{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GPR5V3L3VRRSR2TQW5OVK4EQBN","short_pith_number":"pith:GPR5V3L3","schema_version":"1.0","canonical_sha256":"33e3daed7bac6328ea70b75d5570900b7558b8ebd72adcc9a912a38206e83041","source":{"kind":"arxiv","id":"2410.15474","version":2},"attestation_state":"computed","paper":{"title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniil Tiapkin, Nikita Morozov, Sergey Samsonov, Timofei Gritsaev","submitted_at":"2024-10-20T19:12:14Z","abstract_excerpt":"Generative Flow Networks (GFlowNets) are a family of generative models that learn to sample objects with probabilities proportional to a given reward function. The key concept behind GFlowNets is the use of two stochastic policies: a forward policy, which incrementally constructs compositional objects, and a backward policy, which sequentially deconstructs them. Recent results show a close relationship between GFlowNet training and entropy-regularized reinforcement learning (RL) problems with a particular reward design. However, this connection applies only in the setting of a fixed backward p"},"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":"2410.15474","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T19:12:14Z","cross_cats_sorted":[],"title_canon_sha256":"f81069b63734179744616979c28ad4f04d87ed05a583970a1fc6271762b529a1","abstract_canon_sha256":"fdbf7787f46c2c8d63e002c28972df5001cd6ca47e61f286d0d34e6956e40ab7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:52.684652Z","signature_b64":"J1+e4SGMby/N6feUp4tWYb9tvqbXJITrkhAeIl8TS3UlCrjvMkQccgmbBLcgXY5HEBs5IoeiFgwyWycAToSbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33e3daed7bac6328ea70b75d5570900b7558b8ebd72adcc9a912a38206e83041","last_reissued_at":"2026-07-05T10:22:52.683924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:52.683924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniil Tiapkin, Nikita Morozov, Sergey Samsonov, Timofei Gritsaev","submitted_at":"2024-10-20T19:12:14Z","abstract_excerpt":"Generative Flow Networks (GFlowNets) are a family of generative models that learn to sample objects with probabilities proportional to a given reward function. The key concept behind GFlowNets is the use of two stochastic policies: a forward policy, which incrementally constructs compositional objects, and a backward policy, which sequentially deconstructs them. Recent results show a close relationship between GFlowNet training and entropy-regularized reinforcement learning (RL) problems with a particular reward design. However, this connection applies only in the setting of a fixed backward p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15474","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/2410.15474/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":"2410.15474","created_at":"2026-07-05T10:22:52.684011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15474v2","created_at":"2026-07-05T10:22:52.684011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15474","created_at":"2026-07-05T10:22:52.684011+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPR5V3L3VRRS","created_at":"2026-07-05T10:22:52.684011+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPR5V3L3VRRSR2TQ","created_at":"2026-07-05T10:22:52.684011+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPR5V3L3","created_at":"2026-07-05T10:22:52.684011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN","json":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN.json","graph_json":"https://pith.science/api/pith-number/GPR5V3L3VRRSR2TQW5OVK4EQBN/graph.json","events_json":"https://pith.science/api/pith-number/GPR5V3L3VRRSR2TQW5OVK4EQBN/events.json","paper":"https://pith.science/paper/GPR5V3L3"},"agent_actions":{"view_html":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN","download_json":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN.json","view_paper":"https://pith.science/paper/GPR5V3L3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15474&json=true","fetch_graph":"https://pith.science/api/pith-number/GPR5V3L3VRRSR2TQW5OVK4EQBN/graph.json","fetch_events":"https://pith.science/api/pith-number/GPR5V3L3VRRSR2TQW5OVK4EQBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/action/storage_attestation","attest_author":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/action/author_attestation","sign_citation":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/action/citation_signature","submit_replication":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/action/replication_record"}},"created_at":"2026-07-05T10:22:52.684011+00:00","updated_at":"2026-07-05T10:22:52.684011+00:00"}