media Hugging Face Forums · 1d ago · open_models

CosmicUndercurrent releases Principia-Structurae-Realitatis for testing LLM whole-system coordination

from English

CosmicUndercurrent has open-sourced a model-agnostic reasoning framework designed to test whether structural priming can reduce global inconsistencies in large language models. The project, hosted, investigates if a two-step process improves whole-system coordination compared to local correctness.

The framework uses the formula "Reality = Consciousness × Matter × Coordination" as a structural seed for semantic expansion. It operates via two messages: the first prompts the model to derive an operational reasoning framework based on goals, state, and dependencies; the second applies this derived structure to solve a specific task. The author seeks independent A/B testing to measure behaviors such as constraint retention, dependency propagation, contradiction detection, and reasoning-policy stability.

The goal is to identify cases where the framework fails or performs worse than a baseline, rather than assuming it always improves performance. The author requests detailed comparisons including model used, task details, and specific failure modes to evaluate the utility of this structural priming approach.

Importance 1/3 Trust 1/3 Hugging Face Forums Evaluation & benchmarks Reasoning models

Related articles

media Hugging Face Forums · 51d ago · 34 views

GPT-5.6 recovers 95% of hidden messages in unseen literary cryptography benchmark

A working paper by Joseph JM Walker evaluates frontier language models on an unseen multi-channel literary cryptography benchmark embedded in the physical novel "I Wrote a Book and Made a Million Dollars (I.B. Wryten)." The study finds that GPT-5.6 independently recognized the secondary communication channel and recovered approximately 95% of the embedded material on its first pass, whereas earlier models demonstrated effectively 0% ability.

arxiv arXiv cs.CL · 69d ago · 41 views

GSM-Plus-BN introduces perturbation-based benchmark for Bangla math reasoning

The study introduces GSM-Plus-BN, a novel perturbed Bengali mathematical dataset derived from the English GSM-Plus benchmark and verified by human translators. This resource addresses the lack of systematic benchmarks for assessing model robustness in linguistically diverse regions like Bangladesh.

arxiv arXiv cs.AI · 71d ago · 21 views

WILDTRACE introduces benchmark for natural evidence trails in long-context reasoning

The authors introduce WILDTRACE, a new benchmark designed to evaluate how well models integrate evidence dispersed across distant passages in long documents. Unlike existing benchmarks that rely on planted facts or reverse-engineered chains, WILDTRACE uses 481 tasks derived from 214 naturally occurring sources, such as technical incident reports and literary narratives.

arxiv arXiv cs.CL · 72d ago · 29 views

WILDTRACE benchmark introduces 481 tasks for natural evidence trails in long-context reasoning

The authors introduce WILDTRACE, a new benchmark designed to evaluate how well models integrate evidence dispersed naturally across distant passages in long documents. Unlike existing benchmarks that use planted facts or reverse-engineered chains, WILDTRACE relies on source-internal causal, temporal, and narrative logic.

lab OpenAI News · 85d ago · 31 views

Introducing GeneBench-Pro

GeneBench-Pro is a research-level benchmark designed to measure how AI agents handle ambiguity and make consequential judgments in computational biology, expanding on the original GeneBench. It addresses the limitation of current assessments by testing higher-order capabilities such as handling data noise, revising assumptions, and determining when results are decision-ready.