{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gt4sd-generative-toolkit-for-scientific","title":"Accelerating Material Design with the Generative Toolkit for Scientific Discovery","arxiv_id":"2207.03928","date":"2022-07-08","proceeding":null,"authors":["Matteo Manica","Jannis Born","Joris Cadow","Dimitrios Christofidellis","Ashish Dave","Dean Clarke","Yves Gaetan Nana Teukam","Giorgio Giannone","Samuel C. Hoffman","Matthew Buchan","Vijil Chenthamarakshan","Timothy Donovan","Hsiang Han Hsu","Federico Zipoli","Oliver Schilter","Akihiro Kishimoto","Lisa Hamada","Inkit Padhi","Karl Wehden","Lauren McHugh","Alexy Khrabrov","Payel Das","Seiji Takeda","John R. Smith"],"abstract":"With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery. They harness powerful representations learned from datasets to speed up the formulation of novel hypotheses with the potential to impact material discovery broadly. We present the Generative Toolkit for Scientific Discovery (GT4SD). This extensible open-source library enables scientists, developers, and researchers to train and use state-of-the-art generative models to accelerate scientific discovery focused on material design.","url_abs":"https://arxiv.org/abs/2207.03928v4","url_pdf":"https://arxiv.org/pdf/2207.03928v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gt4sd-generative-toolkit-for-scientific","repo_url":"https://github.com/gt4sd/gt4sd-core","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"materials-screening","task_name":"Materials Screening"},{"task_slug":"scientific-discovery","task_name":"scientific discovery"}],"methods":[{"method_slug":null,"method_name":"Library"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.03928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.03928"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gt4sd/gt4sd-core","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"605b1c20a8f13c63","entry":"class_eval","repo":"gt4sd/gt4sd-core","repo_kind":"official","path":"src/gt4sd/training_pipelines/cgcnn/core.py","file_url":"https://github.com/gt4sd/gt4sd-core/blob/HEAD/src/gt4sd/training_pipelines/cgcnn/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"605b1c20a8f13c63"}},{"code_sha256_prefix":"05a8a96803851212","entry":"distance_to_score","repo":"gt4sd/gt4sd-core","repo_kind":"official","path":"src/gt4sd/properties/scores/core.py","file_url":"https://github.com/gt4sd/gt4sd-core/blob/HEAD/src/gt4sd/properties/scores/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05a8a96803851212"}},{"code_sha256_prefix":"13690cec3ee4ba4f","entry":"mae","repo":"gt4sd/gt4sd-core","repo_kind":"official","path":"src/gt4sd/training_pipelines/cgcnn/core.py","file_url":"https://github.com/gt4sd/gt4sd-core/blob/HEAD/src/gt4sd/training_pipelines/cgcnn/core.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13690cec3ee4ba4f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}