{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7GJ2MTW66MZJYFVOOH2AYHHGUU","short_pith_number":"pith:7GJ2MTW6","schema_version":"1.0","canonical_sha256":"f993a64edef3329c16ae71f40c1ce6a50ccfb550e62d5612d56d9333751ea6d6","source":{"kind":"arxiv","id":"2303.11783","version":2},"attestation_state":"computed","paper":{"title":"CCPL: Cross-modal Contrastive Protein Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Jiangbin Zheng, Stan Z. Li","submitted_at":"2023-03-19T08:19:10Z","abstract_excerpt":"Effective protein representation learning is crucial for predicting protein functions. Traditional methods often pretrain protein language models on large, unlabeled amino acid sequences, followed by finetuning on labeled data. While effective, these methods underutilize the potential of protein structures, which are vital for function determination. Common structural representation techniques rely heavily on annotated data, limiting their generalizability. Moreover, structural pretraining methods, similar to natural language pretraining, can distort actual protein structures. In this work, we"},"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":"2303.11783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2023-03-19T08:19:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fcec865572eb722a6e0d1ca4d2a43d341f30daf3d170eea27bb06fa2375dc1ce","abstract_canon_sha256":"6c82bb60912c926de0406a74010ede4b8a16f9c3a3192c4f63b63bf4dbf83f6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:39.271152Z","signature_b64":"b0RvQrpxVOH010Z2KNr5TZSY4oGr3fj8CN/3p0KF/zquHwdAVmdWSQTkXlwl3SRGQd+/eVBhnAxtX5fMHQI3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f993a64edef3329c16ae71f40c1ce6a50ccfb550e62d5612d56d9333751ea6d6","last_reissued_at":"2026-07-05T09:02:39.270313Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:39.270313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCPL: Cross-modal Contrastive Protein Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Jiangbin Zheng, Stan Z. Li","submitted_at":"2023-03-19T08:19:10Z","abstract_excerpt":"Effective protein representation learning is crucial for predicting protein functions. Traditional methods often pretrain protein language models on large, unlabeled amino acid sequences, followed by finetuning on labeled data. While effective, these methods underutilize the potential of protein structures, which are vital for function determination. Common structural representation techniques rely heavily on annotated data, limiting their generalizability. Moreover, structural pretraining methods, similar to natural language pretraining, can distort actual protein structures. In this work, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11783","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/2303.11783/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":"2303.11783","created_at":"2026-07-05T09:02:39.270398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11783v2","created_at":"2026-07-05T09:02:39.270398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11783","created_at":"2026-07-05T09:02:39.270398+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GJ2MTW66MZJ","created_at":"2026-07-05T09:02:39.270398+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GJ2MTW66MZJYFVO","created_at":"2026-07-05T09:02:39.270398+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GJ2MTW6","created_at":"2026-07-05T09:02:39.270398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17798","citing_title":"DapPep: Domain Adaptive Peptide-agnostic Learning for Universal T-cell Receptor-antigen Binding Affinity Prediction","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU","json":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU.json","graph_json":"https://pith.science/api/pith-number/7GJ2MTW66MZJYFVOOH2AYHHGUU/graph.json","events_json":"https://pith.science/api/pith-number/7GJ2MTW66MZJYFVOOH2AYHHGUU/events.json","paper":"https://pith.science/paper/7GJ2MTW6"},"agent_actions":{"view_html":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU","download_json":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU.json","view_paper":"https://pith.science/paper/7GJ2MTW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11783&json=true","fetch_graph":"https://pith.science/api/pith-number/7GJ2MTW66MZJYFVOOH2AYHHGUU/graph.json","fetch_events":"https://pith.science/api/pith-number/7GJ2MTW66MZJYFVOOH2AYHHGUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU/action/storage_attestation","attest_author":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU/action/author_attestation","sign_citation":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU/action/citation_signature","submit_replication":"https://pith.science/pith/7GJ2MTW66MZJYFVOOH2AYHHGUU/action/replication_record"}},"created_at":"2026-07-05T09:02:39.270398+00:00","updated_at":"2026-07-05T09:02:39.270398+00:00"}