{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AGC75AZL3LXKGJCL6WKCESJT2R","short_pith_number":"pith:AGC75AZL","schema_version":"1.0","canonical_sha256":"0185fe832bdaeea3244bf594224933d476707433de55124a9aa15d04e4c05800","source":{"kind":"arxiv","id":"2605.18552","version":1},"attestation_state":"computed","paper":{"title":"Protein Fold Classification at Scale: Benchmarking and Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Andrei Manolache, Dexiong Chen, Karsten Borgwardt, Mathias Niepert","submitted_at":"2026-05-18T15:32:34Z","abstract_excerpt":"Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of large-scale benchmarks that avoid duplicates and by models that do not scale well. We introduce TEDBench, a large-scale, non-redundant benchmark for protein fold classification constructed from the Encyclopedia of Domains (TED) and Foldseek-clustered AlphaFold structures. We show that on TEDBench, current protein representation learning methods either require very large models or fail to deliver strong performance. To address this challenge, we propose Masked Invariant Autoen"},"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":"2605.18552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T15:32:34Z","cross_cats_sorted":["q-bio.BM","q-bio.QM"],"title_canon_sha256":"54d43e159a057fdefe5973a97e81cb75b1f154d5df2ed56b9e6f206cc3cfaf0e","abstract_canon_sha256":"16cc5ff8c1652bbdf6df7a49d5b6c9126d3d8a4b5d03d725a8443155c9cba5e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:07.361352Z","signature_b64":"xOq9LmqlcqWarGeen6fwbIxGEv/ceemusmgx3ocj0HkBdtSWHUq9TKmCrXlIVzPQpqfNnvO8AwncgYN5tuffDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0185fe832bdaeea3244bf594224933d476707433de55124a9aa15d04e4c05800","last_reissued_at":"2026-05-20T00:06:07.360471Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:07.360471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protein Fold Classification at Scale: Benchmarking and Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Andrei Manolache, Dexiong Chen, Karsten Borgwardt, Mathias Niepert","submitted_at":"2026-05-18T15:32:34Z","abstract_excerpt":"Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of large-scale benchmarks that avoid duplicates and by models that do not scale well. We introduce TEDBench, a large-scale, non-redundant benchmark for protein fold classification constructed from the Encyclopedia of Domains (TED) and Foldseek-clustered AlphaFold structures. We show that on TEDBench, current protein representation learning methods either require very large models or fail to deliver strong performance. To address this challenge, we propose Masked Invariant Autoen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18552","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/2605.18552/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":"2605.18552","created_at":"2026-05-20T00:06:07.360608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18552v1","created_at":"2026-05-20T00:06:07.360608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18552","created_at":"2026-05-20T00:06:07.360608+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGC75AZL3LXK","created_at":"2026-05-20T00:06:07.360608+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGC75AZL3LXKGJCL","created_at":"2026-05-20T00:06:07.360608+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGC75AZL","created_at":"2026-05-20T00:06:07.360608+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/AGC75AZL3LXKGJCL6WKCESJT2R","json":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R.json","graph_json":"https://pith.science/api/pith-number/AGC75AZL3LXKGJCL6WKCESJT2R/graph.json","events_json":"https://pith.science/api/pith-number/AGC75AZL3LXKGJCL6WKCESJT2R/events.json","paper":"https://pith.science/paper/AGC75AZL"},"agent_actions":{"view_html":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R","download_json":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R.json","view_paper":"https://pith.science/paper/AGC75AZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18552&json=true","fetch_graph":"https://pith.science/api/pith-number/AGC75AZL3LXKGJCL6WKCESJT2R/graph.json","fetch_events":"https://pith.science/api/pith-number/AGC75AZL3LXKGJCL6WKCESJT2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R/action/storage_attestation","attest_author":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R/action/author_attestation","sign_citation":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R/action/citation_signature","submit_replication":"https://pith.science/pith/AGC75AZL3LXKGJCL6WKCESJT2R/action/replication_record"}},"created_at":"2026-05-20T00:06:07.360608+00:00","updated_at":"2026-05-20T00:06:07.360608+00:00"}