Skip to content
#generative ai Open access

allen-proxmire/ED-generative: 27.0

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

One primitive does the work: the arrow of time — the irreversible act of commitment. Most attempts at unification add structure. This one removes it. Event Density starts from a discrete relational substrate with no intrinsic metric, no background coordinates, and no dimensionless constants of its own, and asks what a single irreversible act can be made to carry. The answer, so far, is more than expected — and the claim the program actually rests on is this: The thing that selects a measurement outcome in quantum mechanics and the thing that supplies a preferred time in gravity are not two things. They are one primitive. The Problem of Time does not get bridged. It stops arising. What is here 242 papers, 506 documents, 16 arc ledgers. Weak-field gravity reproduced, MOND emerging natively as a horizon interference term rather than a modification, quantum mechanics reconstructed from relational lattices, gauge structure from indistinguishable channels, charge quantization from winding, rest mass from binding rather than a field. And a complete record of everything that failed. That second part is not modesty. It is the point. What makes this repository unusual Every load-bearing claim carries a tier: derived, grounded, inherited, postulated, measured, open. Not as decoration — as a contract. A claim tiered Grounded names the postulate it rests on. A claim tiered Inherited names where the number came from. A claim tiered Open says what would close it. The ledgers record corrections against the theory as carefully as results for it. A flagship prediction that went from confirmed to untested in one day when a systematics critique checked out. A repair carried for two days that turned out to invert the problem rather than fix it. A summary that overstated the arc's own open questions by two. Those are in here, dated, with the reasoning. Six automated checks run over the corpus and fail on drift: stale claims, broken provenance, contradictory definitions across documents, unverified rows, dead pointers. Each was built after a defect got through. How to read it If you have ten minutes — ED_UnifiedFramework_Report.pdf. The whole framework, box by box, with the limits stated in the same breath as the results. If you want the receipts — ED_ItemizedTheory_TieredClaims_v2.xlsx. Every claim, its tier, what it rests on, what would kill it. Sortable. Start with the Core Predictions sheet, then Ledger w Claims. If you want to attack it — physics-papers/predictions/22_Ways_to_Kill_Event_Density.md. Twenty-two ways, written by the author, each with a falsifier. The fastest route to a real objection. If you want one paper — physics-papers/gravity/Paper_a0z_MONDScaleTracksHubbleRate.md. A single prediction, registered before the data, with its kill condition stated in advance and its own confrontation reported honestly, including the parts that go against it. If you are an AI agent — read CLAUDE.md first. It tells you the one rule that matters: read the corpus before you build on it. It exists because a session once spent a day re-deriving results that were already there, then "falsified" its own reconstruction. What this is not Not peer-reviewed. Not complete. No distinctive prediction is confirmed. Two structural questions are open — why gauge multiplicities are {1,2,3}, and whether exact charge conservation forces anomaly freedom. One prerequisite is unproven: universal free fall. The dimensionless constants are inherited, by design and by argument. "Form-complete" here is a coverage claim — the substrate fixes the form of a law while the universe supplies its numbers. It is not closure, not unique derivation, and not empirical validation. The report says so in its first paragraph. The interesting question is not whether this is right. It is whether a program built from one primitive, that documents its own failures this carefully, is wrong in a way that can be found. It is set up so that it can be. Start with the twenty-two.

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations

Related blog posts

GPT-Lab Sep 17, 2026

Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering

AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.