{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z7STES4WTKPBEBLEJPGWQCWUTQ","short_pith_number":"pith:Z7STES4W","schema_version":"1.0","canonical_sha256":"cfe5324b969a9e1205644bcd680ad49c065d27a9df8f3c7b611c30ec251cdd44","source":{"kind":"arxiv","id":"2410.13768","version":1},"attestation_state":"computed","paper":{"title":"Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.mes-hall","cs.AI","cs.MA"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Alireza Ghafarollahi, Markus J. Buehler","submitted_at":"2024-10-17T17:06:26Z","abstract_excerpt":"A multi-agent AI model is used to automate the discovery of new metallic alloys, integrating multimodal data and external knowledge including insights from physics via atomistic simulations. Our multi-agent system features three key components: (a) a suite of LLMs responsible for tasks such as reasoning and planning, (b) a group of AI agents with distinct roles and expertise that dynamically collaborate, and (c) a newly developed graph neural network (GNN) model for rapid retrieval of key physical properties. A set of LLM-driven AI agents collaborate to automate the exploration of the vast des"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.13768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-10-17T17:06:26Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.mes-hall","cs.AI","cs.MA"],"title_canon_sha256":"9d6ef7a51b447104ae74806d46584afb1cfb62b2b26beee83b9d602bf8085187","abstract_canon_sha256":"845ac09d588d55006228f813c295f1eb4f15ed0d8b1f91f9067107aaf8a165d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:05.419388Z","signature_b64":"oqGqVPotkUkg3Kz8XEccqmIsG1lpZwaGtOttBpIr7w77Q9Z3skho5g9OX0ABtnL/jIBJtFftweA63MjptofYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfe5324b969a9e1205644bcd680ad49c065d27a9df8f3c7b611c30ec251cdd44","last_reissued_at":"2026-07-05T09:22:05.418948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:05.418948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.mes-hall","cs.AI","cs.MA"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Alireza Ghafarollahi, Markus J. Buehler","submitted_at":"2024-10-17T17:06:26Z","abstract_excerpt":"A multi-agent AI model is used to automate the discovery of new metallic alloys, integrating multimodal data and external knowledge including insights from physics via atomistic simulations. Our multi-agent system features three key components: (a) a suite of LLMs responsible for tasks such as reasoning and planning, (b) a group of AI agents with distinct roles and expertise that dynamically collaborate, and (c) a newly developed graph neural network (GNN) model for rapid retrieval of key physical properties. A set of LLM-driven AI agents collaborate to automate the exploration of the vast des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13768","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.13768/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2410.13768","created_at":"2026-07-05T09:22:05.419005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13768v1","created_at":"2026-07-05T09:22:05.419005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13768","created_at":"2026-07-05T09:22:05.419005+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7STES4WTKPB","created_at":"2026-07-05T09:22:05.419005+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7STES4WTKPBEBLE","created_at":"2026-07-05T09:22:05.419005+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7STES4W","created_at":"2026-07-05T09:22:05.419005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06591","citing_title":"Generative Artificial Intelligence Extracts Structure-Function Relationships from Plants for New Materials","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ","json":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ.json","graph_json":"https://pith.science/api/pith-number/Z7STES4WTKPBEBLEJPGWQCWUTQ/graph.json","events_json":"https://pith.science/api/pith-number/Z7STES4WTKPBEBLEJPGWQCWUTQ/events.json","paper":"https://pith.science/paper/Z7STES4W"},"agent_actions":{"view_html":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ","download_json":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ.json","view_paper":"https://pith.science/paper/Z7STES4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13768&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7STES4WTKPBEBLEJPGWQCWUTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7STES4WTKPBEBLEJPGWQCWUTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ/action/storage_attestation","attest_author":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ/action/author_attestation","sign_citation":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ/action/citation_signature","submit_replication":"https://pith.science/pith/Z7STES4WTKPBEBLEJPGWQCWUTQ/action/replication_record"}},"created_at":"2026-07-05T09:22:05.419005+00:00","updated_at":"2026-07-05T09:22:05.419005+00:00"}