{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZI4IHMLRORCZ6XJR3ZEQFD4EIH","short_pith_number":"pith:ZI4IHMLR","schema_version":"1.0","canonical_sha256":"ca3883b17174459f5d31de49028f8441c2791ac472f554d42058264275425c0b","source":{"kind":"arxiv","id":"2605.20581","version":1},"attestation_state":"computed","paper":{"title":"TriForces: Augmenting Atomistic GNNs for Transferable Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.LG","authors_text":"Alexandre Duval, Ali Ramlaoui, Fragkiskos D. Malliaros, Hannah Bull, Hugues Talbot, Joseph Musielewicz, Victor Schmidt","submitted_at":"2026-05-20T00:38:43Z","abstract_excerpt":"Machine learning interatomic potentials (MLIPs) achieve excellent accuracy when trained on large Density Functional Theory (DFT) data. To be useful in practice, they must often be adapted to target chemistries using small and expensive task-specific datasets. However, MLIPs transfer inconsistently across domains, with representations that often loose accessible composition and structure information. To address this, we present TriForces, a model-agnostic three-stream framework that separates composition and structure information, combined with self-supervised learning to preserve transferable "},"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":"2605.20581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:38:43Z","cross_cats_sorted":["cond-mat.mtrl-sci"],"title_canon_sha256":"9607b313561026abffdfbab712ba184e54d142dbeb90df57977801643be1c65f","abstract_canon_sha256":"1047bb4bd97345e3bb23dc5ccb0ef34e83d7c2aa10f79ed5fd03c051d8cc0987"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:43.379565Z","signature_b64":"E2QtOdLmO0wbhTQLzr7hBqVPxCcNSnVb/n04l98T+Ex0meTPo9p842tdKJSlaADoAb96hD2s5jsjipxsVDwlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3883b17174459f5d31de49028f8441c2791ac472f554d42058264275425c0b","last_reissued_at":"2026-05-21T01:04:43.378903Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:43.378903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TriForces: Augmenting Atomistic GNNs for Transferable Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.LG","authors_text":"Alexandre Duval, Ali Ramlaoui, Fragkiskos D. Malliaros, Hannah Bull, Hugues Talbot, Joseph Musielewicz, Victor Schmidt","submitted_at":"2026-05-20T00:38:43Z","abstract_excerpt":"Machine learning interatomic potentials (MLIPs) achieve excellent accuracy when trained on large Density Functional Theory (DFT) data. To be useful in practice, they must often be adapted to target chemistries using small and expensive task-specific datasets. However, MLIPs transfer inconsistently across domains, with representations that often loose accessible composition and structure information. To address this, we present TriForces, a model-agnostic three-stream framework that separates composition and structure information, combined with self-supervised learning to preserve transferable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20581","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/2605.20581/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":"2605.20581","created_at":"2026-05-21T01:04:43.378995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20581v1","created_at":"2026-05-21T01:04:43.378995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20581","created_at":"2026-05-21T01:04:43.378995+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZI4IHMLRORCZ","created_at":"2026-05-21T01:04:43.378995+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZI4IHMLRORCZ6XJR","created_at":"2026-05-21T01:04:43.378995+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZI4IHMLR","created_at":"2026-05-21T01:04:43.378995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH","json":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH.json","graph_json":"https://pith.science/api/pith-number/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/graph.json","events_json":"https://pith.science/api/pith-number/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/events.json","paper":"https://pith.science/paper/ZI4IHMLR"},"agent_actions":{"view_html":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH","download_json":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH.json","view_paper":"https://pith.science/paper/ZI4IHMLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20581&json=true","fetch_graph":"https://pith.science/api/pith-number/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/action/storage_attestation","attest_author":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/action/author_attestation","sign_citation":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/action/citation_signature","submit_replication":"https://pith.science/pith/ZI4IHMLRORCZ6XJR3ZEQFD4EIH/action/replication_record"}},"created_at":"2026-05-21T01:04:43.378995+00:00","updated_at":"2026-05-21T01:04:43.378995+00:00"}