{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U3XPIHHOPSJ5OBFKTT7AEN4Q3N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c6b53e8ea4c4b2cb8a0689e1d1b02cb8c305bc2ddd1b7a13f07822fa26ff9523","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:35:28Z","title_canon_sha256":"b49516fd757773a339748090b876a60139d0aeb8494b0fea077468030514fe41"},"schema_version":"1.0","source":{"id":"2402.04379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04379","created_at":"2026-07-05T11:42:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04379v2","created_at":"2026-07-05T11:42:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04379","created_at":"2026-07-05T11:42:20Z"},{"alias_kind":"pith_short_12","alias_value":"U3XPIHHOPSJ5","created_at":"2026-07-05T11:42:20Z"},{"alias_kind":"pith_short_16","alias_value":"U3XPIHHOPSJ5OBFK","created_at":"2026-07-05T11:42:20Z"},{"alias_kind":"pith_short_8","alias_value":"U3XPIHHO","created_at":"2026-07-05T11:42:20Z"}],"graph_snapshots":[{"event_id":"sha256:3c0913d2886011cf4f0a07e6a9dd2428d3847e2e633e380b18bc087fb3edacba","target":"graph","created_at":"2026-07-05T11:42:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.04379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose fine-tuning large language models for generation of stable materials. While unorthodox, fine-tuning large language models on text-encoded atomistic data is simple to implement yet reliable, with around 90% of sampled structures obeying physical constraints on atom positions and charges. Using energy above hull calculations from both learned ML potentials and gold-standard DFT calculations, we show that our strongest model (fine-tuned LLaMA-2 70B) can generate materials predicted to be metastable at about twice the rate (49% vs 28%) of CDVAE, a competing diffusion model. Because of t","authors_text":"Andrea Madotto, Andrew Gordon Wilson, Anuroop Sriram, C. Lawrence Zitnick, Nate Gruver, Zachary Ulissi","cross_cats":["cond-mat.mtrl-sci"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:35:28Z","title":"Fine-Tuned Language Models Generate Stable Inorganic Materials as Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04379","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b2cb237ec619d907555bd8004f5ac10c365e97e7ba5fe267716a801368552fd5","target":"record","created_at":"2026-07-05T11:42:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c6b53e8ea4c4b2cb8a0689e1d1b02cb8c305bc2ddd1b7a13f07822fa26ff9523","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T20:35:28Z","title_canon_sha256":"b49516fd757773a339748090b876a60139d0aeb8494b0fea077468030514fe41"},"schema_version":"1.0","source":{"id":"2402.04379","kind":"arxiv","version":2}},"canonical_sha256":"a6eef41cee7c93d704aa9cfe023790db5fee0e4382756f58c06c952be5961d6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6eef41cee7c93d704aa9cfe023790db5fee0e4382756f58c06c952be5961d6a","first_computed_at":"2026-07-05T11:42:20.314670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:20.314670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e+oPxvjxPPXmkuFTkMycF8proM54OVJxW0UXyPk4hR8etzAVHvABhA4KLYWolwoeHkZhzBEN7VL/eLYmtFzHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:20.315137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2cb237ec619d907555bd8004f5ac10c365e97e7ba5fe267716a801368552fd5","sha256:3c0913d2886011cf4f0a07e6a9dd2428d3847e2e633e380b18bc087fb3edacba"],"state_sha256":"ee080cf48cdf1a51dd1079236e4aa2f3158c123655c8b8b3c52658dc3dca0255"}