Skip to content
#small language model Open access

CAP v0.3 — Canal Activation Protocol — Protocolo mínimo para la relación consciente humano–IA

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

Abstract

[ES] El CAP (Canal Activation Protocol) es un protocolo operativo mínimo diseñado para sostener una relación consciente, portable, trazable y no dependiente entre una persona y un modelo de lenguaje (LLM). No es un prompt, un agente autónomo ni una plataforma. Es un conjunto pequeño de archivos de texto que hace explícitos el estado de trabajo, los límites, la memoria opcional y el control humano. CAP busca reducir derivas previsibles en colaboraciones longitudinales humano–IA: pérdida o exceso de contexto; confusión entre hechos, interpretaciones, hipótesis y decisiones; cierre prematuro o inflación teórica; dependencia de un modelo, proveedor o memoria concreta; sustitución progresiva del criterio humano; y acumulación de intermediación sin posibilidad clara de cuestionarla o detenerla. La versión v0.3 incorpora, respecto de v0.2: - separación epistemológica explícita entre hecho, interpretación, hipótesis, propuesta y decisión humana; - regla de no inflación teórica; - portabilidad entre modelos y continuidad sin cautividad; - contexto proporcional; - salida disponible; - intermediación contestable; - separación explícita entre arquitectura/método y memoria privada del operador; - plantillas públicas limpias para log.md, contexto.md y futuro.md; - separación de módulos experimentales respecto del núcleo. La edición pública conserva arquitectura y método, no memoria personal ni contexto operativo privado. CAP puede utilizarse con cualquier modelo de lenguaje sin integración técnica específica. Se desarrolla dentro de El Canal — Applied Cognitive Symbology (ACS). El Canal propone. El humano decide. Sitio oficial: https://elcanal.es Repositorio: https://github.com/ulaulaygpt/elcanal-cap ORCID: https://orcid.org/0009-0000-8891-7021 [EN] CAP (Canal Activation Protocol) is a minimal operational protocol designed to sustain a conscious, portable, traceable and non-dependent relationship between a person and a language model (LLM). It is not a prompt, an autonomous agent or a platform. It is a small set of text files that makes working state, limits, optional memory and human control explicit. CAP seeks to reduce predictable drifts in longitudinal human–AI collaboration: loss or excess of context; confusion between facts, interpretations, hypotheses and decisions; premature closure or theoretical inflation; dependence on a specific model, provider or memory; progressive substitution of human judgment; and accumulation of intermediation without a clear possibility to question or stop it. Version v0.3 adds, compared with v0.2: - explicit epistemological separation between fact, interpretation, hypothesis, proposal and human decision; - a no-theoretical-inflation rule; - portability across models and continuity without captivity; - proportional context; - available exit; - contestable intermediation; - explicit separation between architecture/method and the operator's private memory; - clean public templates for log.md, contexto.md and futuro.md; - separation of experimental modules from the core. The public edition preserves architecture and method, not personal memory or private operational context. CAP can be used with any language model without specific technical integration. It is developed within El Canal — Applied Cognitive Symbology (ACS). The Channel proposes; the human decides. Official site: https://elcanal.es Repository: https://github.com/ulaulaygpt/elcanal-cap ORCID: https://orcid.org/0009-0000-8891-7021

View source

Similar papers

#small language model Dataset Open access Oct 2026

Socratic guiding questions in synthetic arithmetic data: matched LoRA runs (revision v2)

Supporting data, adapters, predictions and code for the article *Low-Cost LoRA Fine-Tuning of Small Language Models for Multi-Step Arithmetic Reasoning* by Jake O'Grady, Asena Isik Gürhan, Chee Fong Ting and Effirul Ramlan (University of Galway). We generated 20,000 GSM8K-derived arithmetic problems with step-by-step s...

O'Grady, Jake, Gürhan, Asena Isik, Chee, Fong Ting et al. · 465 citations
#computer vision Open access Jun 2016

Software Development in Startup Companies: The Greenfield Startup Model

The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.

Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al. · 178 citations · ⚡14
#computer vision Open access Oct 2016

Software Startups - A Research Agenda

Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.

M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al. · 157 citations · ⚡17
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#computer vision Review Open access May 2015

A survey study on major technical barriers affecting the decision to adopt cloud services

The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.

Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al. · 111 citations · ⚡8
#computer vision Open access Feb 2018

Lean Internal Startups for Software Product Innovation in Large Companies: Enablers and Inhibitors

This study investigates how Lean internal startup facilitates software product innovation in large companies and identifies its enablers and inhibitors, and shows the potential of the method-in-action framework to investigate the Lean startup approach in non-startup context.

Henry Edison, Nina M. Smørsgård, Xiaofeng Wang et al. · 78 citations · ⚡6

Related blog posts

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