{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OK3LO37AXCVOHF43S6QVV6DWB3","short_pith_number":"pith:OK3LO37A","canonical_record":{"source":{"id":"2209.12782","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T15:44:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ed950fc6ee1da3ad4e2682402f93591d9590ac935281042c9386f038f82ff278","abstract_canon_sha256":"c58ed6f0b3373d2a3a063bad903676fd3068124cb5b20c07d16ae6352e9e4ff1"},"schema_version":"1.0"},"canonical_sha256":"72b6b76fe0b8aae3979b97a15af8760ee06a96c3ed113de1fea71494d99f5128","source":{"kind":"arxiv","id":"2209.12782","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12782","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12782v3","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12782","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"pith_short_12","alias_value":"OK3LO37AXCVO","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"pith_short_16","alias_value":"OK3LO37AXCVOHF43","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"pith_short_8","alias_value":"OK3LO37A","created_at":"2026-07-05T06:17:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OK3LO37AXCVOHF43S6QVV6DWB3","target":"record","payload":{"canonical_record":{"source":{"id":"2209.12782","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T15:44:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ed950fc6ee1da3ad4e2682402f93591d9590ac935281042c9386f038f82ff278","abstract_canon_sha256":"c58ed6f0b3373d2a3a063bad903676fd3068124cb5b20c07d16ae6352e9e4ff1"},"schema_version":"1.0"},"canonical_sha256":"72b6b76fe0b8aae3979b97a15af8760ee06a96c3ed113de1fea71494d99f5128","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:01.698112Z","signature_b64":"Exr9WZBhM4Myn4k4rZT1abvO5AMJ/raakyfH8LU+avj5CKRpbdZnpjrQVEpN+OxzOOMw4SZtD4qOP5Q5csoKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72b6b76fe0b8aae3979b97a15af8760ee06a96c3ed113de1fea71494d99f5128","last_reissued_at":"2026-07-05T06:17:01.697567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:01.697567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.12782","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2pfc5HHvNpaAUUTgO6DMUGkEfdo/4kCATsYqynUxhrAJWZWlcx0j5cEOhSyXGvRu6jmxrvoFtboak6LRCOVyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T03:24:31.439856Z"},"content_sha256":"8fe0111b48e8f8d911bf62bd11f06565d31867e7355e683c746e53525d70ee24","schema_version":"1.0","event_id":"sha256:8fe0111b48e8f8d911bf62bd11f06565d31867e7355e683c746e53525d70ee24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OK3LO37AXCVOHF43S6QVV6DWB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning GFlowNets from partial episodes for improved convergence and stability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrei Nica, Emmanuel Bengio, Jarrid Rector-Brooks, Kanika Madan, Maksym Korablyov, Moksh Jain, Nikolay Malkin, Tom Bosc, Yoshua Bengio","submitted_at":"2022-09-26T15:44:24Z","abstract_excerpt":"Generative flow networks (GFlowNets) are a family of algorithms for training a sequential sampler of discrete objects under an unnormalized target density and have been successfully used for various probabilistic modeling tasks. Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory. We argue that these alternatives represent opposite ends of a gradient bias-variance tradeoff and propose a way to exploit this tradeoff to mitigate its harmful effects. Inspired by the TD($\\lambda$) algorithm in reinfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12782","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/2209.12782/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":"2026-07-05T06:17:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xAXCBFs6lyyicGM5hSWl+AdWcfJ5f4BCUWJYIKFaenKcbBYP0JPAMufCT8lB69D8vU5jEcvTlxLhbfHFCQH2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T03:24:31.440236Z"},"content_sha256":"70915967b336ed518c29cd18c8db856550dda03a53426ede1993544f8b35e099","schema_version":"1.0","event_id":"sha256:70915967b336ed518c29cd18c8db856550dda03a53426ede1993544f8b35e099"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OK3LO37AXCVOHF43S6QVV6DWB3/bundle.json","state_url":"https://pith.science/pith/OK3LO37AXCVOHF43S6QVV6DWB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OK3LO37AXCVOHF43S6QVV6DWB3/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":"2026-07-24T03:24:31Z","links":{"resolver":"https://pith.science/pith/OK3LO37AXCVOHF43S6QVV6DWB3","bundle":"https://pith.science/pith/OK3LO37AXCVOHF43S6QVV6DWB3/bundle.json","state":"https://pith.science/pith/OK3LO37AXCVOHF43S6QVV6DWB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OK3LO37AXCVOHF43S6QVV6DWB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OK3LO37AXCVOHF43S6QVV6DWB3","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":"c58ed6f0b3373d2a3a063bad903676fd3068124cb5b20c07d16ae6352e9e4ff1","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T15:44:24Z","title_canon_sha256":"ed950fc6ee1da3ad4e2682402f93591d9590ac935281042c9386f038f82ff278"},"schema_version":"1.0","source":{"id":"2209.12782","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12782","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12782v3","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12782","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"pith_short_12","alias_value":"OK3LO37AXCVO","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"pith_short_16","alias_value":"OK3LO37AXCVOHF43","created_at":"2026-07-05T06:17:01Z"},{"alias_kind":"pith_short_8","alias_value":"OK3LO37A","created_at":"2026-07-05T06:17:01Z"}],"graph_snapshots":[{"event_id":"sha256:70915967b336ed518c29cd18c8db856550dda03a53426ede1993544f8b35e099","target":"graph","created_at":"2026-07-05T06:17:01Z","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/2209.12782/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 algorithms for training a sequential sampler of discrete objects under an unnormalized target density and have been successfully used for various probabilistic modeling tasks. Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory. We argue that these alternatives represent opposite ends of a gradient bias-variance tradeoff and propose a way to exploit this tradeoff to mitigate its harmful effects. Inspired by the TD($\\lambda$) algorithm in reinfor","authors_text":"Andrei Nica, Emmanuel Bengio, Jarrid Rector-Brooks, Kanika Madan, Maksym Korablyov, Moksh Jain, Nikolay Malkin, Tom Bosc, Yoshua Bengio","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T15:44:24Z","title":"Learning GFlowNets from partial episodes for improved convergence and stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12782","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":"sha256:8fe0111b48e8f8d911bf62bd11f06565d31867e7355e683c746e53525d70ee24","target":"record","created_at":"2026-07-05T06:17:01Z","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":"c58ed6f0b3373d2a3a063bad903676fd3068124cb5b20c07d16ae6352e9e4ff1","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T15:44:24Z","title_canon_sha256":"ed950fc6ee1da3ad4e2682402f93591d9590ac935281042c9386f038f82ff278"},"schema_version":"1.0","source":{"id":"2209.12782","kind":"arxiv","version":3}},"canonical_sha256":"72b6b76fe0b8aae3979b97a15af8760ee06a96c3ed113de1fea71494d99f5128","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72b6b76fe0b8aae3979b97a15af8760ee06a96c3ed113de1fea71494d99f5128","first_computed_at":"2026-07-05T06:17:01.697567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:01.697567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Exr9WZBhM4Myn4k4rZT1abvO5AMJ/raakyfH8LU+avj5CKRpbdZnpjrQVEpN+OxzOOMw4SZtD4qOP5Q5csoKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:01.698112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.12782","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fe0111b48e8f8d911bf62bd11f06565d31867e7355e683c746e53525d70ee24","sha256:70915967b336ed518c29cd18c8db856550dda03a53426ede1993544f8b35e099"],"state_sha256":"689d02fa44f26dba2070eeed74fa9b4e412a5ea6f0eb9a3e4dd210927a1f2445"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3TTtFg9gVBaDBHeGdvk662udkltYLf0j7KSoi6gMFVlpIuGc4ZztMO8o5OurxH8mMTcgnVfRniobvsEmCCQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T03:24:31.442401Z","bundle_sha256":"79fdffbf7bbd52454310e6e9419c426487d929aad6e5463762e5a40211fada30"}}