{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EOEB3KQRUT473FPCCJU7W6URKE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4eee16b79420fd954088e44cd85fcb0b4341067a38806144ed1769d8ce7874ec","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T20:14:22Z","title_canon_sha256":"99933b50212ed447d4074c88ff7060d1f4fa9bedf8a10513d9b4a18d6e6cd7cb"},"schema_version":"1.0","source":{"id":"2402.05234","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05234","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05234v3","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05234","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"EOEB3KQRUT47","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"EOEB3KQRUT473FPC","created_at":"2026-07-05T09:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"EOEB3KQR","created_at":"2026-07-05T09:29:26Z"}],"graph_snapshots":[{"event_id":"sha256:160871046057542facc9d3d4d3839193195d9b3c71fc8bb81a36d2acbb4fb3d7","target":"graph","created_at":"2026-07-05T09:29:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.05234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Flow Networks (GFlowNets; GFNs) are a family of energy-based generative methods for combinatorial objects, capable of generating diverse and high-utility samples. However, consistently biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate, $Q$, to create greedier sampling policies which can be controlled by a mixing parameter. We show that several variants of the proposed method, QGFN, are able to improve on the number o","authors_text":"Doina Precup, Elaine Lau, Emmanuel Bengio, Ling Pan, Stephen Zhewen Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T20:14:22Z","title":"QGFN: Controllable Greediness with Action Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05234","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:310b2b3aebbe6a05e313560ab500fedf0dfbeb49d29e3e1b987ea9a1a3e6943a","target":"record","created_at":"2026-07-05T09:29:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4eee16b79420fd954088e44cd85fcb0b4341067a38806144ed1769d8ce7874ec","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T20:14:22Z","title_canon_sha256":"99933b50212ed447d4074c88ff7060d1f4fa9bedf8a10513d9b4a18d6e6cd7cb"},"schema_version":"1.0","source":{"id":"2402.05234","kind":"arxiv","version":3}},"canonical_sha256":"23881daa11a4f9fd95e21269fb7a9151253014f1a4f4ab75b9517cb671cfd81b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23881daa11a4f9fd95e21269fb7a9151253014f1a4f4ab75b9517cb671cfd81b","first_computed_at":"2026-07-05T09:29:26.080127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:26.080127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nGEVoOQ1j1jCUeVjtDW3hXUGswExn5kzPbsgE2vfiZLWu3k516levo5gUw46At0QMXSv+gKVGKf/Se53evcBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:26.080632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05234","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:310b2b3aebbe6a05e313560ab500fedf0dfbeb49d29e3e1b987ea9a1a3e6943a","sha256:160871046057542facc9d3d4d3839193195d9b3c71fc8bb81a36d2acbb4fb3d7"],"state_sha256":"afb35aab8d699a414ac7082d929424e663e3ecfa0a06c639705e8df543dc8b21"}