Phase-Level Adherence Judge

Separate LLM judge that partitions trajectories into five phases and assigns 0–1 adherence scores per phase using Claude Sonnet 4.6

Neighborhood — ranked by edge-count

paper

method

Locked Rubric Extraction
uses
First stage of HFR pipeline that converts skill body into a strict JSON rubric of atomic procedural instructions for adherence judging

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Phase-Level Adherence Analysisconcept0.895
Analysis tracking how closely an agent follows harness guidance at different trajectory phases: harness loaded, mid turn, final turn
Phase Precessionfinding0.715
Hippocampal neural coding phenomenon reproduced by active inference.
Concreteness Judgemethod0.686
LLM-based judge rating SAE latent labels 0-100 for concreteness to filter steering candidates
what criterion should determine that a conscious being is to be treated as equivalent to a human?question0.685
Ethical question about the threshold for full moral status of artificial conscious agents
complianceconcept0.684
The model's tendency to comply with harmful requests, the opposite of refusal.
Marrs Taxonomy Of Levelsframework0.679
Measuring Faithfulness in Chain-of-Thought Reasoning (Lanham et al. 2023)concept0.678
Cited regarding possibility of encoding misaligned reasoning in benign chains-of-thought
Levels of Scaleconcept0.673
The property that living structures contain centers at a beautiful range of sizes at well-marked levels with definite jumps, where each level helps the next; jumps should not be too great (ideally 2:1 to 4:1, less than 10:1)