{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EQNKHU6KI7K6MUPBEYANCYSX4I","short_pith_number":"pith:EQNKHU6K","schema_version":"1.0","canonical_sha256":"241aa3d3ca47d5e651e12600d16257e22b3ab56f913208b1092ce6164f393070","source":{"kind":"arxiv","id":"2310.16802","version":2},"attestation_state":"computed","paper":{"title":"From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adeesh Kolluru, Brandon M. Wood, C. Lawrence Zitnick, John R. Kitchin, Nima Shoghi, Zachary W. Ulissi","submitted_at":"2023-10-25T17:32:23Z","abstract_excerpt":"Foundation models have been transformational in machine learning fields such as natural language processing and computer vision. Similar success in atomic property prediction has been limited due to the challenges of training effective models across multiple chemical domains. To address this, we introduce Joint Multi-domain Pre-training (JMP), a supervised pre-training strategy that simultaneously trains on multiple datasets from different chemical domains, treating each dataset as a unique pre-training task within a multi-task framework. Our combined training dataset consists of $\\sim$120M sy"},"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":"2310.16802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T17:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"23ac0047e68178bc3e09b7710629a51360b69af10e2af66de8ed51e6c7786e26","abstract_canon_sha256":"4d4eff12bd720406cd98600e4fa99f6092c6ee41c30e60893e58a9a3ff40b221"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:40.972603Z","signature_b64":"oRbCC9aKFyNdTwweNthg1sVtOJ/QyYe6yQ/rT7w8pGnHrjv/+aQ6mqjAw1UWs5suXvCJ+Fy/eMzvgYqxRocWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241aa3d3ca47d5e651e12600d16257e22b3ab56f913208b1092ce6164f393070","last_reissued_at":"2026-07-05T08:15:40.972096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:40.972096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adeesh Kolluru, Brandon M. Wood, C. Lawrence Zitnick, John R. Kitchin, Nima Shoghi, Zachary W. Ulissi","submitted_at":"2023-10-25T17:32:23Z","abstract_excerpt":"Foundation models have been transformational in machine learning fields such as natural language processing and computer vision. Similar success in atomic property prediction has been limited due to the challenges of training effective models across multiple chemical domains. To address this, we introduce Joint Multi-domain Pre-training (JMP), a supervised pre-training strategy that simultaneously trains on multiple datasets from different chemical domains, treating each dataset as a unique pre-training task within a multi-task framework. Our combined training dataset consists of $\\sim$120M sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16802","kind":"arxiv","version":2},"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/2310.16802/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":"2310.16802","created_at":"2026-07-05T08:15:40.972149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16802v2","created_at":"2026-07-05T08:15:40.972149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16802","created_at":"2026-07-05T08:15:40.972149+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQNKHU6KI7K6","created_at":"2026-07-05T08:15:40.972149+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQNKHU6KI7K6MUPB","created_at":"2026-07-05T08:15:40.972149+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQNKHU6K","created_at":"2026-07-05T08:15:40.972149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03232","citing_title":"GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2405.04967","citing_title":"MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13297","citing_title":"PaMM: Periodic Motif Memory for Atomistic Models with an Explicit Local-Structure Interface","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I","json":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I.json","graph_json":"https://pith.science/api/pith-number/EQNKHU6KI7K6MUPBEYANCYSX4I/graph.json","events_json":"https://pith.science/api/pith-number/EQNKHU6KI7K6MUPBEYANCYSX4I/events.json","paper":"https://pith.science/paper/EQNKHU6K"},"agent_actions":{"view_html":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I","download_json":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I.json","view_paper":"https://pith.science/paper/EQNKHU6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16802&json=true","fetch_graph":"https://pith.science/api/pith-number/EQNKHU6KI7K6MUPBEYANCYSX4I/graph.json","fetch_events":"https://pith.science/api/pith-number/EQNKHU6KI7K6MUPBEYANCYSX4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I/action/storage_attestation","attest_author":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I/action/author_attestation","sign_citation":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I/action/citation_signature","submit_replication":"https://pith.science/pith/EQNKHU6KI7K6MUPBEYANCYSX4I/action/replication_record"}},"created_at":"2026-07-05T08:15:40.972149+00:00","updated_at":"2026-07-05T08:15:40.972149+00:00"}