{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GPR5V3L3VRRSR2TQW5OVK4EQBN","short_pith_number":"pith:GPR5V3L3","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"},"canonical_sha256":"33e3daed7bac6328ea70b75d5570900b7558b8ebd72adcc9a912a38206e83041","source":{"kind":"arxiv","id":"2410.15474","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15474","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15474v2","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15474","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"GPR5V3L3VRRS","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"GPR5V3L3VRRSR2TQ","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"GPR5V3L3","created_at":"2026-07-05T10:22:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GPR5V3L3VRRSR2TQW5OVK4EQBN","target":"record","payload":{"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"},"canonical_sha256":"33e3daed7bac6328ea70b75d5570900b7558b8ebd72adcc9a912a38206e83041","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"},"source_kind":"arxiv","source_id":"2410.15474","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EHb22CN6BnXAXmT02Z5q7HCxpjChn9DX712GVf+IHk+9aAJgvHLKujCdZgUuok3dKDI45RIPULbbdGGavulJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:21:16.525719Z"},"content_sha256":"3681c1107a4cc5e2ab6c7b5550b69250b840a4ec63995adfc7ba1fd019bd589e","schema_version":"1.0","event_id":"sha256:3681c1107a4cc5e2ab6c7b5550b69250b840a4ec63995adfc7ba1fd019bd589e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GPR5V3L3VRRSR2TQW5OVK4EQBN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2zl7imGHXXaPuph+jazApU2c7QOUKkJypIC65dKeXjCpksyuNHzIjOAwQUFELeYVeeEGPmDlI8M51LWSD+8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:21:16.526265Z"},"content_sha256":"2816c57cb2e906b32cf34e16fd6149fc172c28ea531cd1eb3dd6c6c29d1cdf2f","schema_version":"1.0","event_id":"sha256:2816c57cb2e906b32cf34e16fd6149fc172c28ea531cd1eb3dd6c6c29d1cdf2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/bundle.json","state_url":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T06:21:16Z","links":{"resolver":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN","bundle":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/bundle.json","state":"https://pith.science/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GPR5V3L3VRRSR2TQW5OVK4EQBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GPR5V3L3VRRSR2TQW5OVK4EQBN","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":"fdbf7787f46c2c8d63e002c28972df5001cd6ca47e61f286d0d34e6956e40ab7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T19:12:14Z","title_canon_sha256":"f81069b63734179744616979c28ad4f04d87ed05a583970a1fc6271762b529a1"},"schema_version":"1.0","source":{"id":"2410.15474","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15474","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15474v2","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15474","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"GPR5V3L3VRRS","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"GPR5V3L3VRRSR2TQ","created_at":"2026-07-05T10:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"GPR5V3L3","created_at":"2026-07-05T10:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:2816c57cb2e906b32cf34e16fd6149fc172c28ea531cd1eb3dd6c6c29d1cdf2f","target":"graph","created_at":"2026-07-05T10:22:52Z","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/2410.15474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daniil Tiapkin, Nikita Morozov, Sergey Samsonov, Timofei Gritsaev","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T19:12:14Z","title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15474","kind":"arxiv","version":2},"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":"sha256:3681c1107a4cc5e2ab6c7b5550b69250b840a4ec63995adfc7ba1fd019bd589e","target":"record","created_at":"2026-07-05T10:22:52Z","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":"fdbf7787f46c2c8d63e002c28972df5001cd6ca47e61f286d0d34e6956e40ab7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T19:12:14Z","title_canon_sha256":"f81069b63734179744616979c28ad4f04d87ed05a583970a1fc6271762b529a1"},"schema_version":"1.0","source":{"id":"2410.15474","kind":"arxiv","version":2}},"canonical_sha256":"33e3daed7bac6328ea70b75d5570900b7558b8ebd72adcc9a912a38206e83041","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33e3daed7bac6328ea70b75d5570900b7558b8ebd72adcc9a912a38206e83041","first_computed_at":"2026-07-05T10:22:52.683924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:52.683924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J1+e4SGMby/N6feUp4tWYb9tvqbXJITrkhAeIl8TS3UlCrjvMkQccgmbBLcgXY5HEBs5IoeiFgwyWycAToSbCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:52.684652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15474","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3681c1107a4cc5e2ab6c7b5550b69250b840a4ec63995adfc7ba1fd019bd589e","sha256:2816c57cb2e906b32cf34e16fd6149fc172c28ea531cd1eb3dd6c6c29d1cdf2f"],"state_sha256":"12742f0d14b09d656a175e52ddbf50d700eb7edb3fe8428740516d7c784c6ea2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NlHKXh8xBLs314lrWgfuL2g5xcZlrybQhFe6KsATAQQ/7VpKV0m0U45/KKWT4nb0J+t3lDbzCzat1A/e/5uWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T06:21:16.530178Z","bundle_sha256":"999d57e3b5004c56f7a9f2a851b88d8a4b564b59be3cffb630870f7af8c5a52f"}}