{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q64DTL4KJ6IWXOSVBMQCXPHFLZ","short_pith_number":"pith:Q64DTL4K","schema_version":"1.0","canonical_sha256":"87b839af8a4f916bba550b202bbce55e4f5e7eb75a1a24a46fe2859a22e1c722","source":{"kind":"arxiv","id":"2203.04115","version":3},"attestation_state":"computed","paper":{"title":"Biological Sequence Design with GFlowNets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Alex-Hernandez Garcia, Bonaventure F. P. Dossou, Chanakya Ekbote, Dinghuai Zhang, Emmanuel Bengio, Jarrid Rector-Brooks, Jie Fu, Lena Simine, Micheal Kilgour, Moksh Jain, Payel Das, Tianyu Zhang, Yoshua Bengio","submitted_at":"2022-03-02T15:53:38Z","abstract_excerpt":"Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages, with increasing levels of precision and cost of evaluation, where candidates are filtered. This makes the diversity of proposed candidates a key consideration in the ideation phase. In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candid"},"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":"2203.04115","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-03-02T15:53:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"929f6a35c074e7e8ce41839e4f14eb2a9fb44ee7ef1c5c908308b8eb0fcd051e","abstract_canon_sha256":"ff18af3c436b519e0694184800fc4f8eb6b6c993ed81fd21ecfb5961419f1d47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:14.792895Z","signature_b64":"IClG2a3Jmfn9S2v31in9qCk8uGxLehG1a5auESjSu49gvgN8U/urT4n/RrYFQvkc6ZGCgmAVI5bikDRHp7yoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87b839af8a4f916bba550b202bbce55e4f5e7eb75a1a24a46fe2859a22e1c722","last_reissued_at":"2026-07-05T06:13:14.792516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:14.792516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Biological Sequence Design with GFlowNets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Alex-Hernandez Garcia, Bonaventure F. P. Dossou, Chanakya Ekbote, Dinghuai Zhang, Emmanuel Bengio, Jarrid Rector-Brooks, Jie Fu, Lena Simine, Micheal Kilgour, Moksh Jain, Payel Das, Tianyu Zhang, Yoshua Bengio","submitted_at":"2022-03-02T15:53:38Z","abstract_excerpt":"Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages, with increasing levels of precision and cost of evaluation, where candidates are filtered. This makes the diversity of proposed candidates a key consideration in the ideation phase. In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04115","kind":"arxiv","version":3},"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/2203.04115/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":"2203.04115","created_at":"2026-07-05T06:13:14.792579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.04115v3","created_at":"2026-07-05T06:13:14.792579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04115","created_at":"2026-07-05T06:13:14.792579+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q64DTL4KJ6IW","created_at":"2026-07-05T06:13:14.792579+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q64DTL4KJ6IWXOSV","created_at":"2026-07-05T06:13:14.792579+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q64DTL4K","created_at":"2026-07-05T06:13:14.792579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20964","citing_title":"Semantic Communication meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ","json":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ.json","graph_json":"https://pith.science/api/pith-number/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/graph.json","events_json":"https://pith.science/api/pith-number/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/events.json","paper":"https://pith.science/paper/Q64DTL4K"},"agent_actions":{"view_html":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ","download_json":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ.json","view_paper":"https://pith.science/paper/Q64DTL4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.04115&json=true","fetch_graph":"https://pith.science/api/pith-number/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/action/storage_attestation","attest_author":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/action/author_attestation","sign_citation":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/action/citation_signature","submit_replication":"https://pith.science/pith/Q64DTL4KJ6IWXOSVBMQCXPHFLZ/action/replication_record"}},"created_at":"2026-07-05T06:13:14.792579+00:00","updated_at":"2026-07-05T06:13:14.792579+00:00"}