{"id":38335213,"url":"https://github.com/cedergrouphub/matbert-synthesis-classifier","last_synced_at":"2026-01-17T02:55:46.057Z","repository":{"id":107072210,"uuid":"317101239","full_name":"CederGroupHub/MatBERT-synthesis-classifier","owner":"CederGroupHub","description":"A synthesis paragraph classifier built by fine-tuning MatBERT","archived":false,"fork":false,"pushed_at":"2021-05-13T22:31:13.000Z","size":31,"stargazers_count":6,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-09T23:38:57.906Z","etag":null,"topics":["bert-model","classifier","materials-science","nlp"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CederGroupHub.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2020-11-30T03:32:20.000Z","updated_at":"2025-01-07T13:51:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"fe50a348-c28d-4b51-80f4-c6cceff3e762","html_url":"https://github.com/CederGroupHub/MatBERT-synthesis-classifier","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/CederGroupHub/MatBERT-synthesis-classifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CederGroupHub%2FMatBERT-synthesis-classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CederGroupHub%2FMatBERT-synthesis-classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CederGroupHub%2FMatBERT-synthesis-classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CederGroupHub%2FMatBERT-synthesis-classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CederGroupHub","download_url":"https://codeload.github.com/CederGroupHub/MatBERT-synthesis-classifier/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CederGroupHub%2FMatBERT-synthesis-classifier/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28492591,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-17T02:39:23.645Z","status":"ssl_error","status_checked_at":"2026-01-17T02:34:19.649Z","response_time":85,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bert-model","classifier","materials-science","nlp"],"created_at":"2026-01-17T02:55:45.953Z","updated_at":"2026-01-17T02:55:46.051Z","avatar_url":"https://github.com/CederGroupHub.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## MatBERT synthesis classifier\nA synthesis paragraph classifier built by fine-tuning MatBERT. \nBuilt by the text-mining team at [CEDER group](https://ceder.berkeley.edu). \n\n## Usage\n\n```\nfrom synthesis_classifier import get_model, get_tokenizer, run_batch\n\nmodel = get_model()\ntokenizer = get_tokenizer()\n\nparagraphs = [...]\n\nfor batch in batches:\n    result = run_batch(batch, model, tokenizer)\n    print(result)\n\n# Output:\n# [{\n# 'text': '10.1063/1.3676216: The raw materials were BaCO3, ZnO, Nb2O5, \n# and Ta2O5 powders with purity of more than 99.5%. Ba[Zn1/3 (Nb1−xTax)2/3]O3 \n# (BZNT, x\\u2009=\\u20090.0, 0.2, 0.4, 0.6, 0.8, 1.0) solid solutions were \n# synthesized by conventional solid-state sintering technique. Oxide compounds \n# were mixed for 12\\u2009h in polyethylene jars with zirconia balls and then \n# dried and calcined at 1100 °C for 2\\u2009h. After remilling, the powders were \n# dried and pressed into discs of 15\\u2009mm\\u2009×\\u20091\\u2009mm and next \n# sintered at 1500 °C for 3\\u2009h.', \n# \n# 'tokens': ['10', '.', '106', '##3', '/', '1', '.', '367', '##62', '##16', ':', \n# 'The', 'raw', 'materials', 'were', 'Ba', '##CO3', ',', 'ZnO', ',', 'Nb2O5', ',', \n# 'and', 'Ta2O5', 'powders', 'with', 'purity', 'of', 'more', 'than', '99', '.', \n# '5', '%', '.', 'Ba', '[', 'Zn', '##1', '/', '3', '(', 'Nb', '##1−x', '##Ta', \n# '##x', ')', '2', '/', '3', ']', 'O3', '(', 'BZ', '##NT', ',', 'x', '=', '0', \n# '.', '0', ',', '0', '.', '2', ',', '0', '.', '4', ',', '0', '.', '6', ',', '0', \n# '.', '8', ',', '1', '.', '0', ')', 'solid', 'solutions', 'were', 'synthesized', \n# 'by', 'conventional', 'solid', '-', 'state', 'sintering', 'technique', '.', \n# 'Oxid', '##e', 'compounds', 'were', 'mixed', 'for', '12', 'h', 'in', 'polyethylene', \n# 'j', '##ars', 'with', 'zirconia', 'balls', 'and', 'then', 'dried', 'and', 'calcined', \n# 'at', '1100', '°C', 'for', '2', 'h', '.', 'After', 'rem', '##illing', ',', 'the', \n# 'powders', 'were', 'dried', 'and', 'pressed', 'into', 'discs', 'of', '15', 'mm', \n# '×', '1', 'mm', 'and', 'next', 'sintered', 'at', '1500', '°C', 'for', '3', 'h', '.'], \n#\n# 'scores': {\n# 'solid_state_ceramic_synthesis': 0.9992626309394836, \n# 'sol_gel_ceramic_synthesis': 0.00024707740521989763, \n# 'hydrothermal_ceramic_synthesis': 8.356467151315883e-05, \n# 'precipitation_ceramic_synthesis': 8.224111661547795e-05, \n# 'something_else': 0.00032462377566844225}}\n```\n\n## Citing\n\nWhile we are working on a new paper, it's always nice to cite our previous paper:\n\n```\n@article{huo2019semi,\n  title={Semi-supervised machine-learning classification of materials synthesis procedures},\n  author={Huo, Haoyan and Rong, Ziqin and Kononova, Olga and Sun, Wenhao and Botari, Tiago and He, Tanjin and Tshitoyan, Vahe and Ceder, Gerbrand},\n  journal={npj Computational Materials},\n  volume={5},\n  number={1},\n  pages={1--7},\n  year={2019},\n  publisher={Nature Publishing Group}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcedergrouphub%2Fmatbert-synthesis-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcedergrouphub%2Fmatbert-synthesis-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcedergrouphub%2Fmatbert-synthesis-classifier/lists"}