{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2ZRWXWMWVHUW23IAZBEDSYTHR","short_pith_number":"pith:M2ZRWXWM","schema_version":"1.0","canonical_sha256":"66b31b5eccb54f4b6b68064241cb133c63f844ec4907a954d283af185c1ecc01","source":{"kind":"arxiv","id":"2403.00875","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Haitao Lin, Lirong Wu, Rui Sun, Stan Z. Li, Yufei Huang","submitted_at":"2024-03-01T07:58:29Z","abstract_excerpt":"Augmentation is an effective alternative to utilize the small amount of labeled protein data. However, most of the existing work focuses on design-ing new architectures or pre-training tasks, and relatively little work has studied data augmentation for proteins. This paper extends data augmentation techniques previously used for images and texts to proteins and then benchmarks these techniques on a variety of protein-related tasks, providing the first comprehensive evaluation of protein augmentation. Furthermore, we propose two novel semantic-level protein augmentation methods, namely Integrat"},"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":"2403.00875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-03-01T07:58:29Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.BM"],"title_canon_sha256":"867b8ea610f0ee95e2918566f20c167c5c34f15fadca6479b2286067c226f7c3","abstract_canon_sha256":"d4a3a2c439df30eb662881c820bb6b011f19d0da30e9e3d754ba0d039a38cd00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:13.124392Z","signature_b64":"H0odiIS1SuY0Kz4kLrQx2Ip2tsMfVmTOuohuebvfMn0Cpk8JQzXKb0M3aRJDfcDEpmmn8sHerBP6+ax35M5WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66b31b5eccb54f4b6b68064241cb133c63f844ec4907a954d283af185c1ecc01","last_reissued_at":"2026-07-05T07:51:13.123957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:13.123957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Haitao Lin, Lirong Wu, Rui Sun, Stan Z. Li, Yufei Huang","submitted_at":"2024-03-01T07:58:29Z","abstract_excerpt":"Augmentation is an effective alternative to utilize the small amount of labeled protein data. However, most of the existing work focuses on design-ing new architectures or pre-training tasks, and relatively little work has studied data augmentation for proteins. This paper extends data augmentation techniques previously used for images and texts to proteins and then benchmarks these techniques on a variety of protein-related tasks, providing the first comprehensive evaluation of protein augmentation. Furthermore, we propose two novel semantic-level protein augmentation methods, namely Integrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00875","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/2403.00875/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":"2403.00875","created_at":"2026-07-05T07:51:13.124013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00875v1","created_at":"2026-07-05T07:51:13.124013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00875","created_at":"2026-07-05T07:51:13.124013+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2ZRWXWMWVHU","created_at":"2026-07-05T07:51:13.124013+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2ZRWXWMWVHUW23I","created_at":"2026-07-05T07:51:13.124013+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2ZRWXWM","created_at":"2026-07-05T07:51:13.124013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22307","citing_title":"Enhancing Protein Representation Learning via Manifold Restore Mixing","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR","json":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR.json","graph_json":"https://pith.science/api/pith-number/M2ZRWXWMWVHUW23IAZBEDSYTHR/graph.json","events_json":"https://pith.science/api/pith-number/M2ZRWXWMWVHUW23IAZBEDSYTHR/events.json","paper":"https://pith.science/paper/M2ZRWXWM"},"agent_actions":{"view_html":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR","download_json":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR.json","view_paper":"https://pith.science/paper/M2ZRWXWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00875&json=true","fetch_graph":"https://pith.science/api/pith-number/M2ZRWXWMWVHUW23IAZBEDSYTHR/graph.json","fetch_events":"https://pith.science/api/pith-number/M2ZRWXWMWVHUW23IAZBEDSYTHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR/action/storage_attestation","attest_author":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR/action/author_attestation","sign_citation":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR/action/citation_signature","submit_replication":"https://pith.science/pith/M2ZRWXWMWVHUW23IAZBEDSYTHR/action/replication_record"}},"created_at":"2026-07-05T07:51:13.124013+00:00","updated_at":"2026-07-05T07:51:13.124013+00:00"}