffs, with runtime integration still to be verified.

Question discovery and research portfolios

01使命与三界态势Mission and worldsnapshot02问题发生器Question generators03问题证书与预检Certificate and preflight04独立盲评Independent blind review05互补问题组合Complementary portfolio
Public question-design responsibilities; implementation status remains as described.Swipe to inspect the full diagram.

Wenjie · Hilbertforge

Decide what to investigate

Mission, knowledge, capabilities and needs constrain pursuitworthiness. The proposed initial generators examine contradictions, assumptions, measurement needs, capability changes, social needs and negative results. Coverage certificates and prior-work collisions test opportunities. Discovery preserves alternative solution space rather than choosing an algorithm before seeking an application.

Question certificates and portfolio selection

Question certificates state the target, value, rivals, minimal test and resources. Preflight and blind review precede Pareto and quality-diversity portfolio selection, followed by human retention. Teaching and review subscribe independently and cannot write each other’s judgements. Certificates can feed idea discovery; the Eulerforge handoff name in the original design is a historical interface.

Current delivery and integration role

The local package contains architecture, Question Card schema, event contracts and review rules. Its first vertical slice is described as a proposed implementation. It therefore contributes a design workstream for question value and experimental envelopes rather than a deployed opportunity-discovery service. Integration should preserve the distinction between question selection and mechanism search.

Read the full introduction

Idea and research-action exploration

01Ground the question找到真正的问题02Open the search展开不同可能03Ask for evidence让批评有依据04Make a real revision让想法实质改变05Compare and calibrate比较,也校准06Test the strongest claim追问最强的主张07Leave a research dossier交付可检验的方向
Evidence and criticism change the next research action. Conceptual workflow.Swipe to inspect the full diagram.

Innovation Generator · Ariadne

Explore the next discriminator

Evidence-guided search, substantive revision and testable research dossiers within AutoResearch.

How current results shape later design

Evidence-guided search, substantive revision and testable research dossiers within AutoResearch.

Hand off to experiments and structural recombination

Outputs are candidates with mechanisms, predictions, precedents, actions and states, plus exploration records that can inform experiment contracts or Fusion parents. Acquisition is not a causal experiment, and one discriminating probe does not automatically confirm a mechanism. Host observations and independent review receive these objects; open-domain interfaces still need implementation domain by domain.

Read the full introduction

Structural recombination of questions and ideas

01亲本问题或解法Parent questions or ideas02类型化科学图Typed scientific graphs03映射与 BridgeMappings and bridge04FusionDSL操作FusionDSL operations05验证与必要性Verification andnecessity06结果与血缘Selected result andlineage
Structural inspection and scientific-effect experiments are distinct stages.Swipe to inspect the full diagram.

Lancer Fusion

Find structure, then verify the combination

The engine accepts 2–N questions or ideas, compiles typed structures, searches mappings and Generic Space, and establishes a Fusion Contract. A load-bearing Bridge connects to constrained FusionDSL, followed by type, scope, logic, interface and evidence checks. Problem and idea fusion share a kernel but use different conflict semantics and objectives.

One result with complete lineage

Each stage of the multi-parent tree checks A, B and Bridge necessity. Accepted candidates enter a Pareto/quality-diversity archive; the product returns one selected card. Mappings, failures, repairs and witnesses remain inspectable through CLI, API and local UI. Potential grades, structural levels and evidence maturity are separate, and target grades are goals rather than guarantees.

Independent experiments follow structural admission

v0.2.0 provides deterministic structural execution, immutable traces and contract smoke tests. Real prior-art retrieval, domain experiments, trained semantic providers, independent review and sign-off remain external boundaries. Within the programme it recombines candidate mechanisms; bridge and parent ablations, ordinary combinations and matched-budget experiments test substantive gains.

Read the full introduction

Evidence workbench and frozen experiments

01文献与资产Literature and assets02问题与实验合同Question and experimentcontract03冻结模块执行Frozen-module execution04反驳与留出测试Refutation and held-outtests05复算、状态与学习Recalculation, state andlearning
Sources, frozen experiments and evidence states retain their relationships.Swipe to inspect the full diagram.

Research Hub

A shared entry with distinct evidence states

The workbench unifies source records, skill reviews, engineering maturity and research judgements while retaining reading depth, versions, inactive historical sources and originals. Status, search, source, verification and assessment operations expose provenance and benchmark adequacy. A PDF, extracted text or valid hash does not imply completed semantic reading.

Frozen modules and improvement headroom

Runs invoke registered frozen local modules rather than arbitrary shell commands and write new directories preserving existing evidence. Contracts lead into training or policy compilation, refutation, whole-family tests and recalculation. A capacity diagnosis shows the original threshold is unattainable in a fixed policy library, motivating headroom preflight. Execution checks can pass while a scientific effect remains unidentified.

Workspace and platform integration status

A local research process has run, but historical engines, review, Fusion, teaching, clients and distributed services are not one integrated product. Research Hub therefore supplies the evidence and experiment workstream, using integration audits to separate reusable mechanisms, historical checks and unfinished interfaces. Recursive self-improvement requires changed actions, full-cost unseen-task comparisons and independent promotion.

Read the full introduction

Evidence-constrained manuscript and figure compilation

01研究事实与证据Research facts andevidence02AVIR 与诊断AVIR and diagnosis03故事与图联合规划Joint story–figureplanning04论文编译Manuscript compilation05图形编译Figure compilation06交叉核查与发布包Cross-checks and releasebundle
Writing and figures share author evidence, then meet cross-checking.Swipe to inspect the full diagram.

LSMFC

Register facts before compiling expression

Theory, methods, code mappings, experiments, literature and visual evidence enter shared registries and seven-layer AVIR. Central claims require evidence, warrants, assumptions and potential defeaters. Diagnosis leads to joint story–figure planning, separate manuscript and figure compilation, then checks that modalities support the same claims.

Dependency propagation and the visual firewall

Experimental changes mark related claims, paragraphs, figures and sign-offs stale, returning them to checks. Source and sentence-level provenance travel with artefacts. Visual refinement may change expression but not data, statistics, coordinates or scientific relationships. Research gaps generate upgrade tasks; language providers cannot introduce facts, numbers, citations or broader scope.

From checkable findings to a release bundle

v2.0.0 provides CLI, API, a local workbench, review and human sign-off, plus manuscripts, editable vectors and auditable release bundles. It is a non-training toolchain without dedicated model-training or cluster infrastructure. As the programme’s delivery workstream it receives checked facts and claims; polished writing and demo builds do not establish scientific validity.

Read the full introduction

v14.3.0-alpha · Offline scaffold

Research artifact研究材料Clerk书记官Object + lens + fieldScout检索官Claims + quotes + coverageProsecutor控方Advocate辩方Insider领域内行Blind Probe盲探针Problem onlyEvidence checks卷宗与证据检查Evidence profile → score map证据画像 → 独立评分
An offline role-design scaffold; real-paper validation remains pending.Swipe to inspect the full diagram.

Themis Court

The contribution-review and writing module in AutoResearch, connecting lens routing, independent critique, evidence profiles, and deterministic checks with research taste and author-guided writing.

For author-side self-audit, laboratory discussion, and research education. Current checks use offline fixtures; real-paper First Flight, live retrieval, substantial calibration, and blinded evaluations remain pending.

Read the full introduction

Workflow and supporting utilities

Question & criteria问题与标准01 / RESEARCH JUDGMENTSource discovery多源发现02 / EXTERNAL TOOLSExported records导出记录03 / ARTIFACTRecord processing记录处理04 / LOCAL UTILITYStaged screening分层筛选05 / RESEARCH JUDGMENTExtract & assess提取与评估06 / RESEARCH JUDGMENTThematic synthesis主题综合07 / RESEARCH JUDGMENTDOI metadata checkDOI 复核08 / LOCAL UTILITYCompare & revise对照与修订09 / RESEARCH JUDGMENTReview document综述文档10 / ARTIFACTCompare · revise · recheck对照 · 修订 · 重新核查
Discovery, screening and synthesis; metadata checks do not verify every scientific claim.Swipe to inspect the full diagram.

Literature Review

A structured route through source discovery, record processing, staged screening, thematic synthesis, and citation review, supporting evidence preparation within AutoResearch.

This page describes a workflow and its supporting utilities. Source access, selection decisions, and substantive evidence checks remain part of each review.

Read the full introduction

Current implementation & research scope

This is a research programme and local engineering collection with multiple workstreams. Cross-module identities, permissions, services and meta-policy promotion still require integration and validation. It does not claim a fully deployed platform, RSI certification or method originality.