method
active
method:stitch-baseline

Stitch (baseline)

Baseline model stitching trained in a single behavioral direction without CL auxiliary loss, used for comparison with CLMAS.

Related by similarity (8)

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.

  • Latent Stitchmethod0.780
    Baseline method using a single orthogonal matrix trained to map source latents to target latents via CL auxiliary loss without behavioral objective.
  • Conditional generation on explicit Big Five labels using per-dimension descriptors; used as inference-time baseline
  • MTL architecture with linear combinations of activations across tasks.
  • A trait already strongly expressed at baseline (alpha=0) without steering intervention
  • Model Stitchingmethod0.746
    Technique to measure representational compatibility by integrating intermediate representations of one model into another
  • Model stitching without learning a stitching layer, demonstrating strong alignment across different model training regimes
  • Baseline method sampling a random vector as feature direction for comparison with learned methods
  • PCA Baselinemethod0.727
    PCA components treated as SAE latents for comparison.