{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MSVJXQD54RBYW4KZU25F6QMJIU","short_pith_number":"pith:MSVJXQD5","canonical_record":{"source":{"id":"2402.05309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T23:02:53Z","cross_cats_sorted":[],"title_canon_sha256":"fed12259dd60ce2b784384af83ef54a2fac88ff0751d4d9b2acf88eec722cc1b","abstract_canon_sha256":"a6f11082cb3f316ba4e72287cfcfc5fc6588aff2518c7e1dd68f4e18f0961664"},"schema_version":"1.0"},"canonical_sha256":"64aa9bc07de4438b7159a6ba5f4189450225541847666a8ad7825db21f71ea54","source":{"kind":"arxiv","id":"2402.05309","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05309","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05309v2","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05309","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"MSVJXQD54RBY","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"MSVJXQD54RBYW4KZ","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"MSVJXQD5","created_at":"2026-07-05T10:49:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MSVJXQD54RBYW4KZU25F6QMJIU","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T23:02:53Z","cross_cats_sorted":[],"title_canon_sha256":"fed12259dd60ce2b784384af83ef54a2fac88ff0751d4d9b2acf88eec722cc1b","abstract_canon_sha256":"a6f11082cb3f316ba4e72287cfcfc5fc6588aff2518c7e1dd68f4e18f0961664"},"schema_version":"1.0"},"canonical_sha256":"64aa9bc07de4438b7159a6ba5f4189450225541847666a8ad7825db21f71ea54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:43.167779Z","signature_b64":"q0eQ7zgIICR0UpR/FFIh0yrZevkIRCk8VvQSMeu/F1F0vftAQnyoT8R0u+ClDng7CHP+8rDOtgqfO6RRzrRAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64aa9bc07de4438b7159a6ba5f4189450225541847666a8ad7825db21f71ea54","last_reissued_at":"2026-07-05T10:49:43.167396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:43.167396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05309","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":"2026-07-05T10:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"di3XFGOvev80GNIxSupt+QZc5h25BtSb63mlOb/+9WBX8JBy69UvcyGQ4CESnbtFiBSf3D6c7HFMEGsTq5o1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:26:35.241119Z"},"content_sha256":"e1690230706ea4f5cf77237a9004550d85ddce7c321300d8d4a844d4e0e7d002","schema_version":"1.0","event_id":"sha256:e1690230706ea4f5cf77237a9004550d85ddce7c321300d8d4a844d4e0e7d002"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MSVJXQD54RBYW4KZU25F6QMJIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Generalization Behaviours of Generative Flow Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emmanuel Bengio, Lazar Atanackovic","submitted_at":"2024-02-07T23:02:53Z","abstract_excerpt":"Generative Flow Networks (GFlowNets, GFNs) are a generative framework for learning unnormalized probability mass functions over discrete spaces. Since their inception, GFlowNets have proven to be useful for learning generative models in applications where the majority of the discrete space is unvisited during training. This has inspired some to hypothesize that GFlowNets, when paired with deep neural networks (DNNs), have favorable generalization properties. In this work, we empirically verify some of the hypothesized mechanisms of generalization of GFlowNets. We accomplish this by introducing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05309","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/2402.05309/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":"2026-07-05T10:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgcTPKdXIzdNgA4idSdaSacsSsl3eH5Aw5wCzGKIA092D1BfGYNPA1Zv0+5q+tVP52ohCLvKvPYYruVL7CgNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:26:35.241739Z"},"content_sha256":"c809de01db100783e11ce11088a4b06b04793b60e9a1713b4fb8c570a9985f07","schema_version":"1.0","event_id":"sha256:c809de01db100783e11ce11088a4b06b04793b60e9a1713b4fb8c570a9985f07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSVJXQD54RBYW4KZU25F6QMJIU/bundle.json","state_url":"https://pith.science/pith/MSVJXQD54RBYW4KZU25F6QMJIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSVJXQD54RBYW4KZU25F6QMJIU/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":"2026-08-08T20:26:35Z","links":{"resolver":"https://pith.science/pith/MSVJXQD54RBYW4KZU25F6QMJIU","bundle":"https://pith.science/pith/MSVJXQD54RBYW4KZU25F6QMJIU/bundle.json","state":"https://pith.science/pith/MSVJXQD54RBYW4KZU25F6QMJIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSVJXQD54RBYW4KZU25F6QMJIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MSVJXQD54RBYW4KZU25F6QMJIU","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":"a6f11082cb3f316ba4e72287cfcfc5fc6588aff2518c7e1dd68f4e18f0961664","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T23:02:53Z","title_canon_sha256":"fed12259dd60ce2b784384af83ef54a2fac88ff0751d4d9b2acf88eec722cc1b"},"schema_version":"1.0","source":{"id":"2402.05309","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05309","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05309v2","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05309","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"MSVJXQD54RBY","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"MSVJXQD54RBYW4KZ","created_at":"2026-07-05T10:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"MSVJXQD5","created_at":"2026-07-05T10:49:43Z"}],"graph_snapshots":[{"event_id":"sha256:c809de01db100783e11ce11088a4b06b04793b60e9a1713b4fb8c570a9985f07","target":"graph","created_at":"2026-07-05T10:49:43Z","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/2402.05309/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 generative framework for learning unnormalized probability mass functions over discrete spaces. Since their inception, GFlowNets have proven to be useful for learning generative models in applications where the majority of the discrete space is unvisited during training. This has inspired some to hypothesize that GFlowNets, when paired with deep neural networks (DNNs), have favorable generalization properties. In this work, we empirically verify some of the hypothesized mechanisms of generalization of GFlowNets. We accomplish this by introducing","authors_text":"Emmanuel Bengio, Lazar Atanackovic","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T23:02:53Z","title":"Investigating Generalization Behaviours of Generative Flow Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05309","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:e1690230706ea4f5cf77237a9004550d85ddce7c321300d8d4a844d4e0e7d002","target":"record","created_at":"2026-07-05T10:49:43Z","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":"a6f11082cb3f316ba4e72287cfcfc5fc6588aff2518c7e1dd68f4e18f0961664","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T23:02:53Z","title_canon_sha256":"fed12259dd60ce2b784384af83ef54a2fac88ff0751d4d9b2acf88eec722cc1b"},"schema_version":"1.0","source":{"id":"2402.05309","kind":"arxiv","version":2}},"canonical_sha256":"64aa9bc07de4438b7159a6ba5f4189450225541847666a8ad7825db21f71ea54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64aa9bc07de4438b7159a6ba5f4189450225541847666a8ad7825db21f71ea54","first_computed_at":"2026-07-05T10:49:43.167396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:43.167396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q0eQ7zgIICR0UpR/FFIh0yrZevkIRCk8VvQSMeu/F1F0vftAQnyoT8R0u+ClDng7CHP+8rDOtgqfO6RRzrRAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:43.167779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05309","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1690230706ea4f5cf77237a9004550d85ddce7c321300d8d4a844d4e0e7d002","sha256:c809de01db100783e11ce11088a4b06b04793b60e9a1713b4fb8c570a9985f07"],"state_sha256":"52f06beddb5f97c0d109a9ceef601687928694dabb966b81f3296ecaa396a141"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0tdx7WU6tbqKpE6fEbOsU08cjp+Um6mBXL5bLgFAoNh5HPl6LqzOdOq71FdjAsqA9ejY6hljLzeTStCqzi0AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:26:35.247891Z","bundle_sha256":"55f7640753b3fb4fc78a35640535f5c1f80eec8ba6ee005e3a125894c0d1cfd3"}}