{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5CTWA2JE5SPVDQT7MCR3SEZU7U","short_pith_number":"pith:5CTWA2JE","schema_version":"1.0","canonical_sha256":"e8a7606924ec9f51c27f60a3b91334fd0fb16a41ce76272641e45914dc35326b","source":{"kind":"arxiv","id":"2309.03099","version":1},"attestation_state":"computed","paper":{"title":"PeptideBERT: A Language Model based on Transformers for Peptide Property Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Adrita Das, Amir Barati Farimani, Chakradhar Guntuboina, Parisa Mollaei, Seongwon Kim","submitted_at":"2023-08-28T01:09:21Z","abstract_excerpt":"Recent advances in Language Models have enabled the protein modeling community with a powerful tool since protein sequences can be represented as text. Specifically, by taking advantage of Transformers, sequence-to-property prediction will be amenable without the need for explicit structural data. In this work, inspired by recent progress in Large Language Models (LLMs), we introduce PeptideBERT, a protein language model for predicting three key properties of peptides (hemolysis, solubility, and non-fouling). The PeptideBert utilizes the ProtBERT pretrained transformer model with 12 attention "},"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":"2309.03099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-28T01:09:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8df6ad69ce94416bda613e37a5b7d9986b80df6be2f54322218ff6a91378de7a","abstract_canon_sha256":"21b8e0c15e1036f6e4aeca2b5ab549d3a237006e105cc1aa9ebce3ba9918f322"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:20.850650Z","signature_b64":"32X/faQvpX0d5cAOYiCWQFnTBIAMENws6OPhQQRVMuLWLfftAYtaPogYyM7Wx3jcq3BNHGzilbCE4egWIRp/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8a7606924ec9f51c27f60a3b91334fd0fb16a41ce76272641e45914dc35326b","last_reissued_at":"2026-07-05T06:48:20.850155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:20.850155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PeptideBERT: A Language Model based on Transformers for Peptide Property Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Adrita Das, Amir Barati Farimani, Chakradhar Guntuboina, Parisa Mollaei, Seongwon Kim","submitted_at":"2023-08-28T01:09:21Z","abstract_excerpt":"Recent advances in Language Models have enabled the protein modeling community with a powerful tool since protein sequences can be represented as text. Specifically, by taking advantage of Transformers, sequence-to-property prediction will be amenable without the need for explicit structural data. In this work, inspired by recent progress in Large Language Models (LLMs), we introduce PeptideBERT, a protein language model for predicting three key properties of peptides (hemolysis, solubility, and non-fouling). The PeptideBert utilizes the ProtBERT pretrained transformer model with 12 attention "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03099","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/2309.03099/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":"2309.03099","created_at":"2026-07-05T06:48:20.850212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.03099v1","created_at":"2026-07-05T06:48:20.850212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03099","created_at":"2026-07-05T06:48:20.850212+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CTWA2JE5SPV","created_at":"2026-07-05T06:48:20.850212+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CTWA2JE5SPVDQT7","created_at":"2026-07-05T06:48:20.850212+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CTWA2JE","created_at":"2026-07-05T06:48:20.850212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20098","citing_title":"Transformers in Protein: A Survey","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U","json":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U.json","graph_json":"https://pith.science/api/pith-number/5CTWA2JE5SPVDQT7MCR3SEZU7U/graph.json","events_json":"https://pith.science/api/pith-number/5CTWA2JE5SPVDQT7MCR3SEZU7U/events.json","paper":"https://pith.science/paper/5CTWA2JE"},"agent_actions":{"view_html":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U","download_json":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U.json","view_paper":"https://pith.science/paper/5CTWA2JE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.03099&json=true","fetch_graph":"https://pith.science/api/pith-number/5CTWA2JE5SPVDQT7MCR3SEZU7U/graph.json","fetch_events":"https://pith.science/api/pith-number/5CTWA2JE5SPVDQT7MCR3SEZU7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/action/storage_attestation","attest_author":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/action/author_attestation","sign_citation":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/action/citation_signature","submit_replication":"https://pith.science/pith/5CTWA2JE5SPVDQT7MCR3SEZU7U/action/replication_record"}},"created_at":"2026-07-05T06:48:20.850212+00:00","updated_at":"2026-07-05T06:48:20.850212+00:00"}