{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZSFPVYQDOBFBOWXCRWE7KXSSAQ","short_pith_number":"pith:ZSFPVYQD","schema_version":"1.0","canonical_sha256":"cc8afae203704a175ae28d89f55e520434f9b0ae5e01d33088328e3d9b9e810a","source":{"kind":"arxiv","id":"2310.02779","version":2},"attestation_state":"computed","paper":{"title":"Expected flow networks in stochastic environments and two-player zero-sum games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Bilun Sun, Danilo Vucetic, Gauthier Gidel, Marco Jiralerspong, Nikolay Malkin, Tianyu Zhang, Yoshua Bengio","submitted_at":"2023-10-04T12:50:29Z","abstract_excerpt":"Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution. GFlowNets have been successfully applied to various structured object generation tasks, sampling a diverse set of high-reward objects quickly. We propose expected flow networks (EFlowNets), which extend GFlowNets to stochastic environments. We show that EFlowNets outperform other GFlowNet formulations in stochastic tasks such as protein design. We then extend the concept of EFlowNets to adversarial environments, proposing adversarial flow networks (AFlowNets) for two-player zero-sum games"},"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":"2310.02779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T12:50:29Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"f6e71e00d68fb1268c0a97f3b5eeb9ec4398ce98665d0ba84bac9a7abf3146fa","abstract_canon_sha256":"9eda3f48441dcafe96d9f46067a227bb41e1427cd71558312d400d92fac7ba36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:45.247559Z","signature_b64":"WJo2nZj8IITEwOaV0TYspPzCslCQdDBlOWlCzi1bE4hOJN0EKe5WlLP9ip7FChI8pjvC44NesxPOWWyuK3Y9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc8afae203704a175ae28d89f55e520434f9b0ae5e01d33088328e3d9b9e810a","last_reissued_at":"2026-07-05T07:55:45.247121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:45.247121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expected flow networks in stochastic environments and two-player zero-sum games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Bilun Sun, Danilo Vucetic, Gauthier Gidel, Marco Jiralerspong, Nikolay Malkin, Tianyu Zhang, Yoshua Bengio","submitted_at":"2023-10-04T12:50:29Z","abstract_excerpt":"Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution. GFlowNets have been successfully applied to various structured object generation tasks, sampling a diverse set of high-reward objects quickly. We propose expected flow networks (EFlowNets), which extend GFlowNets to stochastic environments. We show that EFlowNets outperform other GFlowNet formulations in stochastic tasks such as protein design. We then extend the concept of EFlowNets to adversarial environments, proposing adversarial flow networks (AFlowNets) for two-player zero-sum games"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02779","kind":"arxiv","version":2},"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/2310.02779/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":"2310.02779","created_at":"2026-07-05T07:55:45.247184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02779v2","created_at":"2026-07-05T07:55:45.247184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02779","created_at":"2026-07-05T07:55:45.247184+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSFPVYQDOBFB","created_at":"2026-07-05T07:55:45.247184+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSFPVYQDOBFBOWXC","created_at":"2026-07-05T07:55:45.247184+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSFPVYQD","created_at":"2026-07-05T07:55:45.247184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05422","citing_title":"IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ","json":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ.json","graph_json":"https://pith.science/api/pith-number/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/graph.json","events_json":"https://pith.science/api/pith-number/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/events.json","paper":"https://pith.science/paper/ZSFPVYQD"},"agent_actions":{"view_html":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ","download_json":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ.json","view_paper":"https://pith.science/paper/ZSFPVYQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02779&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZSFPVYQDOBFBOWXCRWE7KXSSAQ/action/replication_record"}},"created_at":"2026-07-05T07:55:45.247184+00:00","updated_at":"2026-07-05T07:55:45.247184+00:00"}