{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IAIF6B5CVCRWIJNFEMXB34KI3G","short_pith_number":"pith:IAIF6B5C","schema_version":"1.0","canonical_sha256":"40105f07a2a8a36425a5232e1df148d989ad4030c1a8867084991011460a0d74","source":{"kind":"arxiv","id":"2412.13519","version":1},"attestation_state":"computed","paper":{"title":"Open-Source Protein Language Models for Function Prediction and Protein Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bharath Ramsundar, Shivasankaran Vanaja Pandi","submitted_at":"2024-12-18T05:41:15Z","abstract_excerpt":"Protein language models (PLMs) have shown promise in improving the understanding of protein sequences, contributing to advances in areas such as function prediction and protein engineering. However, training these models from scratch requires significant computational resources, limiting their accessibility. To address this, we integrate a PLM into DeepChem, an open-source framework for computational biology and chemistry, to provide a more accessible platform for protein-related tasks.\n  We evaluate the performance of the integrated model on various protein prediction tasks, showing that it 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":"2412.13519","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T05:41:15Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"0f427ca09a4e61421f82a3638126ebf36fb5dac4e6086d2d66698d25180ca516","abstract_canon_sha256":"e573a30d73f8060d27aea23496ab9601077d5645d4a2863ac5ff7f80b8c4ad11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:03.219868Z","signature_b64":"PZAC4Da6DQiXQw3zPVTTyHICH5am//yP+ckmJpa/sNjAU59PRxixL6aeIkHRhFhssCUXsF3Rh/3fCegU6IAiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40105f07a2a8a36425a5232e1df148d989ad4030c1a8867084991011460a0d74","last_reissued_at":"2026-07-05T09:51:03.219447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:03.219447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Source Protein Language Models for Function Prediction and Protein Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bharath Ramsundar, Shivasankaran Vanaja Pandi","submitted_at":"2024-12-18T05:41:15Z","abstract_excerpt":"Protein language models (PLMs) have shown promise in improving the understanding of protein sequences, contributing to advances in areas such as function prediction and protein engineering. However, training these models from scratch requires significant computational resources, limiting their accessibility. To address this, we integrate a PLM into DeepChem, an open-source framework for computational biology and chemistry, to provide a more accessible platform for protein-related tasks.\n  We evaluate the performance of the integrated model on various protein prediction tasks, showing that it a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13519","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/2412.13519/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":"2412.13519","created_at":"2026-07-05T09:51:03.219505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13519v1","created_at":"2026-07-05T09:51:03.219505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13519","created_at":"2026-07-05T09:51:03.219505+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAIF6B5CVCRW","created_at":"2026-07-05T09:51:03.219505+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAIF6B5CVCRWIJNF","created_at":"2026-07-05T09:51:03.219505+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAIF6B5C","created_at":"2026-07-05T09:51:03.219505+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/IAIF6B5CVCRWIJNFEMXB34KI3G","json":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G.json","graph_json":"https://pith.science/api/pith-number/IAIF6B5CVCRWIJNFEMXB34KI3G/graph.json","events_json":"https://pith.science/api/pith-number/IAIF6B5CVCRWIJNFEMXB34KI3G/events.json","paper":"https://pith.science/paper/IAIF6B5C"},"agent_actions":{"view_html":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G","download_json":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G.json","view_paper":"https://pith.science/paper/IAIF6B5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13519&json=true","fetch_graph":"https://pith.science/api/pith-number/IAIF6B5CVCRWIJNFEMXB34KI3G/graph.json","fetch_events":"https://pith.science/api/pith-number/IAIF6B5CVCRWIJNFEMXB34KI3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/action/storage_attestation","attest_author":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/action/author_attestation","sign_citation":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/action/citation_signature","submit_replication":"https://pith.science/pith/IAIF6B5CVCRWIJNFEMXB34KI3G/action/replication_record"}},"created_at":"2026-07-05T09:51:03.219505+00:00","updated_at":"2026-07-05T09:51:03.219505+00:00"}