{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/151374"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/151374","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Top-Down Synthesis for Library Learning","abstract":"This thesis introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain specific language (DSL). The algorithm builds abstractions directly from initial DSL primitives, using syntactic pattern matching of intermediate abstractions to intelligently prune the search space and guide the algorithm towards abstractions that maximally capture shared structures in the corpus. We present an implementation of the approach in a tool called Stitch and evaluate it against the state-of-the-art deductive library learning algorithm from DreamCoder. Our evaluation shows that Stitch is 3-4 orders of magnitude faster and uses 2 orders of magnitude less memory while maintaining comparable or better library quality (as measured by compressivity). We also demonstrate Stitch’s scalability on corpora containing hundreds of complex programs that are intractable with prior deductive approaches and show empirically that it is robust to terminating the search procedure early—further allowing it to scale to challenging datasets by means of early stopping. We publish the code, the documentation, a tutorial, and a Python library for interfacing with our for our Rust implementation of Stitch. Tutorial & Documentation (Python Library): https://stitch-bindings.read thedocs.io/en/stable/intro/tutorial.html Rust Implementation: https://github.com/mlb2251/stitch Artifact (Awarded: Reusable): https://github.com/mlb2251/stitch-artifact","abstract_html":"This thesis introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain specific language (DSL). The algorithm builds abstractions directly from initial DSL primitives, using syntactic pattern matching of intermediate abstractions to intelligently prune the search space and guide the algorithm towards abstractions that maximally capture shared structures in the corpus. We present an implementation of the approach in a tool called Stitch and evaluate it against the state-of-the-art deductive library learning algorithm from DreamCoder. Our evaluation shows that Stitch is 3-4 orders of magnitude faster and uses 2 orders of magnitude less memory while maintaining comparable or better library quality (as measured by compressivity). We also demonstrate Stitch’s scalability on corpora containing hundreds of complex programs that are intractable with prior deductive approaches and show empirically that it is robust to terminating the search procedure early—further allowing it to scale to challenging datasets by means of early stopping. We publish the code, the documentation, a tutorial, and a Python library for interfacing with our for our Rust implementation of Stitch. Tutorial & Documentation (Python Library): https://stitch-bindings.read thedocs.io/en/stable/intro/tutorial.html Rust Implementation: https://github.com/mlb2251/stitch Artifact (Awarded: Reusable): https://github.com/mlb2251/stitch-artifact","abstract_has_math":false,"creators":["Bowers, Matthew L."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Solar-Lezama, Armando"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06","date_published":"2023-06","updated_at":"2026-07-22T22:20:47Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/151374","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Solar-Lezama, Armando"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Bowers, Matthew L."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-07-31T19:35:02Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-07-31T19:35:02Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/151374"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain specific language (DSL). The algorithm builds abstractions directly from initial DSL primitives, using syntactic pattern matching of intermediate abstractions to intelligently prune the search space and guide the algorithm towards abstractions that maximally capture shared structures in the corpus. We present an implementation of the approach in a tool called Stitch and evaluate it against the state-of-the-art deductive library learning algorithm from DreamCoder. Our evaluation shows that Stitch is 3-4 orders of magnitude faster and uses 2 orders of magnitude less memory while maintaining comparable or better library quality (as measured by compressivity). We also demonstrate Stitch’s scalability on corpora containing hundreds of complex programs that are intractable with prior deductive approaches and show empirically that it is robust to terminating the search procedure early—further allowing it to scale to challenging datasets by means of early stopping. We publish the code, the documentation, a tutorial, and a Python library for interfacing with our for our Rust implementation of Stitch. Tutorial & Documentation (Python Library): https://stitch-bindings.read thedocs.io/en/stable/intro/tutorial.html Rust Implementation: https://github.com/mlb2251/stitch Artifact (Awarded: Reusable): https://github.com/mlb2251/stitch-artifact"]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Top-Down Synthesis for Library Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Solar-Lezama, Armando"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Bowers, Matthew L."],"dc:date.accessioned":["2023-07-31T19:35:02Z"],"dc:date.available":["2023-07-31T19:35:02Z"],"dc:date.issued":["2023-06"],"dc:description.abstract":["This thesis introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain specific language (DSL). The algorithm builds abstractions directly from initial DSL primitives, using syntactic pattern matching of intermediate abstractions to intelligently prune the search space and guide the algorithm towards abstractions that maximally capture shared structures in the corpus. We present an implementation of the approach in a tool called Stitch and evaluate it against the state-of-the-art deductive library learning algorithm from DreamCoder. Our evaluation shows that Stitch is 3-4 orders of magnitude faster and uses 2 orders of magnitude less memory while maintaining comparable or better library quality (as measured by compressivity). We also demonstrate Stitch’s scalability on corpora containing hundreds of complex programs that are intractable with prior deductive approaches and show empirically that it is robust to terminating the search procedure early—further allowing it to scale to challenging datasets by means of early stopping. We publish the code, the documentation, a tutorial, and a Python library for interfacing with our for our Rust implementation of Stitch. Tutorial & Documentation (Python Library): https://stitch-bindings.read thedocs.io/en/stable/intro/tutorial.html Rust Implementation: https://github.com/mlb2251/stitch Artifact (Awarded: Reusable): https://github.com/mlb2251/stitch-artifact"],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/151374"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Top-Down Synthesis for Library Learning"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:20:47Z"}