{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2K6JTU2CUJ6QHHD7OIRJJKCQPY","short_pith_number":"pith:2K6JTU2C","schema_version":"1.0","canonical_sha256":"d2bc99d342a27d039c7f722294a8507e1cbcada76f9adb92b57f0a209a0807e9","source":{"kind":"arxiv","id":"2310.19685","version":3},"attestation_state":"computed","paper":{"title":"DGFN: Double Generative Flow Networks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Elaine Lau, Emmanuel Bengio, Nikhil Vemgal","submitted_at":"2023-10-30T16:04:02Z","abstract_excerpt":"Deep learning is emerging as an effective tool in drug discovery, with potential applications in both predictive and generative models. Generative Flow Networks (GFlowNets/GFNs) are a recently introduced method recognized for the ability to generate diverse candidates, in particular in small molecule generation tasks. In this work, we introduce double GFlowNets (DGFNs). Drawing inspiration from reinforcement learning and Double Deep Q-Learning, we introduce a target network used to sample trajectories, while updating the main network with these sampled trajectories. Empirical results confirm t"},"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":"2310.19685","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T16:04:02Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"9082bb59ffa67ca6d22a2b5dd4a9457b8e7b9f0810857518bf5cf862082817ac","abstract_canon_sha256":"a8205bfb3e255c6e3fb4939736ba3181cf493b81b4d32ff88d10090297a462f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:55.696496Z","signature_b64":"RHI3CppVLboOMHVZ5yVe6YXEa/PRR1QHNkeCFIwayVyfzC6IwUzU81UC7zT0AWgzn/tnXni9qZDKiiNaxyQGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2bc99d342a27d039c7f722294a8507e1cbcada76f9adb92b57f0a209a0807e9","last_reissued_at":"2026-07-05T07:09:55.695962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:55.695962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DGFN: Double Generative Flow Networks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Elaine Lau, Emmanuel Bengio, Nikhil Vemgal","submitted_at":"2023-10-30T16:04:02Z","abstract_excerpt":"Deep learning is emerging as an effective tool in drug discovery, with potential applications in both predictive and generative models. Generative Flow Networks (GFlowNets/GFNs) are a recently introduced method recognized for the ability to generate diverse candidates, in particular in small molecule generation tasks. In this work, we introduce double GFlowNets (DGFNs). Drawing inspiration from reinforcement learning and Double Deep Q-Learning, we introduce a target network used to sample trajectories, while updating the main network with these sampled trajectories. Empirical results confirm t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19685","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/2310.19685/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":"2310.19685","created_at":"2026-07-05T07:09:55.696028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19685v3","created_at":"2026-07-05T07:09:55.696028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19685","created_at":"2026-07-05T07:09:55.696028+00:00"},{"alias_kind":"pith_short_12","alias_value":"2K6JTU2CUJ6Q","created_at":"2026-07-05T07:09:55.696028+00:00"},{"alias_kind":"pith_short_16","alias_value":"2K6JTU2CUJ6QHHD7","created_at":"2026-07-05T07:09:55.696028+00:00"},{"alias_kind":"pith_short_8","alias_value":"2K6JTU2C","created_at":"2026-07-05T07:09:55.696028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14096","citing_title":"Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems","ref_index":112,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY","json":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY.json","graph_json":"https://pith.science/api/pith-number/2K6JTU2CUJ6QHHD7OIRJJKCQPY/graph.json","events_json":"https://pith.science/api/pith-number/2K6JTU2CUJ6QHHD7OIRJJKCQPY/events.json","paper":"https://pith.science/paper/2K6JTU2C"},"agent_actions":{"view_html":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY","download_json":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY.json","view_paper":"https://pith.science/paper/2K6JTU2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19685&json=true","fetch_graph":"https://pith.science/api/pith-number/2K6JTU2CUJ6QHHD7OIRJJKCQPY/graph.json","fetch_events":"https://pith.science/api/pith-number/2K6JTU2CUJ6QHHD7OIRJJKCQPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY/action/storage_attestation","attest_author":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY/action/author_attestation","sign_citation":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY/action/citation_signature","submit_replication":"https://pith.science/pith/2K6JTU2CUJ6QHHD7OIRJJKCQPY/action/replication_record"}},"created_at":"2026-07-05T07:09:55.696028+00:00","updated_at":"2026-07-05T07:09:55.696028+00:00"}