Skip to content
STIMSMITH

Bin Mapping

Concept

Bin Mapping is a mapping scheme used by GENESYS in program synthesis via continuous optimization. It maps continuous variables produced by CMA-ES to discrete program tokens, and is described as resilient to small changes in continuous variables. A uniform variant of bin mapping, which relies on no learning model, can synthesize 73% of programs and outperforms NPO, which synthesizes 58%.

First seen 7/2/2026
Last seen 7/2/2026
Evidence 6 chunks
Wiki v1

WIKI

Bin Mapping

Bin Mapping is a mapping component of the GENESYS program synthesis system, which formulates program synthesis as a continuous optimization problem solved with CMA-ES combined with a token probability model (LSTM).

Role in GENESYS

READ FULL ARTICLE →

NEIGHBORHOOD

No graph connections found for this entity yet. It may appear in future ingestion runs.

explore full graph →

RELATIONSHIPS

1 connections
Genesys ← uses 100% 2e
GENESYS uses bin mapping as its primary mapping scheme to convert continuous parameters into DSL tokens.

CITATIONS

5 sources
5 citations — click to expand
[1] GENESYS's mapping scheme is resilient to small changes in continuous variables, making the overall optimization problem easier than that of NPO. Synthesizing Programs with Continuous Optimization
[2] Even uniform bin mapping (a scheme that does not rely on any learning model at all) can synthesize 73% of all programs, outperforming NPO, which synthesizes 58% of all programs. Synthesizing Programs with Continuous Optimization
[3] GENESYS is characterized as Function formulation + CMA-ES + Token probability (LSTM), with bin mapping as part of its mapping scheme. Synthesizing Programs with Continuous Optimization
[4] Under added random noise to continuous variables, GENESYS's synthesis rate drops about 10% on average across different length programs, whereas NPO drops about 20%. Synthesizing Programs with Continuous Optimization
[5] GENESYS synthesizes at least 1.1% and up to 31.3% more programs across all lengths than DeepCoder, PCCoder, RobustFill, PushGP, and NetSyn, and on average 28.1% more for length-10 programs. Synthesizing Programs with Continuous Optimization