Sam Ramdan

Frozen Forecast: Sign-Kernel Alignment Ranks Held-Out Adapters' Output-Matched Learning (SCAFFOLD, E5)

A forecast frozen on 2026-10-17 10:47 +0400 (SHA-256 0400cbfb03436aa54c54a3b59bb11fd9c252475cbdb34e11c91272f0cc8b1012), before any B-learning run with these adapters, for the preprint Head Start or Process? Decomposing How an Experience-Acquired Abstraction Shapes Later Learning...

Head Start or Process? Decomposing How an Experience-Acquired Abstraction Shapes Later Learning in a Small Language Model

When a network that has acquired an abstraction A learns a second abstraction B faster, does A supply information or change the process by which B is learned? We decompose a gradient learner's function-space update into starting predictions, evidence and tangent kernel, and isola...

A Compounding Fingerprint: Telling Abstraction from Exemplar Reuse in Context

When a model improves at a structured task after earlier examples in context, has it abstracted the structure or reused the examples? Improvement alone cannot tell: longer contexts, recall and exemplar matching all produce it. We introduce a compounding fingerprint for in-context...