{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CWITVAH7CJN2Q3BU7OM3WHJFGF","short_pith_number":"pith:CWITVAH7","canonical_record":{"source":{"id":"1906.06914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2019-06-17T09:30:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"197bdaebe63e09c1ff01e278d5f3bd01bad2942d32273b272f9cbf8b30912f49","abstract_canon_sha256":"6ff2c709e4a0a215b595cd4d280c06f8ab4ad74e8ed5c3ea3288151f988b7ae0"},"schema_version":"1.0"},"canonical_sha256":"15913a80ff125ba86c34fb99bb1d25316bb4b34c8ffc1d9ffe3f8df316bdeac4","source":{"kind":"arxiv","id":"1906.06914","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06914","created_at":"2026-05-17T23:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06914v1","created_at":"2026-05-17T23:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06914","created_at":"2026-05-17T23:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"CWITVAH7CJN2","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CWITVAH7CJN2Q3BU","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CWITVAH7","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CWITVAH7CJN2Q3BU7OM3WHJFGF","target":"record","payload":{"canonical_record":{"source":{"id":"1906.06914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2019-06-17T09:30:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"197bdaebe63e09c1ff01e278d5f3bd01bad2942d32273b272f9cbf8b30912f49","abstract_canon_sha256":"6ff2c709e4a0a215b595cd4d280c06f8ab4ad74e8ed5c3ea3288151f988b7ae0"},"schema_version":"1.0"},"canonical_sha256":"15913a80ff125ba86c34fb99bb1d25316bb4b34c8ffc1d9ffe3f8df316bdeac4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:12.338070Z","signature_b64":"D7OeipJ9sooq4Ajgm3bANcoZodFMLF3ugdrZOEB8ukLSkeV3l/upOQcK++G5zdBNPzRFkrv//bt5tuHwr4WtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15913a80ff125ba86c34fb99bb1d25316bb4b34c8ffc1d9ffe3f8df316bdeac4","last_reissued_at":"2026-05-17T23:43:12.337595Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:12.337595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.06914","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":"2026-05-17T23:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mBKbau3GrqxQYhTPdIWIWCD4s8uvVnpKSJmWuh3R4SOtbTFLhT0hHM8QtjM7CXpilU0dU77XOaI8vgQ7bJn2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:14:29.161704Z"},"content_sha256":"ab17d6fbe9a6df4a00bd5dd44aa1ce16d143da79ac2db50cbbfacd1147f6eadc","schema_version":"1.0","event_id":"sha256:ab17d6fbe9a6df4a00bd5dd44aa1ce16d143da79ac2db50cbbfacd1147f6eadc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CWITVAH7CJN2Q3BU7OM3WHJFGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Inference with Numerical Derivatives: variance reduction through coupling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.CO","authors_text":"Alexander Immer, Guillaume P. Dehaene","submitted_at":"2019-06-17T09:30:29Z","abstract_excerpt":"The Black Box Variational Inference (Ranganath et al. (2014)) algorithm provides a universal method for Variational Inference, but taking advantage of special properties of the approximation family or of the target can improve the convergence speed significantly. For example, if the approximation family is a transformation family, such as a Gaussian, then switching to the reparameterization gradient (Kingma and Welling (2014)) often yields a major reduction in gradient variance. Ultimately, reducing the variance can reduce the computational cost and yield better approximations.\n  We present a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06914","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":""},"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":"2026-05-17T23:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S079miNujt+aXD0Zph9QsnLYTDwPzNKLQHGZitzeGT7YVDIDMVhZ+KxH7Ss/J/gJp8IZkMQZwd0ps1+/h443Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:14:29.162037Z"},"content_sha256":"2622b6f39833790e441fae5ed0fac9ab7318af54588a95375ec2b5f3fd561607","schema_version":"1.0","event_id":"sha256:2622b6f39833790e441fae5ed0fac9ab7318af54588a95375ec2b5f3fd561607"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWITVAH7CJN2Q3BU7OM3WHJFGF/bundle.json","state_url":"https://pith.science/pith/CWITVAH7CJN2Q3BU7OM3WHJFGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWITVAH7CJN2Q3BU7OM3WHJFGF/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":"2026-07-17T05:14:29Z","links":{"resolver":"https://pith.science/pith/CWITVAH7CJN2Q3BU7OM3WHJFGF","bundle":"https://pith.science/pith/CWITVAH7CJN2Q3BU7OM3WHJFGF/bundle.json","state":"https://pith.science/pith/CWITVAH7CJN2Q3BU7OM3WHJFGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWITVAH7CJN2Q3BU7OM3WHJFGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CWITVAH7CJN2Q3BU7OM3WHJFGF","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":"6ff2c709e4a0a215b595cd4d280c06f8ab4ad74e8ed5c3ea3288151f988b7ae0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2019-06-17T09:30:29Z","title_canon_sha256":"197bdaebe63e09c1ff01e278d5f3bd01bad2942d32273b272f9cbf8b30912f49"},"schema_version":"1.0","source":{"id":"1906.06914","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06914","created_at":"2026-05-17T23:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06914v1","created_at":"2026-05-17T23:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06914","created_at":"2026-05-17T23:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"CWITVAH7CJN2","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CWITVAH7CJN2Q3BU","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CWITVAH7","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:2622b6f39833790e441fae5ed0fac9ab7318af54588a95375ec2b5f3fd561607","target":"graph","created_at":"2026-05-17T23:43:12Z","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":"The Black Box Variational Inference (Ranganath et al. (2014)) algorithm provides a universal method for Variational Inference, but taking advantage of special properties of the approximation family or of the target can improve the convergence speed significantly. For example, if the approximation family is a transformation family, such as a Gaussian, then switching to the reparameterization gradient (Kingma and Welling (2014)) often yields a major reduction in gradient variance. Ultimately, reducing the variance can reduce the computational cost and yield better approximations.\n  We present a ","authors_text":"Alexander Immer, Guillaume P. Dehaene","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2019-06-17T09:30:29Z","title":"Variational Inference with Numerical Derivatives: variance reduction through coupling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06914","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:ab17d6fbe9a6df4a00bd5dd44aa1ce16d143da79ac2db50cbbfacd1147f6eadc","target":"record","created_at":"2026-05-17T23:43:12Z","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":"6ff2c709e4a0a215b595cd4d280c06f8ab4ad74e8ed5c3ea3288151f988b7ae0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2019-06-17T09:30:29Z","title_canon_sha256":"197bdaebe63e09c1ff01e278d5f3bd01bad2942d32273b272f9cbf8b30912f49"},"schema_version":"1.0","source":{"id":"1906.06914","kind":"arxiv","version":1}},"canonical_sha256":"15913a80ff125ba86c34fb99bb1d25316bb4b34c8ffc1d9ffe3f8df316bdeac4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15913a80ff125ba86c34fb99bb1d25316bb4b34c8ffc1d9ffe3f8df316bdeac4","first_computed_at":"2026-05-17T23:43:12.337595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:12.337595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D7OeipJ9sooq4Ajgm3bANcoZodFMLF3ugdrZOEB8ukLSkeV3l/upOQcK++G5zdBNPzRFkrv//bt5tuHwr4WtCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:12.338070Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.06914","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab17d6fbe9a6df4a00bd5dd44aa1ce16d143da79ac2db50cbbfacd1147f6eadc","sha256:2622b6f39833790e441fae5ed0fac9ab7318af54588a95375ec2b5f3fd561607"],"state_sha256":"744fec6123d89d946671243121a110716e060813b27685a24f4663da6e507980"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wr03Ug2++7ejwERUR10is8Oq1rI4JilmuB1Y79LtuhQmn6kZzXpZy6aj5ozjixHTPm9D7qhV28czx99bO/UnDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T05:14:29.164114Z","bundle_sha256":"2135836627594060ea1d9b4dc61648002cdc8a2a84887c4b1f14ca25a549695f"}}