{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7XDAMJWASQEDU6CN6ZP5OVCTRP","short_pith_number":"pith:7XDAMJWA","schema_version":"1.0","canonical_sha256":"fdc60626c094083a784df65fd754538bc3674b05aeceec4ebdbab33dd894f660","source":{"kind":"arxiv","id":"2502.01533","version":1},"attestation_state":"computed","paper":{"title":"Transformers trained on proteins can learn to attend to Euclidean distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Charlotte M. Deane, Constantin Schneider, Isaac Ellmen, Matthew I.J. Raybould","submitted_at":"2025-02-03T17:12:44Z","abstract_excerpt":"While conventional Transformers generally operate on sequence data, they can be used in conjunction with structure models, typically SE(3)-invariant or equivariant graph neural networks (GNNs), for 3D applications such as protein structure modelling. These hybrids typically involve either (1) preprocessing/tokenizing structural features as input for Transformers or (2) taking Transformer embeddings and processing them within a structural representation. However, there is evidence that Transformers can learn to process structural information on their own, such as the AlphaFold3 structural diffu"},"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":"2502.01533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T17:12:44Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"0b7dd4390b2041942757cb3b680e317023a2ae8cec45f7916dfe2e3babee72e3","abstract_canon_sha256":"43a64e0f9e49cf38a3c4d6fc164ec1091ecb780a698785ccfcdb3babbc6c67d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:38.846301Z","signature_b64":"dPk2AQeDiIPW09dHSuotkpI8p4nGrAE6xa/00GLnzjAB77Nc0+IijQ3V5dnEYVUDlsd+x6dhU5TWX1vQOO/bDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdc60626c094083a784df65fd754538bc3674b05aeceec4ebdbab33dd894f660","last_reissued_at":"2026-07-05T11:46:38.845800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:38.845800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers trained on proteins can learn to attend to Euclidean distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Charlotte M. Deane, Constantin Schneider, Isaac Ellmen, Matthew I.J. Raybould","submitted_at":"2025-02-03T17:12:44Z","abstract_excerpt":"While conventional Transformers generally operate on sequence data, they can be used in conjunction with structure models, typically SE(3)-invariant or equivariant graph neural networks (GNNs), for 3D applications such as protein structure modelling. These hybrids typically involve either (1) preprocessing/tokenizing structural features as input for Transformers or (2) taking Transformer embeddings and processing them within a structural representation. However, there is evidence that Transformers can learn to process structural information on their own, such as the AlphaFold3 structural diffu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01533","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/2502.01533/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":"2502.01533","created_at":"2026-07-05T11:46:38.845877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01533v1","created_at":"2026-07-05T11:46:38.845877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01533","created_at":"2026-07-05T11:46:38.845877+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XDAMJWASQED","created_at":"2026-07-05T11:46:38.845877+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XDAMJWASQEDU6CN","created_at":"2026-07-05T11:46:38.845877+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XDAMJWA","created_at":"2026-07-05T11:46:38.845877+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/7XDAMJWASQEDU6CN6ZP5OVCTRP","json":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP.json","graph_json":"https://pith.science/api/pith-number/7XDAMJWASQEDU6CN6ZP5OVCTRP/graph.json","events_json":"https://pith.science/api/pith-number/7XDAMJWASQEDU6CN6ZP5OVCTRP/events.json","paper":"https://pith.science/paper/7XDAMJWA"},"agent_actions":{"view_html":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP","download_json":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP.json","view_paper":"https://pith.science/paper/7XDAMJWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01533&json=true","fetch_graph":"https://pith.science/api/pith-number/7XDAMJWASQEDU6CN6ZP5OVCTRP/graph.json","fetch_events":"https://pith.science/api/pith-number/7XDAMJWASQEDU6CN6ZP5OVCTRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP/action/storage_attestation","attest_author":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP/action/author_attestation","sign_citation":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP/action/citation_signature","submit_replication":"https://pith.science/pith/7XDAMJWASQEDU6CN6ZP5OVCTRP/action/replication_record"}},"created_at":"2026-07-05T11:46:38.845877+00:00","updated_at":"2026-07-05T11:46:38.845877+00:00"}