{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VYQDCBLICNURK5RAUT7CEUDNJ3","short_pith_number":"pith:VYQDCBLI","schema_version":"1.0","canonical_sha256":"ae203105681369157620a4fe22506d4ec7c5f1aed787f30e5a2b50631788e1c2","source":{"kind":"arxiv","id":"2306.12231","version":2},"attestation_state":"computed","paper":{"title":"Predicting protein variants with equivariant graph neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Antonia Boca, Simon Mathis","submitted_at":"2023-06-21T12:44:52Z","abstract_excerpt":"Pre-trained models have been successful in many protein engineering tasks. Most notably, sequence-based models have achieved state-of-the-art performance on protein fitness prediction while structure-based models have been used experimentally to develop proteins with enhanced functions. However, there is a research gap in comparing structure- and sequence-based methods for predicting protein variants that are better than the wildtype protein. This paper aims to address this gap by conducting a comparative study between the abilities of equivariant graph neural networks (EGNNs) and sequence-bas"},"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":"2306.12231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T12:44:52Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"98c166887fddc04f24fbd39a0401e4444a7e7e7768ab633bf909b5e547a2ba68","abstract_canon_sha256":"d2c074fb939abe4326075a4564b410d01d0b4d8e2571327f3d579d5d8da0d743"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:46.388861Z","signature_b64":"2z4tYZQxMegjntEgOglkwO1/VDraoGlZi6VvvSjjUbnK0Bvz+vfUdVC/LqnS8bWhB6N9Q/Z1gWUFB3U2n671CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae203105681369157620a4fe22506d4ec7c5f1aed787f30e5a2b50631788e1c2","last_reissued_at":"2026-07-05T06:33:46.388441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:46.388441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting protein variants with equivariant graph neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Antonia Boca, Simon Mathis","submitted_at":"2023-06-21T12:44:52Z","abstract_excerpt":"Pre-trained models have been successful in many protein engineering tasks. Most notably, sequence-based models have achieved state-of-the-art performance on protein fitness prediction while structure-based models have been used experimentally to develop proteins with enhanced functions. However, there is a research gap in comparing structure- and sequence-based methods for predicting protein variants that are better than the wildtype protein. This paper aims to address this gap by conducting a comparative study between the abilities of equivariant graph neural networks (EGNNs) and sequence-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12231","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/2306.12231/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":"2306.12231","created_at":"2026-07-05T06:33:46.388498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12231v2","created_at":"2026-07-05T06:33:46.388498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12231","created_at":"2026-07-05T06:33:46.388498+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYQDCBLICNUR","created_at":"2026-07-05T06:33:46.388498+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYQDCBLICNURK5RA","created_at":"2026-07-05T06:33:46.388498+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYQDCBLI","created_at":"2026-07-05T06:33:46.388498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16886","citing_title":"Exploring zero-shot structure-based protein fitness prediction","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3","json":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3.json","graph_json":"https://pith.science/api/pith-number/VYQDCBLICNURK5RAUT7CEUDNJ3/graph.json","events_json":"https://pith.science/api/pith-number/VYQDCBLICNURK5RAUT7CEUDNJ3/events.json","paper":"https://pith.science/paper/VYQDCBLI"},"agent_actions":{"view_html":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3","download_json":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3.json","view_paper":"https://pith.science/paper/VYQDCBLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12231&json=true","fetch_graph":"https://pith.science/api/pith-number/VYQDCBLICNURK5RAUT7CEUDNJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/VYQDCBLICNURK5RAUT7CEUDNJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3/action/storage_attestation","attest_author":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3/action/author_attestation","sign_citation":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3/action/citation_signature","submit_replication":"https://pith.science/pith/VYQDCBLICNURK5RAUT7CEUDNJ3/action/replication_record"}},"created_at":"2026-07-05T06:33:46.388498+00:00","updated_at":"2026-07-05T06:33:46.388498+00:00"}