{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ES6MVWES4KEIR3Z7CRDB3UGHA5","short_pith_number":"pith:ES6MVWES","schema_version":"1.0","canonical_sha256":"24bccad892e28888ef3f14461dd0c7077ce6c3749422efc3f948c052fc07c2c7","source":{"kind":"arxiv","id":"2303.17728","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of GPT and BERT-based models on identifying protein-protein interactions in biomedical text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arzucan \\\"Ozg\\\"ur, Christianah Jemiyo, Hasin Rehana, Jie Zheng, Junguk Hur, Mert Basmaci, Nur Bengisu \\c{C}am, Yongqun He","submitted_at":"2023-03-30T22:06:10Z","abstract_excerpt":"Detecting protein-protein interactions (PPIs) is crucial for understanding genetic mechanisms, disease pathogenesis, and drug design. However, with the fast-paced growth of biomedical literature, there is a growing need for automated and accurate extraction of PPIs to facilitate scientific knowledge discovery. Pre-trained language models, such as generative pre-trained transformers (GPT) and bidirectional encoder representations from transformers (BERT), have shown promising results in natural language processing (NLP) tasks. We evaluated the performance of PPI identification of multiple GPT a"},"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":"2303.17728","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-30T22:06:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4620f18f6ea8ae47b389d42b17cdaffb35091be1c97588dd9857ba03db061435","abstract_canon_sha256":"a0d804e6a41af41b5b4f7dbe382e9de9c4a3b79898fed7c7c5cc5beae2065e84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:24.938039Z","signature_b64":"7WX+QVJqycl7Tc/W4+6qsh0n7P+hpH/l5KFxVx41cQRJw8j9QxnMAk66yhPkeccZ78a0f4lOzYONlhCoor6ADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24bccad892e28888ef3f14461dd0c7077ce6c3749422efc3f948c052fc07c2c7","last_reissued_at":"2026-07-05T07:23:24.937612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:24.937612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of GPT and BERT-based models on identifying protein-protein interactions in biomedical text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arzucan \\\"Ozg\\\"ur, Christianah Jemiyo, Hasin Rehana, Jie Zheng, Junguk Hur, Mert Basmaci, Nur Bengisu \\c{C}am, Yongqun He","submitted_at":"2023-03-30T22:06:10Z","abstract_excerpt":"Detecting protein-protein interactions (PPIs) is crucial for understanding genetic mechanisms, disease pathogenesis, and drug design. However, with the fast-paced growth of biomedical literature, there is a growing need for automated and accurate extraction of PPIs to facilitate scientific knowledge discovery. Pre-trained language models, such as generative pre-trained transformers (GPT) and bidirectional encoder representations from transformers (BERT), have shown promising results in natural language processing (NLP) tasks. We evaluated the performance of PPI identification of multiple GPT a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17728","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/2303.17728/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":"2303.17728","created_at":"2026-07-05T07:23:24.937669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17728v2","created_at":"2026-07-05T07:23:24.937669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17728","created_at":"2026-07-05T07:23:24.937669+00:00"},{"alias_kind":"pith_short_12","alias_value":"ES6MVWES4KEI","created_at":"2026-07-05T07:23:24.937669+00:00"},{"alias_kind":"pith_short_16","alias_value":"ES6MVWES4KEIR3Z7","created_at":"2026-07-05T07:23:24.937669+00:00"},{"alias_kind":"pith_short_8","alias_value":"ES6MVWES","created_at":"2026-07-05T07:23:24.937669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08897","citing_title":"PlantDeBERTa: An Open Source Language Model for Plant Science","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5","json":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5.json","graph_json":"https://pith.science/api/pith-number/ES6MVWES4KEIR3Z7CRDB3UGHA5/graph.json","events_json":"https://pith.science/api/pith-number/ES6MVWES4KEIR3Z7CRDB3UGHA5/events.json","paper":"https://pith.science/paper/ES6MVWES"},"agent_actions":{"view_html":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5","download_json":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5.json","view_paper":"https://pith.science/paper/ES6MVWES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17728&json=true","fetch_graph":"https://pith.science/api/pith-number/ES6MVWES4KEIR3Z7CRDB3UGHA5/graph.json","fetch_events":"https://pith.science/api/pith-number/ES6MVWES4KEIR3Z7CRDB3UGHA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5/action/storage_attestation","attest_author":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5/action/author_attestation","sign_citation":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5/action/citation_signature","submit_replication":"https://pith.science/pith/ES6MVWES4KEIR3Z7CRDB3UGHA5/action/replication_record"}},"created_at":"2026-07-05T07:23:24.937669+00:00","updated_at":"2026-07-05T07:23:24.937669+00:00"}