{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KU2DWVSU65T57RHAT4LOL4BGTI","short_pith_number":"pith:KU2DWVSU","canonical_record":{"source":{"id":"2302.06576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T18:24:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"930401683b2bf84d081e94439b1e700790a11223e7b1fd13c6db834c279199ca","abstract_canon_sha256":"9a3af3042b70fc689e982e886e84587078269f1da5c4bf7d111d03b42b857dbc"},"schema_version":"1.0"},"canonical_sha256":"55343b5654f767dfc4e09f16e5f0269a000475ea0cd053966f12e1e7a87f69cd","source":{"kind":"arxiv","id":"2302.06576","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06576","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06576v2","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06576","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"KU2DWVSU65T5","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"KU2DWVSU65T57RHA","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"KU2DWVSU","created_at":"2026-07-05T06:17:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KU2DWVSU65T57RHAT4LOL4BGTI","target":"record","payload":{"canonical_record":{"source":{"id":"2302.06576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T18:24:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"930401683b2bf84d081e94439b1e700790a11223e7b1fd13c6db834c279199ca","abstract_canon_sha256":"9a3af3042b70fc689e982e886e84587078269f1da5c4bf7d111d03b42b857dbc"},"schema_version":"1.0"},"canonical_sha256":"55343b5654f767dfc4e09f16e5f0269a000475ea0cd053966f12e1e7a87f69cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:04.867936Z","signature_b64":"m+pDn5bNgSKfZxMRvz8fEjRyLBRPjS2BrYIo9Pu2HySN38u859K0a+9GQ32BioV0q7O+nX7zsBx4RO4Li68NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55343b5654f767dfc4e09f16e5f0269a000475ea0cd053966f12e1e7a87f69cd","last_reissued_at":"2026-07-05T06:17:04.867523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:04.867523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.06576","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":"2026-07-05T06:17:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JAUZ14qlZfT7MrXACXNkLYxZzwiTNCZ/7VVNbZRoJDKq5uwz2lIUfUS5HF70Wz5TvH7G3sX977tS8FD2LbKmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T00:30:31.700393Z"},"content_sha256":"deaa8de2dc221489a90c3bce84ca1e309381967269fe349c4ddcb94f44714069","schema_version":"1.0","event_id":"sha256:deaa8de2dc221489a90c3bce84ca1e309381967269fe349c4ddcb94f44714069"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KU2DWVSU65T57RHAT4LOL4BGTI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GFlowNet-EM for learning compositional latent variable models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandros Graikos, Edward J. Hu, Katie Everett, Moksh Jain, Nikolay Malkin, Yoshua Bengio","submitted_at":"2023-02-13T18:24:21Z","abstract_excerpt":"Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large number of possible configurations of the latents. A key tradeoff in modeling the posteriors over latents is between expressivity and tractable optimization. For algorithms based on expectation-maximization (EM), the E-step is often intractable without restrictive approximations to the posterior. We propose the use of GFlowNets, algorithms for sampling from an unnormalized density by learning a stochastic policy for sequential construction of samples, for thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06576","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/2302.06576/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":"2026-07-05T06:17:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVvRgUhPbeOB/ZOwmxrJg3+l+0gjBTwXZxZz053X7+yWFyv3OJOBf/kMbpus3Ksy4u7jVEfRJeW9RLnEnB/EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T00:30:31.700768Z"},"content_sha256":"74980b7cef01bf7c63ff8520c22d51f5383c10b74b87f78ac8b8797045ad7f6d","schema_version":"1.0","event_id":"sha256:74980b7cef01bf7c63ff8520c22d51f5383c10b74b87f78ac8b8797045ad7f6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KU2DWVSU65T57RHAT4LOL4BGTI/bundle.json","state_url":"https://pith.science/pith/KU2DWVSU65T57RHAT4LOL4BGTI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KU2DWVSU65T57RHAT4LOL4BGTI/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":"2026-07-27T00:30:31Z","links":{"resolver":"https://pith.science/pith/KU2DWVSU65T57RHAT4LOL4BGTI","bundle":"https://pith.science/pith/KU2DWVSU65T57RHAT4LOL4BGTI/bundle.json","state":"https://pith.science/pith/KU2DWVSU65T57RHAT4LOL4BGTI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KU2DWVSU65T57RHAT4LOL4BGTI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KU2DWVSU65T57RHAT4LOL4BGTI","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":"9a3af3042b70fc689e982e886e84587078269f1da5c4bf7d111d03b42b857dbc","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T18:24:21Z","title_canon_sha256":"930401683b2bf84d081e94439b1e700790a11223e7b1fd13c6db834c279199ca"},"schema_version":"1.0","source":{"id":"2302.06576","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06576","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06576v2","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06576","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"KU2DWVSU65T5","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"KU2DWVSU65T57RHA","created_at":"2026-07-05T06:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"KU2DWVSU","created_at":"2026-07-05T06:17:04Z"}],"graph_snapshots":[{"event_id":"sha256:74980b7cef01bf7c63ff8520c22d51f5383c10b74b87f78ac8b8797045ad7f6d","target":"graph","created_at":"2026-07-05T06:17:04Z","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/2302.06576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large number of possible configurations of the latents. A key tradeoff in modeling the posteriors over latents is between expressivity and tractable optimization. For algorithms based on expectation-maximization (EM), the E-step is often intractable without restrictive approximations to the posterior. We propose the use of GFlowNets, algorithms for sampling from an unnormalized density by learning a stochastic policy for sequential construction of samples, for thi","authors_text":"Alexandros Graikos, Edward J. Hu, Katie Everett, Moksh Jain, Nikolay Malkin, Yoshua Bengio","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T18:24:21Z","title":"GFlowNet-EM for learning compositional latent variable models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06576","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:deaa8de2dc221489a90c3bce84ca1e309381967269fe349c4ddcb94f44714069","target":"record","created_at":"2026-07-05T06:17:04Z","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":"9a3af3042b70fc689e982e886e84587078269f1da5c4bf7d111d03b42b857dbc","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T18:24:21Z","title_canon_sha256":"930401683b2bf84d081e94439b1e700790a11223e7b1fd13c6db834c279199ca"},"schema_version":"1.0","source":{"id":"2302.06576","kind":"arxiv","version":2}},"canonical_sha256":"55343b5654f767dfc4e09f16e5f0269a000475ea0cd053966f12e1e7a87f69cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55343b5654f767dfc4e09f16e5f0269a000475ea0cd053966f12e1e7a87f69cd","first_computed_at":"2026-07-05T06:17:04.867523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:04.867523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m+pDn5bNgSKfZxMRvz8fEjRyLBRPjS2BrYIo9Pu2HySN38u859K0a+9GQ32BioV0q7O+nX7zsBx4RO4Li68NDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:04.867936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.06576","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:deaa8de2dc221489a90c3bce84ca1e309381967269fe349c4ddcb94f44714069","sha256:74980b7cef01bf7c63ff8520c22d51f5383c10b74b87f78ac8b8797045ad7f6d"],"state_sha256":"73742a3e23051ee145c7e7f6ab3459dd01bbcf5fe59ba5eae3a1b79c7142cb73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXJDeVkaTJPj2wDAkW3oSvViOaGE+P9hZt8j0XgvpcVzmJoWbva8noovAcVCvLggTWUU+QT6XgCMb5NkI/06AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T00:30:31.702896Z","bundle_sha256":"2908fb9fb787caf16e505863f3719335f695ea05bb38ceb6ac812be3b4b8fbb6"}}