{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2023-11-29-gnome-millions-of-materials/","md":"https://postcutoff.com/e/2023-11-29-gnome-millions-of-materials/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2023-11-29-gnome-millions-of-materials","date":"2023-11-29","date_precision":"day","short_title":"GNoME predicts 2.2 million new crystals, 380,000 stable, but novelty and usefulness are disputed","deck":null,"takeaway":"DeepMind's GNoME (Nature, Nov 2023) used graph neural networks and active learning with DFT to predict 2.2 million new inorganic crystal structures, 380,000 of them computed to be stable.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"disputed","labels":["Disputed"]},"sources":[{"n":1,"title":"Scaling deep learning for materials discovery (Nature)","url":"https://www.nature.com/articles/s41586-023-06735-9","type":"paper","group":"primary","domain":"nature.com"},{"n":2,"title":"DeepMind: Millions of new materials discovered with deep learning","url":"https://deepmind.google/blog/millions-of-new-materials-discovered-with-deep-learning/","type":"official","group":"primary","domain":"deepmind.google"},{"n":3,"title":"C&EN: Google DeepMind AI crystallography database includes near duplicate structures and unrealistic compounds (Oct 14, 2026; partly paywalled)","url":"https://cen.acs.org/research-integrity/Google-DeepMind-structures-near-duplicates-questionable/104/web/2026/10","type":"press","group":"press","domain":"cen.acs.org"},{"n":4,"title":"Cheetham & Seshadri critique (Chemistry of Materials)","url":"https://pubs.acs.org/doi/10.1021/acs.chemmater.4c00643","type":"discussion","group":"reactions","domain":"pubs.acs.org"}],"official":2,"filed":"2026-09-29","updated":"2026-10-16","orgs":["Google DeepMind","Lawrence Berkeley National Laboratory"],"title":"GNoME predicts 2.2 million new crystals, 380,000 stable, but novelty and usefulness are disputed","summary":"DeepMind's GNoME (Nature, Nov 2023) used graph neural networks and active learning with DFT to predict 2.2 million new inorganic crystal structures, 380,000 of them computed to be stable. DeepMind called it '800 years' worth of knowledge'. Solid-state chemists later found 'scant evidence' of compounds that are novel, credible and useful.","key_facts":["2.2M new structures; 380k predicted stable; ~400k added to the Materials Project","DeepMind: over 700 had already been independently synthesised by other groups","Cheetham & Seshadri (Chem. Mater., Apr 2024): 'scant evidence for compounds that fulfill the trifecta of novelty, credibility, and utility'","Oct 14, 2026 (C&EN, Dalmeet Singh Chawla): new outside research says the GNoME database is 'littered with duplicates of known and hypothesized crystal structures found in other databases' and contains unrealistic compounds; Google DeepMind did not comment (article partly paywalled; the study's authors and figures were not read)","GNoME lead Ekin Doğuş Çubuk later co-founded Periodic Labs (2025)"],"key_numbers":[],"tags":["materials","chemistry","graph-neural-networks","controversy"],"science":{"field":"materials","subfield":"inorganic crystal discovery","problem":"Discovering new stable inorganic materials","result":"An order-of-magnitude expansion of computationally predicted stable crystals (380,000).","open_since":"","ai_system":["GNoME"],"human_role":"Human-designed pipeline; predictions automated","verification":{"key":"peer-review","label":"Peer-reviewed","text":"Peer-reviewed in Nature; DFT-computed stability; limited experimental synthesis"},"status":"disputed","shock":"The scale ('800 years of knowledge') was striking, but so was the pushback from chemists about what counts as a new material."},"body_md":"## What happened\n\nDeepMind scaled ML-guided materials screening by orders of magnitude and released the predicted structures to researchers.\n\n## Why it matters\n\nIt is the largest AI materials-prediction effort, and a leading example of the gap between computational \"discovery\" and a useful new material.","disputed":[],"related":[{"id":"2025-09-30-periodic-labs-300m-seed","url":"https://postcutoff.com/e/2025-09-30-periodic-labs-300m-seed/","date":"2025-09-30","date_precision":"day","short_title":"Periodic Labs launches with a $300M seed round to build AI scientists with autonomous labs","deck":null,"takeaway":"Periodic Labs is the flagship of the 2025–26 \"AI scientist plus autonomous lab\" startup wave, alongside Lila Sciences and Radical AI.","category":"business","category_label":"Business","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":1,"filed":"2026-09-29","updated":"2026-10-04","orgs":["Periodic Labs"]},{"id":"2023-11-29-a-lab-autonomous-synthesis-dispute","url":"https://postcutoff.com/e/2023-11-29-a-lab-autonomous-synthesis-dispute/","date":"2023-11-29","date_precision":"day","short_title":"Berkeley's A-Lab claims 41 new materials from autonomous synthesis","deck":"After critiques Nature corrects it to 36 'inorganic' (not 'novel') materials","takeaway":"It is the clearest case study of overclaiming in AI-driven science, and of how human expert scrutiny corrected it.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"disputed","labels":["Disputed"]},"sources":3,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Lawrence Berkeley National Laboratory"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-16","type":"edit","text":"C&EN report (Oct 14, 2026) on near-duplicate and unrealistic structures in the GNoME database"},{"date":"2026-09-29","type":"edit","text":"Linked Periodic Labs entry"},{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-10-16","human_review":null,"version":{"date":"2026-10-16"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/gnome-predicts-2-2-million"}