Towards a Programmer’s Apprentice (Again)

Authors: Howard Shrobe, Boris Katz, Randall Davis

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental A Programmer s Assistant could interact with the programmer to capture and preserve design rationale, in a natural way that would make rationale capture cost less than it s worth , and could also detect common flaws in program design. Such a programmer s assistant was not practical when it was first proposed decades ago, but advances over the years make now the time to revisit the concept, as our prototype shows.
Researcher Affiliation Academia Howard Shrobe, Boris Katz, and Randall Davis MIT CSAIL 32 Vassar Street Cambridge, MA 02139
Pseudocode Yes The synthesized code is shown in Figure 3.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper does not provide information about publicly available or open datasets used for training or evaluation of the described prototype.
Dataset Splits No The paper does not provide specific dataset split information (e.g., train/validation/test percentages or counts).
Hardware Specification No Spoken language is captured using the SIRI programmatic interface (on a Mac Book). This provides a general device name but no specific hardware details (CPU, GPU, RAM, etc.) for the main system running the prototype.
Software Dependencies No Spoken language is captured using the SIRI programmatic interface (on a Mac Book) and is then parsed using an HTTP-based interface to the START natural language system... We generate Common Lisp... Specific version numbers for these software components are not provided.
Experiment Setup No The paper describes a demonstration scenario but does not provide specific experimental setup details such as concrete hyperparameter values or training configurations.