{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NSB633UZR7EFWTIEPJGF2QHZJK","short_pith_number":"pith:NSB633UZ","canonical_record":{"source":{"id":"2307.01422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T01:28:02Z","cross_cats_sorted":[],"title_canon_sha256":"98bae421104c75eabd6bf28b4f596a0ca4bfe807a4af054d62d1a9911b5c9702","abstract_canon_sha256":"b65b582d9b477d4768d8ae3b413bf301e32d3c01ae1bad5dfa7612fa78459935"},"schema_version":"1.0"},"canonical_sha256":"6c83edee998fc85b4d047a4c5d40f94a97bc411becdbd363f05dd7fea6b24315","source":{"kind":"arxiv","id":"2307.01422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01422","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01422v1","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01422","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"NSB633UZR7EF","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"NSB633UZR7EFWTIE","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"NSB633UZ","created_at":"2026-07-05T06:27:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NSB633UZR7EFWTIEPJGF2QHZJK","target":"record","payload":{"canonical_record":{"source":{"id":"2307.01422","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T01:28:02Z","cross_cats_sorted":[],"title_canon_sha256":"98bae421104c75eabd6bf28b4f596a0ca4bfe807a4af054d62d1a9911b5c9702","abstract_canon_sha256":"b65b582d9b477d4768d8ae3b413bf301e32d3c01ae1bad5dfa7612fa78459935"},"schema_version":"1.0"},"canonical_sha256":"6c83edee998fc85b4d047a4c5d40f94a97bc411becdbd363f05dd7fea6b24315","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:56.303653Z","signature_b64":"VJ4Up4hPpYIdACAGlstUTmPhUE2FG5btjG7jVxyiscv8L+tO4rjaPRd7T+IDB3J925bjUmcKCdv718T4av+OCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c83edee998fc85b4d047a4c5d40f94a97bc411becdbd363f05dd7fea6b24315","last_reissued_at":"2026-07-05T06:27:56.303200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:56.303200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.01422","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"It7+i3lkYYJl2NewObnngjBH4uJdXUtkKgTLTS+cBOR44PnCo7SXeXob8OLLwRZBXDZ/vs700RkAh5HG3IGxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:30:02.647712Z"},"content_sha256":"a43541dea8d83c0ce9003531ff9b02ba0be203b6ce47a45450d7ad66a35391a9","schema_version":"1.0","event_id":"sha256:a43541dea8d83c0ce9003531ff9b02ba0be203b6ce47a45450d7ad66a35391a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NSB633UZR7EFWTIEPJGF2QHZJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Flow Networks: a Markov Chain Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tristan Deleu, Yoshua Bengio","submitted_at":"2023-07-04T01:28:02Z","abstract_excerpt":"While Markov chain Monte Carlo methods (MCMC) provide a general framework to sample from a probability distribution defined up to normalization, they often suffer from slow convergence to the target distribution when the latter is highly multi-modal. Recently, Generative Flow Networks (GFlowNets) have been proposed as an alternative framework to mitigate this issue when samples have a clear compositional structure, by treating sampling as a sequential decision making problem. Although they were initially introduced from the perspective of flow networks, the recent advances of GFlowNets draw mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01422","kind":"arxiv","version":1},"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/2307.01422/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":"2026-07-05T06:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZb4XjJGOcfuVwzTVHAyswQ/fwmX5l9QV26jGuAlPVJ6TKiZfRffei3NL0ha2lrbL920HVSnRU1OrBU/c8U9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:30:02.648327Z"},"content_sha256":"0ec8c4a5842af086c51b7eca19d482dcb493b556e7f4460c9bb43a9fd16ae602","schema_version":"1.0","event_id":"sha256:0ec8c4a5842af086c51b7eca19d482dcb493b556e7f4460c9bb43a9fd16ae602"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NSB633UZR7EFWTIEPJGF2QHZJK/bundle.json","state_url":"https://pith.science/pith/NSB633UZR7EFWTIEPJGF2QHZJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NSB633UZR7EFWTIEPJGF2QHZJK/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":"2026-08-04T14:30:02Z","links":{"resolver":"https://pith.science/pith/NSB633UZR7EFWTIEPJGF2QHZJK","bundle":"https://pith.science/pith/NSB633UZR7EFWTIEPJGF2QHZJK/bundle.json","state":"https://pith.science/pith/NSB633UZR7EFWTIEPJGF2QHZJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NSB633UZR7EFWTIEPJGF2QHZJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NSB633UZR7EFWTIEPJGF2QHZJK","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":"b65b582d9b477d4768d8ae3b413bf301e32d3c01ae1bad5dfa7612fa78459935","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T01:28:02Z","title_canon_sha256":"98bae421104c75eabd6bf28b4f596a0ca4bfe807a4af054d62d1a9911b5c9702"},"schema_version":"1.0","source":{"id":"2307.01422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01422","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01422v1","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01422","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"NSB633UZR7EF","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"NSB633UZR7EFWTIE","created_at":"2026-07-05T06:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"NSB633UZ","created_at":"2026-07-05T06:27:56Z"}],"graph_snapshots":[{"event_id":"sha256:0ec8c4a5842af086c51b7eca19d482dcb493b556e7f4460c9bb43a9fd16ae602","target":"graph","created_at":"2026-07-05T06:27:56Z","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/2307.01422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Markov chain Monte Carlo methods (MCMC) provide a general framework to sample from a probability distribution defined up to normalization, they often suffer from slow convergence to the target distribution when the latter is highly multi-modal. Recently, Generative Flow Networks (GFlowNets) have been proposed as an alternative framework to mitigate this issue when samples have a clear compositional structure, by treating sampling as a sequential decision making problem. Although they were initially introduced from the perspective of flow networks, the recent advances of GFlowNets draw mo","authors_text":"Tristan Deleu, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T01:28:02Z","title":"Generative Flow Networks: a Markov Chain Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01422","kind":"arxiv","version":1},"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:a43541dea8d83c0ce9003531ff9b02ba0be203b6ce47a45450d7ad66a35391a9","target":"record","created_at":"2026-07-05T06:27:56Z","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":"b65b582d9b477d4768d8ae3b413bf301e32d3c01ae1bad5dfa7612fa78459935","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T01:28:02Z","title_canon_sha256":"98bae421104c75eabd6bf28b4f596a0ca4bfe807a4af054d62d1a9911b5c9702"},"schema_version":"1.0","source":{"id":"2307.01422","kind":"arxiv","version":1}},"canonical_sha256":"6c83edee998fc85b4d047a4c5d40f94a97bc411becdbd363f05dd7fea6b24315","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c83edee998fc85b4d047a4c5d40f94a97bc411becdbd363f05dd7fea6b24315","first_computed_at":"2026-07-05T06:27:56.303200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:56.303200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VJ4Up4hPpYIdACAGlstUTmPhUE2FG5btjG7jVxyiscv8L+tO4rjaPRd7T+IDB3J925bjUmcKCdv718T4av+OCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:56.303653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a43541dea8d83c0ce9003531ff9b02ba0be203b6ce47a45450d7ad66a35391a9","sha256:0ec8c4a5842af086c51b7eca19d482dcb493b556e7f4460c9bb43a9fd16ae602"],"state_sha256":"9b4f44033b94e6420629e4e2232d27213ea647f4edd41d798743c03115ce486f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3I54cJbyPzbZfpQ9xr9UGTSnS7NXXcSKNZGwvWitSnd6VWEv/5mQhrYZWyiHxP89tA7tKAfdavMef9Eg61R8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:30:02.670629Z","bundle_sha256":"5ffb15e4e9ab11d3c9e8aaf11d3b779422a74dfb14f1b31fc32901b7795c4340"}}