Skip to content
View Anurag1's full-sized avatar
💭
Billionaire businessman
💭
Billionaire businessman

Block or report Anurag1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Anurag1/README.md

Anurag1 — AI Research & Open Experiments

A connected portfolio of experiments around AI reasoning, structured knowledge, geometric representations, discovery, agents, and verification.

Core research question

Can AI move from generating plausible answers toward discovering missing relationships, producing falsifiable hypotheses, and learning from verification?

Research map

Perception
    ↓
Structured representation
    ↓
Knowledge graph / geometry
    ↓
Assumptions + contradictions
    ↓
Unexplored relationships
    ↓
Hypotheses
    ↓
Falsifiable tests
    ↓
Validation + replication

Featured research repositories

Area Repository Purpose
Discovery Geometric-Engine-Intelligence- Knowledge graph + unexplored-edge discovery prototype
Discovery HONET- Contradiction/assumption-driven research framework
Reasoning Generalised-Meta-Attention-Architecture Experimental reasoning/attention architecture
Adaptive reasoning SUPHAI_MODEL Adaptive inference and uncertainty experiments
Geometry GeoSemAlign-Visual-Geometry-Symbol-Meaning-Pipeline Geometry, symbols, and semantic alignment
Agents symbiote-agent-live Agent execution experiments
Collective reasoning Synthetic-Reason-Collective-Intelligence-System Multi-system reasoning experiments
Knowledge Aurora-The-Conversational-Knowledge-Lens Conversational knowledge exploration

How to contribute

Contributions are especially useful when they test rather than merely endorse an idea.

High-value contributions include:

  • independent replications;
  • stronger baselines;
  • ablation studies;
  • mathematical formalization;
  • counterexamples and falsification tests;
  • benchmark datasets;
  • provenance/evidence improvements;
  • reproducibility fixes;
  • alternative implementations.

A negative result is valuable when it is reproducible.

See the shared contribution guidelines.

Scientific standard

Claims should distinguish:

  1. Algorithmic novelty — the system produces a different/useful result.
  2. Knowledge novelty — the result is not already present in the evaluated corpus.
  3. Scientific discovery — the result survives empirical testing and independent replication.

The goal is to make the third claim difficult to make—and therefore meaningful when earned.

@Anurag1's activity is private