{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SV3W7U7OP4LTUN5OCZK4GLQ75E","short_pith_number":"pith:SV3W7U7O","schema_version":"1.0","canonical_sha256":"95776fd3ee7f173a37ae1655c32e1fe913e9ffa29821b974e2d481b11c7f2db1","source":{"kind":"arxiv","id":"2204.01168","version":1},"attestation_state":"computed","paper":{"title":"Few Shot Protein Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"q-bio.BM","authors_text":"Soumya Ram, Tristan Bepler","submitted_at":"2022-04-03T22:14:02Z","abstract_excerpt":"We present the MSA-to-protein transformer, a generative model of protein sequences conditioned on protein families represented by multiple sequence alignments (MSAs). Unlike existing approaches to learning generative models of protein families, the MSA-to-protein transformer conditions sequence generation directly on a learned encoding of the multiple sequence alignment, circumventing the need for fitting dedicated family models. By training on a large set of well-curated multiple sequence alignments in Pfam, our MSA-to-protein transformer generalizes well to protein families not observed duri"},"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":"2204.01168","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-04-03T22:14:02Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"faf9ae244a65991a56ed3afcde13222ad41d428dc2ce2aee9cf75b40e4cb0382","abstract_canon_sha256":"bdf405dc8966f74c4c25b210586b79abce2f9467da5bb63d20eb242db2d9db49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:16.099260Z","signature_b64":"CWPRDnH74MLH8+0J1/AAorlLbVwD8MUCOyvKGRTsSHyOI1AV9G/b57aug3DiTnHZo5G4N7hlEL2FSA3x3KGuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95776fd3ee7f173a37ae1655c32e1fe913e9ffa29821b974e2d481b11c7f2db1","last_reissued_at":"2026-07-05T04:11:16.098791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:16.098791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few Shot Protein Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"q-bio.BM","authors_text":"Soumya Ram, Tristan Bepler","submitted_at":"2022-04-03T22:14:02Z","abstract_excerpt":"We present the MSA-to-protein transformer, a generative model of protein sequences conditioned on protein families represented by multiple sequence alignments (MSAs). Unlike existing approaches to learning generative models of protein families, the MSA-to-protein transformer conditions sequence generation directly on a learned encoding of the multiple sequence alignment, circumventing the need for fitting dedicated family models. By training on a large set of well-curated multiple sequence alignments in Pfam, our MSA-to-protein transformer generalizes well to protein families not observed duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01168","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/2204.01168/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":"2204.01168","created_at":"2026-07-05T04:11:16.098848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.01168v1","created_at":"2026-07-05T04:11:16.098848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01168","created_at":"2026-07-05T04:11:16.098848+00:00"},{"alias_kind":"pith_short_12","alias_value":"SV3W7U7OP4LT","created_at":"2026-07-05T04:11:16.098848+00:00"},{"alias_kind":"pith_short_16","alias_value":"SV3W7U7OP4LTUN5O","created_at":"2026-07-05T04:11:16.098848+00:00"},{"alias_kind":"pith_short_8","alias_value":"SV3W7U7O","created_at":"2026-07-05T04:11:16.098848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22252","citing_title":"LineageFlow: Flow Matching for High-Fidelity Family-Aware Protein Sequence Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E","json":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E.json","graph_json":"https://pith.science/api/pith-number/SV3W7U7OP4LTUN5OCZK4GLQ75E/graph.json","events_json":"https://pith.science/api/pith-number/SV3W7U7OP4LTUN5OCZK4GLQ75E/events.json","paper":"https://pith.science/paper/SV3W7U7O"},"agent_actions":{"view_html":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E","download_json":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E.json","view_paper":"https://pith.science/paper/SV3W7U7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.01168&json=true","fetch_graph":"https://pith.science/api/pith-number/SV3W7U7OP4LTUN5OCZK4GLQ75E/graph.json","fetch_events":"https://pith.science/api/pith-number/SV3W7U7OP4LTUN5OCZK4GLQ75E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E/action/storage_attestation","attest_author":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E/action/author_attestation","sign_citation":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E/action/citation_signature","submit_replication":"https://pith.science/pith/SV3W7U7OP4LTUN5OCZK4GLQ75E/action/replication_record"}},"created_at":"2026-07-05T04:11:16.098848+00:00","updated_at":"2026-07-05T04:11:16.098848+00:00"}