{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ATU5QPOS7T2EKSEK37FVCCT54H","short_pith_number":"pith:ATU5QPOS","canonical_record":{"source":{"id":"1805.11284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-29T07:50:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b46477f26e41761fb73158a5b2a048b736f21bf0ea892fe34d73dd716ba1d1b7","abstract_canon_sha256":"87911cec6dcb6e66e4eb292759999c26a8287346ef50b137fa44f871e773e658"},"schema_version":"1.0"},"canonical_sha256":"04e9d83dd2fcf445488adfcb510a7de1ef81384794b6e0076c15593a214cb49d","source":{"kind":"arxiv","id":"1805.11284","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11284","created_at":"2026-05-18T00:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11284v2","created_at":"2026-05-18T00:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11284","created_at":"2026-05-18T00:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"ATU5QPOS7T2E","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ATU5QPOS7T2EKSEK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ATU5QPOS","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ATU5QPOS7T2EKSEK37FVCCT54H","target":"record","payload":{"canonical_record":{"source":{"id":"1805.11284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-29T07:50:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b46477f26e41761fb73158a5b2a048b736f21bf0ea892fe34d73dd716ba1d1b7","abstract_canon_sha256":"87911cec6dcb6e66e4eb292759999c26a8287346ef50b137fa44f871e773e658"},"schema_version":"1.0"},"canonical_sha256":"04e9d83dd2fcf445488adfcb510a7de1ef81384794b6e0076c15593a214cb49d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:21.186457Z","signature_b64":"wJf+z2xT1VnpgBYoAEmwOEQAUO90x8pwOllvBE2bfkFptyAqmZfGIiNQGSOihgK8pLNE7lPB069UfmIohZXOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04e9d83dd2fcf445488adfcb510a7de1ef81384794b6e0076c15593a214cb49d","last_reissued_at":"2026-05-18T00:14:21.185856Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:21.185856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.11284","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":"2026-05-18T00:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfDYuYVETZRgvLu57EK/LSn1+jVli/McmMA1AdXEZYICGzErdKETsutyh8iDboi5Ty7wH8oSp5PYShtgT+f1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:05:43.519029Z"},"content_sha256":"554e644df2ae33f95dcb168ea832e75e3c21d7a739c1a93a3046472a62ba1a43","schema_version":"1.0","event_id":"sha256:554e644df2ae33f95dcb168ea832e75e3c21d7a739c1a93a3046472a62ba1a43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ATU5QPOS7T2EKSEK37FVCCT54H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wasserstein Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Maris, Luca Ambrogioni, Marcel A. J. van Gerven, Max Hinne, Umut G\\\"u\\c{c}l\\\"u, Ya\\u{g}mur G\\\"u\\c{c}l\\\"ut\\\"urk","submitted_at":"2018-05-29T07:50:26Z","abstract_excerpt":"This paper introduces Wasserstein variational inference, a new form of approximate Bayesian inference based on optimal transport theory. Wasserstein variational inference uses a new family of divergences that includes both f-divergences and the Wasserstein distance as special cases. The gradients of the Wasserstein variational loss are obtained by backpropagating through the Sinkhorn iterations. This technique results in a very stable likelihood-free training method that can be used with implicit distributions and probabilistic programs. Using the Wasserstein variational inference framework, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11284","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":""},"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":"2026-05-18T00:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VM7aFfQFG0SPsLgH0Nz1ce7Yj/XtJyD2DunkGRTT/3hQMv59ZXUmhx1AxTUJej0jjMmCl98+3rJPwWKS9mj3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:05:43.519722Z"},"content_sha256":"a6fc79566aa527485ba0020bcceaec40b8553adec57e48cbf484a5605a93c1fa","schema_version":"1.0","event_id":"sha256:a6fc79566aa527485ba0020bcceaec40b8553adec57e48cbf484a5605a93c1fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ATU5QPOS7T2EKSEK37FVCCT54H/bundle.json","state_url":"https://pith.science/pith/ATU5QPOS7T2EKSEK37FVCCT54H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ATU5QPOS7T2EKSEK37FVCCT54H/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":"2026-05-31T23:05:43Z","links":{"resolver":"https://pith.science/pith/ATU5QPOS7T2EKSEK37FVCCT54H","bundle":"https://pith.science/pith/ATU5QPOS7T2EKSEK37FVCCT54H/bundle.json","state":"https://pith.science/pith/ATU5QPOS7T2EKSEK37FVCCT54H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ATU5QPOS7T2EKSEK37FVCCT54H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ATU5QPOS7T2EKSEK37FVCCT54H","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":"87911cec6dcb6e66e4eb292759999c26a8287346ef50b137fa44f871e773e658","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-29T07:50:26Z","title_canon_sha256":"b46477f26e41761fb73158a5b2a048b736f21bf0ea892fe34d73dd716ba1d1b7"},"schema_version":"1.0","source":{"id":"1805.11284","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11284","created_at":"2026-05-18T00:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11284v2","created_at":"2026-05-18T00:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11284","created_at":"2026-05-18T00:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"ATU5QPOS7T2E","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ATU5QPOS7T2EKSEK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ATU5QPOS","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:a6fc79566aa527485ba0020bcceaec40b8553adec57e48cbf484a5605a93c1fa","target":"graph","created_at":"2026-05-18T00:14:21Z","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"},"paper":{"abstract_excerpt":"This paper introduces Wasserstein variational inference, a new form of approximate Bayesian inference based on optimal transport theory. Wasserstein variational inference uses a new family of divergences that includes both f-divergences and the Wasserstein distance as special cases. The gradients of the Wasserstein variational loss are obtained by backpropagating through the Sinkhorn iterations. This technique results in a very stable likelihood-free training method that can be used with implicit distributions and probabilistic programs. Using the Wasserstein variational inference framework, w","authors_text":"Eric Maris, Luca Ambrogioni, Marcel A. J. van Gerven, Max Hinne, Umut G\\\"u\\c{c}l\\\"u, Ya\\u{g}mur G\\\"u\\c{c}l\\\"ut\\\"urk","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-29T07:50:26Z","title":"Wasserstein Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11284","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":"sha256:554e644df2ae33f95dcb168ea832e75e3c21d7a739c1a93a3046472a62ba1a43","target":"record","created_at":"2026-05-18T00:14:21Z","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":"87911cec6dcb6e66e4eb292759999c26a8287346ef50b137fa44f871e773e658","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-29T07:50:26Z","title_canon_sha256":"b46477f26e41761fb73158a5b2a048b736f21bf0ea892fe34d73dd716ba1d1b7"},"schema_version":"1.0","source":{"id":"1805.11284","kind":"arxiv","version":2}},"canonical_sha256":"04e9d83dd2fcf445488adfcb510a7de1ef81384794b6e0076c15593a214cb49d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04e9d83dd2fcf445488adfcb510a7de1ef81384794b6e0076c15593a214cb49d","first_computed_at":"2026-05-18T00:14:21.185856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:21.185856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wJf+z2xT1VnpgBYoAEmwOEQAUO90x8pwOllvBE2bfkFptyAqmZfGIiNQGSOihgK8pLNE7lPB069UfmIohZXOCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:21.186457Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11284","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:554e644df2ae33f95dcb168ea832e75e3c21d7a739c1a93a3046472a62ba1a43","sha256:a6fc79566aa527485ba0020bcceaec40b8553adec57e48cbf484a5605a93c1fa"],"state_sha256":"b1c2011dc3e327d8150885d16b0d355b70f7b03c559af182a75c802a6ea09f67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m0xzugjtLTr2qEOMIEufEAqM2iUz9FRZJiJGlJnd6/6cHo6qRXQD41CHmTL1uiLlaqBPIBfRcQHpG/oGiy1ODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T23:05:43.523502Z","bundle_sha256":"a084ba2e940b2bc9b333acdda34deb51397a6e286280e1d03a2f6a65837ac85f"}}