{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DOPE75Z7VACDO2YCEBNEW2WDRB","short_pith_number":"pith:DOPE75Z7","schema_version":"1.0","canonical_sha256":"1b9e4ff73fa804376b02205a4b6ac3884c09b2bb94649c3785b0bf4a0e99439d","source":{"kind":"arxiv","id":"2206.13517","version":1},"attestation_state":"computed","paper":{"title":"ProGen2: Exploring the Boundaries of Protein Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ali Madani, Eli N. Weinstein, Erik Nijkamp, Jeffrey Ruffolo, Nikhil Naik","submitted_at":"2022-06-27T17:55:02Z","abstract_excerpt":"Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial intelligence-driven protein design. However, we lack a sufficient understanding of how very large-scale models and data play a role in effective protein model development. We introduce a suite of protein language models, named ProGen2, that are scaled up to 6.4B parameters and trained on different sequence datasets drawn from over a billion proteins from genomic, metagenomic, and immune repertoire databases. ProGen2 models show state-of-the-art"},"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":"2206.13517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T17:55:02Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"343359ac1a916ed2ce35ac7479604ed2dc7ab75ffa8e2dd269c0a7c2dc57917f","abstract_canon_sha256":"9a26ada6ab4f9b5ff7b9521192a1fb38f3375b2e8afcd781fb59ce5ff8c35768"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:51.790755Z","signature_b64":"YNv2wvPWTcaJhBj1IuXTbnqsAfHZ7c9WQFHKX43re9Jccdofsi7RTn6uWP0mGU90GW2fRCwuQMoOKGJBz/S+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b9e4ff73fa804376b02205a4b6ac3884c09b2bb94649c3785b0bf4a0e99439d","last_reissued_at":"2026-07-05T04:35:51.790294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:51.790294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProGen2: Exploring the Boundaries of Protein Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ali Madani, Eli N. Weinstein, Erik Nijkamp, Jeffrey Ruffolo, Nikhil Naik","submitted_at":"2022-06-27T17:55:02Z","abstract_excerpt":"Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial intelligence-driven protein design. However, we lack a sufficient understanding of how very large-scale models and data play a role in effective protein model development. We introduce a suite of protein language models, named ProGen2, that are scaled up to 6.4B parameters and trained on different sequence datasets drawn from over a billion proteins from genomic, metagenomic, and immune repertoire databases. ProGen2 models show state-of-the-art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13517","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/2206.13517/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":"2206.13517","created_at":"2026-07-05T04:35:51.790369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.13517v1","created_at":"2026-07-05T04:35:51.790369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13517","created_at":"2026-07-05T04:35:51.790369+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOPE75Z7VACD","created_at":"2026-07-05T04:35:51.790369+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOPE75Z7VACDO2YC","created_at":"2026-07-05T04:35:51.790369+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOPE75Z7","created_at":"2026-07-05T04:35:51.790369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2303.17564","citing_title":"BloombergGPT: A Large Language Model for Finance","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07554","citing_title":"ProteinJEPA: Latent prediction complements protein language models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB","json":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB.json","graph_json":"https://pith.science/api/pith-number/DOPE75Z7VACDO2YCEBNEW2WDRB/graph.json","events_json":"https://pith.science/api/pith-number/DOPE75Z7VACDO2YCEBNEW2WDRB/events.json","paper":"https://pith.science/paper/DOPE75Z7"},"agent_actions":{"view_html":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB","download_json":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB.json","view_paper":"https://pith.science/paper/DOPE75Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.13517&json=true","fetch_graph":"https://pith.science/api/pith-number/DOPE75Z7VACDO2YCEBNEW2WDRB/graph.json","fetch_events":"https://pith.science/api/pith-number/DOPE75Z7VACDO2YCEBNEW2WDRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB/action/storage_attestation","attest_author":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB/action/author_attestation","sign_citation":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB/action/citation_signature","submit_replication":"https://pith.science/pith/DOPE75Z7VACDO2YCEBNEW2WDRB/action/replication_record"}},"created_at":"2026-07-05T04:35:51.790369+00:00","updated_at":"2026-07-05T04:35:51.790369+00:00"}