{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JPNTXXL5VHWCLIQELESCRA3IHI","short_pith_number":"pith:JPNTXXL5","canonical_record":{"source":{"id":"2306.17693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T14:19:44Z","cross_cats_sorted":[],"title_canon_sha256":"c20ba2cd4ae9a66aea4b1d462d9b045a88cdcfff5d8e0ba38154fcc380a239e5","abstract_canon_sha256":"6da5271dea079560ff43593763ffecd8c2e43b39ed5f4df3a8a289c5e15b7789"},"schema_version":"1.0"},"canonical_sha256":"4bdb3bdd7da9ec25a20459242883683a2c2583980b5489a2fdb8fbc67bfff356","source":{"kind":"arxiv","id":"2306.17693","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17693","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17693v1","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17693","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"pith_short_12","alias_value":"JPNTXXL5VHWC","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"pith_short_16","alias_value":"JPNTXXL5VHWCLIQE","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"pith_short_8","alias_value":"JPNTXXL5","created_at":"2026-07-05T06:26:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JPNTXXL5VHWCLIQELESCRA3IHI","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T14:19:44Z","cross_cats_sorted":[],"title_canon_sha256":"c20ba2cd4ae9a66aea4b1d462d9b045a88cdcfff5d8e0ba38154fcc380a239e5","abstract_canon_sha256":"6da5271dea079560ff43593763ffecd8c2e43b39ed5f4df3a8a289c5e15b7789"},"schema_version":"1.0"},"canonical_sha256":"4bdb3bdd7da9ec25a20459242883683a2c2583980b5489a2fdb8fbc67bfff356","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:30.644586Z","signature_b64":"iAb2P1wIV1QJlFd5mq2n6eDKNdK15WSW1QR0PQEqYltkNaBzB/GlRzPe/foJyEGfViSdppsXW6ZvogOxiWWiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bdb3bdd7da9ec25a20459242883683a2c2583980b5489a2fdb8fbc67bfff356","last_reissued_at":"2026-07-05T06:26:30.644015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:30.644015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17693","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":"2026-07-05T06:26:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i60VlSf4Y/ELNvK3r3QD0LgE63qI6XMFR7V9P3qehBLaiPUbzdVZKP6ewSyhxE3HqBnbsYzxnuWfTgI+r6GyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:56:01.366376Z"},"content_sha256":"2274ad108d874c78619ced219fe80f3d26f5599b90451f1ec29feadcf816e678","schema_version":"1.0","event_id":"sha256:2274ad108d874c78619ced219fe80f3d26f5599b90451f1ec29feadcf816e678"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JPNTXXL5VHWCLIQELESCRA3IHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thompson sampling for improved exploration in GFlowNets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng-Hao Liu, Jarrid Rector-Brooks, Kanika Madan, Maksym Korablyov, Moksh Jain, Nikolay Malkin, Sarath Chandar, Yoshua Bengio","submitted_at":"2023-06-30T14:19:44Z","abstract_excerpt":"Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy. Unlike other algorithms for hierarchical sampling that optimize a variational bound, GFlowNet algorithms can stably run off-policy, which can be advantageous for discovering modes of the target distribution. Despite this flexibility in the choice of behaviour policy, the optimal way of efficiently selecting trajectories for training has not yet been systematically explored. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17693","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/2306.17693/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":"2026-07-05T06:26:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/68pLP72hbpWccQGxXV2cbcQc+lLYAIdj7QInyDfp+CTrCmGZ9UhmSijzkGQl7c95vqrkPFMQR/3dXI2HhzdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:56:01.367394Z"},"content_sha256":"d48352a4fa771f883f85aebcb6a84cb3522a6ccd149ad486a2061d280aa05471","schema_version":"1.0","event_id":"sha256:d48352a4fa771f883f85aebcb6a84cb3522a6ccd149ad486a2061d280aa05471"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPNTXXL5VHWCLIQELESCRA3IHI/bundle.json","state_url":"https://pith.science/pith/JPNTXXL5VHWCLIQELESCRA3IHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPNTXXL5VHWCLIQELESCRA3IHI/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":"2026-08-17T20:56:01Z","links":{"resolver":"https://pith.science/pith/JPNTXXL5VHWCLIQELESCRA3IHI","bundle":"https://pith.science/pith/JPNTXXL5VHWCLIQELESCRA3IHI/bundle.json","state":"https://pith.science/pith/JPNTXXL5VHWCLIQELESCRA3IHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPNTXXL5VHWCLIQELESCRA3IHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JPNTXXL5VHWCLIQELESCRA3IHI","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":"6da5271dea079560ff43593763ffecd8c2e43b39ed5f4df3a8a289c5e15b7789","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T14:19:44Z","title_canon_sha256":"c20ba2cd4ae9a66aea4b1d462d9b045a88cdcfff5d8e0ba38154fcc380a239e5"},"schema_version":"1.0","source":{"id":"2306.17693","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17693","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17693v1","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17693","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"pith_short_12","alias_value":"JPNTXXL5VHWC","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"pith_short_16","alias_value":"JPNTXXL5VHWCLIQE","created_at":"2026-07-05T06:26:30Z"},{"alias_kind":"pith_short_8","alias_value":"JPNTXXL5","created_at":"2026-07-05T06:26:30Z"}],"graph_snapshots":[{"event_id":"sha256:d48352a4fa771f883f85aebcb6a84cb3522a6ccd149ad486a2061d280aa05471","target":"graph","created_at":"2026-07-05T06:26:30Z","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/2306.17693/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy. Unlike other algorithms for hierarchical sampling that optimize a variational bound, GFlowNet algorithms can stably run off-policy, which can be advantageous for discovering modes of the target distribution. Despite this flexibility in the choice of behaviour policy, the optimal way of efficiently selecting trajectories for training has not yet been systematically explored. ","authors_text":"Cheng-Hao Liu, Jarrid Rector-Brooks, Kanika Madan, Maksym Korablyov, Moksh Jain, Nikolay Malkin, Sarath Chandar, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T14:19:44Z","title":"Thompson sampling for improved exploration in GFlowNets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17693","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":"sha256:2274ad108d874c78619ced219fe80f3d26f5599b90451f1ec29feadcf816e678","target":"record","created_at":"2026-07-05T06:26:30Z","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":"6da5271dea079560ff43593763ffecd8c2e43b39ed5f4df3a8a289c5e15b7789","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T14:19:44Z","title_canon_sha256":"c20ba2cd4ae9a66aea4b1d462d9b045a88cdcfff5d8e0ba38154fcc380a239e5"},"schema_version":"1.0","source":{"id":"2306.17693","kind":"arxiv","version":1}},"canonical_sha256":"4bdb3bdd7da9ec25a20459242883683a2c2583980b5489a2fdb8fbc67bfff356","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bdb3bdd7da9ec25a20459242883683a2c2583980b5489a2fdb8fbc67bfff356","first_computed_at":"2026-07-05T06:26:30.644015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:30.644015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iAb2P1wIV1QJlFd5mq2n6eDKNdK15WSW1QR0PQEqYltkNaBzB/GlRzPe/foJyEGfViSdppsXW6ZvogOxiWWiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:30.644586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17693","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2274ad108d874c78619ced219fe80f3d26f5599b90451f1ec29feadcf816e678","sha256:d48352a4fa771f883f85aebcb6a84cb3522a6ccd149ad486a2061d280aa05471"],"state_sha256":"ce74b6de33cb7a4033f010e948dcbf0c095768fdd497e150e152acb58f0b2220"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0O20hSJYIpaDusbkM507qBfzdvCNIw2W4fDdBDkeAOt2UBqOM5Ar2QfWrlkHAfjOLXJiZeM/HSlQ06pfTKGAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:56:01.384505Z","bundle_sha256":"6751a61613f69f0cb435e7bc718dd545e42a42518326ae3fdb472dda1e76a6b5"}}