{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UN7GL36W75JITDYSYY6XB4RLLM","short_pith_number":"pith:UN7GL36W","canonical_record":{"source":{"id":"2002.09547","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T20:47:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60227d7770124b26ad3a7059be6288b0df786a1f1516710815fd9cbb52ba2c27","abstract_canon_sha256":"36d9d694c999b00eda38d8801742e42fbdf195b47be275f20c07f2d28797d824"},"schema_version":"1.0"},"canonical_sha256":"a37e65efd6ff52898f12c63d70f22b5b1665fd06c5d2601abf187d670d46539e","source":{"kind":"arxiv","id":"2002.09547","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09547","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09547v2","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09547","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"UN7GL36W75JI","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"UN7GL36W75JITDYS","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"UN7GL36W","created_at":"2026-07-05T00:43:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UN7GL36W75JITDYSYY6XB4RLLM","target":"record","payload":{"canonical_record":{"source":{"id":"2002.09547","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T20:47:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"60227d7770124b26ad3a7059be6288b0df786a1f1516710815fd9cbb52ba2c27","abstract_canon_sha256":"36d9d694c999b00eda38d8801742e42fbdf195b47be275f20c07f2d28797d824"},"schema_version":"1.0"},"canonical_sha256":"a37e65efd6ff52898f12c63d70f22b5b1665fd06c5d2601abf187d670d46539e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:58.603731Z","signature_b64":"ijPGjjbT9rCBgkO+A38dtKVbMncH2fBtQTPgprYBOwWTJhKiYv5R3Jjuz7H01vp5TwOCLc2+oTYYfYt83kFUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a37e65efd6ff52898f12c63d70f22b5b1665fd06c5d2601abf187d670d46539e","last_reissued_at":"2026-07-05T00:43:58.603332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:58.603332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.09547","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":"2026-07-05T00:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3jEKFOX6NJLM6iimt/FQOw6f7o4yv88JShQhgG/n+OOs4Zl6acbJqL0Twtfz0i7490RAOg/SLpbvFk+kVU1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:20.577877Z"},"content_sha256":"de7eedd8d09076c890541150d34e2392e34bec0f453a12b7e2b40702fff991be","schema_version":"1.0","event_id":"sha256:de7eedd8d09076c890541150d34e2392e34bec0f453a12b7e2b40702fff991be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UN7GL36W75JITDYSYY6XB4RLLM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris van der Heide, Fred Roosta, Liam Hodgkinson, Michael W. Mahoney","submitted_at":"2020-02-21T20:47:55Z","abstract_excerpt":"We introduce stochastic normalizing flows, an extension of continuous normalizing flows for maximum likelihood estimation and variational inference (VI) using stochastic differential equations (SDEs). Using the theory of rough paths, the underlying Brownian motion is treated as a latent variable and approximated, enabling efficient training of neural SDEs as random neural ordinary differential equations. These SDEs can be used for constructing efficient Markov chains to sample from the underlying distribution of a given dataset. Furthermore, by considering families of targeted SDEs with prescr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09547","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/2002.09547/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":"2026-07-05T00:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"df8hEUhbA6IxanWpeBlMXl91r7fg/+oqy39a0jwZ++JWr13q9puApc6KPUp3IjRdCG8GBHPZa67IOhUj3aJQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:42:20.578787Z"},"content_sha256":"882fab5d5d1bdb5399d686878067ff198260b038696bfc86b28cdc8fbefa20c1","schema_version":"1.0","event_id":"sha256:882fab5d5d1bdb5399d686878067ff198260b038696bfc86b28cdc8fbefa20c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UN7GL36W75JITDYSYY6XB4RLLM/bundle.json","state_url":"https://pith.science/pith/UN7GL36W75JITDYSYY6XB4RLLM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UN7GL36W75JITDYSYY6XB4RLLM/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":"2026-08-10T16:42:20Z","links":{"resolver":"https://pith.science/pith/UN7GL36W75JITDYSYY6XB4RLLM","bundle":"https://pith.science/pith/UN7GL36W75JITDYSYY6XB4RLLM/bundle.json","state":"https://pith.science/pith/UN7GL36W75JITDYSYY6XB4RLLM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UN7GL36W75JITDYSYY6XB4RLLM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UN7GL36W75JITDYSYY6XB4RLLM","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":"36d9d694c999b00eda38d8801742e42fbdf195b47be275f20c07f2d28797d824","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T20:47:55Z","title_canon_sha256":"60227d7770124b26ad3a7059be6288b0df786a1f1516710815fd9cbb52ba2c27"},"schema_version":"1.0","source":{"id":"2002.09547","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09547","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09547v2","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09547","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"UN7GL36W75JI","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"UN7GL36W75JITDYS","created_at":"2026-07-05T00:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"UN7GL36W","created_at":"2026-07-05T00:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:882fab5d5d1bdb5399d686878067ff198260b038696bfc86b28cdc8fbefa20c1","target":"graph","created_at":"2026-07-05T00:43:58Z","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/2002.09547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce stochastic normalizing flows, an extension of continuous normalizing flows for maximum likelihood estimation and variational inference (VI) using stochastic differential equations (SDEs). Using the theory of rough paths, the underlying Brownian motion is treated as a latent variable and approximated, enabling efficient training of neural SDEs as random neural ordinary differential equations. These SDEs can be used for constructing efficient Markov chains to sample from the underlying distribution of a given dataset. Furthermore, by considering families of targeted SDEs with prescr","authors_text":"Chris van der Heide, Fred Roosta, Liam Hodgkinson, Michael W. Mahoney","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T20:47:55Z","title":"Stochastic Normalizing Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09547","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:de7eedd8d09076c890541150d34e2392e34bec0f453a12b7e2b40702fff991be","target":"record","created_at":"2026-07-05T00:43:58Z","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":"36d9d694c999b00eda38d8801742e42fbdf195b47be275f20c07f2d28797d824","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T20:47:55Z","title_canon_sha256":"60227d7770124b26ad3a7059be6288b0df786a1f1516710815fd9cbb52ba2c27"},"schema_version":"1.0","source":{"id":"2002.09547","kind":"arxiv","version":2}},"canonical_sha256":"a37e65efd6ff52898f12c63d70f22b5b1665fd06c5d2601abf187d670d46539e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a37e65efd6ff52898f12c63d70f22b5b1665fd06c5d2601abf187d670d46539e","first_computed_at":"2026-07-05T00:43:58.603332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:58.603332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ijPGjjbT9rCBgkO+A38dtKVbMncH2fBtQTPgprYBOwWTJhKiYv5R3Jjuz7H01vp5TwOCLc2+oTYYfYt83kFUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:58.603731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09547","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de7eedd8d09076c890541150d34e2392e34bec0f453a12b7e2b40702fff991be","sha256:882fab5d5d1bdb5399d686878067ff198260b038696bfc86b28cdc8fbefa20c1"],"state_sha256":"24fb172015442eac4841f4ad62103ace1aa8cf450101e93aee7068761bd1d064"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rLe2YIJuAhThFkl49MDzKwhsjokEuuZotc0XZgow5biScbyV/8syunHkiLOXlI2D2UTho3mAp9LvdGj3vQOkAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:42:20.633573Z","bundle_sha256":"2653df40682d4c9f4f1a562fd5f8e450add868902f3359cfaa669595f571c8bf"}}