{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7R5FTE2LEAPBD7XL7N33OGIGGY","short_pith_number":"pith:7R5FTE2L","schema_version":"1.0","canonical_sha256":"fc7a59934b201e11feebfb77b719063615971e294c9fb492043cfca7f00c08ba","source":{"kind":"arxiv","id":"2410.12771","version":1},"attestation_state":"computed","paper":{"title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Open Materials 2024 supplies 110 million DFT calculations and EquiformerV2 models that reach F1 scores above 0.9 for ground-state stability.","cross_cats":["cs.AI","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Ammar Rizvi, Brandon M. Wood, C. Lawrence Zitnick, Luis Barroso-Luque, Meng Gao, Misko Dzamba, Muhammed Shuaibi, Xiang Fu, Zachary W. Ulissi","submitted_at":"2024-10-16T17:48:34Z","abstract_excerpt":"The ability to discover new materials with desirable properties is critical for numerous applications from helping mitigate climate change to advances in next generation computing hardware. AI has the potential to accelerate materials discovery and design by more effectively exploring the chemical space compared to other computational methods or by trial-and-error. While substantial progress has been made on AI for materials data, benchmarks, and models, a barrier that has emerged is the lack of publicly available training data and open pre-trained models. To address this, we present a Meta FA"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2410.12771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-10-16T17:48:34Z","cross_cats_sorted":["cs.AI","physics.comp-ph"],"title_canon_sha256":"a1c9e6d5393a4135b476439554a6b23824a83a4d01d074dfe135bc6b647eb6d2","abstract_canon_sha256":"671e2fdaa49b54659570d6128bf9bcfabf0dfdcb1410db749b787caba444520c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.205487Z","signature_b64":"x0Y4k9xVHi7PfgU6keea0LuuEP7PLNgSy7rLGOky+vO+ygEVFXrjFVCL4mbdK0VnWj5T3UL0tJSN4imxcOepDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc7a59934b201e11feebfb77b719063615971e294c9fb492043cfca7f00c08ba","last_reissued_at":"2026-05-17T23:38:46.205046Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.205046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Open Materials 2024 supplies 110 million DFT calculations and EquiformerV2 models that reach F1 scores above 0.9 for ground-state stability.","cross_cats":["cs.AI","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Ammar Rizvi, Brandon M. Wood, C. Lawrence Zitnick, Luis Barroso-Luque, Meng Gao, Misko Dzamba, Muhammed Shuaibi, Xiang Fu, Zachary W. Ulissi","submitted_at":"2024-10-16T17:48:34Z","abstract_excerpt":"The ability to discover new materials with desirable properties is critical for numerous applications from helping mitigate climate change to advances in next generation computing hardware. AI has the potential to accelerate materials discovery and design by more effectively exploring the chemical space compared to other computational methods or by trial-and-error. While substantial progress has been made on AI for materials data, benchmarks, and models, a barrier that has emerged is the lack of publicly available training data and open pre-trained models. To address this, we present a Meta FA"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our EquiformerV2 models achieve state-of-the-art performance on the Matbench Discovery leaderboard and are capable of predicting ground-state stability and formation energies to an F1 score above 0.9 and an accuracy of 20 meV/atom, respectively.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The DFT calculations in the dataset provide sufficiently accurate representations of real material ground-state stabilities and formation energies, and the models trained on this data will generalize reliably to new, unseen materials.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OMat24 provides over 110 million DFT calculations and EquiformerV2 models that reach state-of-the-art performance on material stability and formation energy prediction.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Open Materials 2024 supplies 110 million DFT calculations and EquiformerV2 models that reach F1 scores above 0.9 for ground-state stability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1457ec85c0ab692213e590beeac3047cbd9b74a59084328783f60377c6f07eef"},"source":{"id":"2410.12771","kind":"arxiv","version":1},"verdict":{"id":"69d5f168-4954-4a19-ac73-7d2c5a06fb27","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T23:39:17.163341Z","strongest_claim":"Our EquiformerV2 models achieve state-of-the-art performance on the Matbench Discovery leaderboard and are capable of predicting ground-state stability and formation energies to an F1 score above 0.9 and an accuracy of 20 meV/atom, respectively.","one_line_summary":"OMat24 provides over 110 million DFT calculations and EquiformerV2 models that reach state-of-the-art performance on material stability and formation energy prediction.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The DFT calculations in the dataset provide sufficiently accurate representations of real material ground-state stabilities and formation energies, and the models trained on this data will generalize reliably to new, unseen materials.","pith_extraction_headline":"Open Materials 2024 supplies 110 million DFT calculations and EquiformerV2 models that reach F1 scores above 0.9 for ground-state stability."},"references":{"count":65,"sample":[{"doi":"","year":2020,"title":"Lawrence Zitnick, and Zachary Ulissi","work_id":"4fd130ba-140c-4347-90aa-d5a461d1880d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"An introduction to electrocatalyst design using machine learning for renewable energy storage","work_id":"9f905ff1-1f8f-4999-93a8-7aadf34f745f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Robust and synthesizable photocatalysts for co2 reduction: a data-driven materials discovery.Nature Communications, 10(1):443, 2019","work_id":"2a0976f5-91fe-4e45-9f13-fb0cde352bb9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Brabson, Abhishek Das, Zachary Ulissi, Matt Uyttendaele, Andrew J","work_id":"25749663-3d6c-4200-8554-2a41dc1e48f9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Recent advances and applications of deep learning methods in materials science.npj Computational Materials, 8(1):59, 2022","work_id":"b27b8feb-208e-4483-a6fa-9be539f50a2a","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":65,"snapshot_sha256":"44b9e42905f94bd3d17a39027a11a5ee2d85c47e156d6c2e42b1b5130a3915a5","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"de7a064804cc28e814dc44fc48ba42030fd71b927b97f2e4e1282b7d93c89c25"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.12771","created_at":"2026-05-17T23:38:46.205119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12771v1","created_at":"2026-05-17T23:38:46.205119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12771","created_at":"2026-05-17T23:38:46.205119+00:00"},{"alias_kind":"pith_short_12","alias_value":"7R5FTE2LEAPB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"7R5FTE2LEAPBD7XL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"7R5FTE2L","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2508.09113","citing_title":"Machine Learning Phonon Spectra for Fast and Accurate Optical Lineshapes of Defects","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2509.14205","citing_title":"Teachers that teach the irrelevant: Pre-training machine learned interaction potentials with classical force fields for robust molecular dynamics simulations","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04015","citing_title":"Atomistic Machine Learning with Irreducible Cartesian Natural Tensors","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2510.05020","citing_title":"Comparing fine-tuning strategies of MACE machine learning force field for modeling Li-ion diffusion in LiF for batteries","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2512.02309","citing_title":"An experimentally validated end-to-end framework for operando modeling of intrinsically complex metallosilicates","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2512.05717","citing_title":"Comparing the latent features of universal machine-learning interatomic potentials","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2512.09169","citing_title":"AI-Driven Expansion and Application of the Alexandria Database","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2601.16331","citing_title":"Accuracy and Efficiency Benchmarks of Pretrained Machine Learning Potentials for Molecular Simulations","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14527","citing_title":"Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13594","citing_title":"Assessing foundational atomistic models for iron alloys under Earth's core conditions","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01642","citing_title":"Machine Learning Interatomic Potentials for Million-Atom Simulations of Multicomponent Alloys","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27685","citing_title":"VibroML: an automated toolkit for high-throughput vibrational analysis and dynamic instability remediation of crystalline materials using machine-learned potentials","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08262","citing_title":"SLayerGen: a Crystal Generative Model for all Space and Layer Groups","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08960","citing_title":"CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09394","citing_title":"Systematic Fine-Tuning of MACE Interatomic Potentials for Catalysis","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08885","citing_title":"Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24607","citing_title":"Errors that matter: Uncertainty-aware universal machine-learning potentials calibrated on experiments","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05733","citing_title":"Density diversity in training data governs thermodynamic transferability of machine learning interatomic potentials","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23758","citing_title":"Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductor Discovery","ref_index":89,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21850","citing_title":"OptiMat Alloys: a FAIR, living database of multi-principal element alloys enabled by a conversational agent","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11827","citing_title":"Inverse Design of Inorganic Compounds with Generative AI","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07927","citing_title":"MatterSim-MT: A multi-task foundation model for in silico materials characterization","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15821","citing_title":"Breaking the Training Barrier of Billion-Parameter Universal Machine Learning Interatomic Potentials","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20515","citing_title":"Accurate and Efficient Interatomic Potentials for Dislocations in InP","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY","json":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY.json","graph_json":"https://pith.science/api/pith-number/7R5FTE2LEAPBD7XL7N33OGIGGY/graph.json","events_json":"https://pith.science/api/pith-number/7R5FTE2LEAPBD7XL7N33OGIGGY/events.json","paper":"https://pith.science/paper/7R5FTE2L"},"agent_actions":{"view_html":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY","download_json":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY.json","view_paper":"https://pith.science/paper/7R5FTE2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12771&json=true","fetch_graph":"https://pith.science/api/pith-number/7R5FTE2LEAPBD7XL7N33OGIGGY/graph.json","fetch_events":"https://pith.science/api/pith-number/7R5FTE2LEAPBD7XL7N33OGIGGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY/action/storage_attestation","attest_author":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY/action/author_attestation","sign_citation":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY/action/citation_signature","submit_replication":"https://pith.science/pith/7R5FTE2LEAPBD7XL7N33OGIGGY/action/replication_record"}},"created_at":"2026-05-17T23:38:46.205119+00:00","updated_at":"2026-05-17T23:38:46.205119+00:00"}