{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KMYKXUJ2GHVXZJUJQP7JIRKAXH","short_pith_number":"pith:KMYKXUJ2","schema_version":"1.0","canonical_sha256":"5330abd13a31eb7ca68983fe944540b9fd2888fcdc0f23e6766cb124e89f94b7","source":{"kind":"arxiv","id":"2004.03497","version":1},"attestation_state":"computed","paper":{"title":"ProGen: Language Modeling for Protein Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-bio.BM","authors_text":"Ali Madani, Bryan McCann, Namrata Anand, Nikhil Naik, Nitish Shirish Keskar, Po-Ssu Huang, Raphael R. Eguchi, Richard Socher","submitted_at":"2020-03-08T04:27:16Z","abstract_excerpt":"Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science. We pose protein engineering as an unsupervised sequence generation problem in order to leverage the exponentially growing set of proteins that lack costly, structural annotations. We train a 1.2B-parameter language model, ProGen, on ~280M protein sequences conditioned on taxonomic and keyword tags such as molecular function and cellular component. This provides ProGen with an unprecedented range of evolutionary sequence diversity and allows it to generate wit"},"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":"2004.03497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2020-03-08T04:27:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"214b46455e91fad9ec9fc8d65da29ca75a7e995a24d0abf1f89a9150d136b432","abstract_canon_sha256":"b2d363e4ef0a5328861a0c5df13b7799510cda78bd7e00d7ac9e355874476e2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:26.781136Z","signature_b64":"fNuNd5i4gDOB81hd64kGpcNdWP3XHvbRlchA78V785K7gH7tEOWmabdIGzvclWzHN7aCkelCeNsfr8kYIb9RAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5330abd13a31eb7ca68983fe944540b9fd2888fcdc0f23e6766cb124e89f94b7","last_reissued_at":"2026-07-05T00:53:26.780665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:26.780665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProGen: Language Modeling for Protein Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-bio.BM","authors_text":"Ali Madani, Bryan McCann, Namrata Anand, Nikhil Naik, Nitish Shirish Keskar, Po-Ssu Huang, Raphael R. Eguchi, Richard Socher","submitted_at":"2020-03-08T04:27:16Z","abstract_excerpt":"Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science. We pose protein engineering as an unsupervised sequence generation problem in order to leverage the exponentially growing set of proteins that lack costly, structural annotations. We train a 1.2B-parameter language model, ProGen, on ~280M protein sequences conditioned on taxonomic and keyword tags such as molecular function and cellular component. This provides ProGen with an unprecedented range of evolutionary sequence diversity and allows it to generate wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03497","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/2004.03497/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":"2004.03497","created_at":"2026-07-05T00:53:26.780719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03497v1","created_at":"2026-07-05T00:53:26.780719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03497","created_at":"2026-07-05T00:53:26.780719+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMYKXUJ2GHVX","created_at":"2026-07-05T00:53:26.780719+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMYKXUJ2GHVXZJUJ","created_at":"2026-07-05T00:53:26.780719+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMYKXUJ2","created_at":"2026-07-05T00:53:26.780719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01628","citing_title":"Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling","ref_index":217,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30963","citing_title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01628","citing_title":"Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21750","citing_title":"From Words to Amino Acids: Does the Curse of Depth Persist?","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2009.14794","citing_title":"Rethinking Attention with Performers","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08826","citing_title":"Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10189","citing_title":"ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00948","citing_title":"Co-Generative De Novo Functional Protein Design","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH","json":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH.json","graph_json":"https://pith.science/api/pith-number/KMYKXUJ2GHVXZJUJQP7JIRKAXH/graph.json","events_json":"https://pith.science/api/pith-number/KMYKXUJ2GHVXZJUJQP7JIRKAXH/events.json","paper":"https://pith.science/paper/KMYKXUJ2"},"agent_actions":{"view_html":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH","download_json":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH.json","view_paper":"https://pith.science/paper/KMYKXUJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03497&json=true","fetch_graph":"https://pith.science/api/pith-number/KMYKXUJ2GHVXZJUJQP7JIRKAXH/graph.json","fetch_events":"https://pith.science/api/pith-number/KMYKXUJ2GHVXZJUJQP7JIRKAXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/action/storage_attestation","attest_author":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/action/author_attestation","sign_citation":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/action/citation_signature","submit_replication":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/action/replication_record"}},"created_at":"2026-07-05T00:53:26.780719+00:00","updated_at":"2026-07-05T00:53:26.780719+00:00"}