{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ST5GN6BYXEJH3QWAZSZFDL4NQD","short_pith_number":"pith:ST5GN6BY","canonical_record":{"source":{"id":"1807.01604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T14:14:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e4c872f8250a696571f2fd1d78ea21c1709aa9f279eef2e1188b8283511727e","abstract_canon_sha256":"430793343446ac6d2439ec51f9e6577cbda740d28ba9ea951359c16bdd5c479a"},"schema_version":"1.0"},"canonical_sha256":"94fa66f838b9127dc2c0ccb251af8d80ecd469dfd66e055c4e44a68c04032470","source":{"kind":"arxiv","id":"1807.01604","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01604","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01604v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01604","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"ST5GN6BYXEJH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"ST5GN6BYXEJH3QWA","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"ST5GN6BY","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ST5GN6BYXEJH3QWAZSZFDL4NQD","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T14:14:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e4c872f8250a696571f2fd1d78ea21c1709aa9f279eef2e1188b8283511727e","abstract_canon_sha256":"430793343446ac6d2439ec51f9e6577cbda740d28ba9ea951359c16bdd5c479a"},"schema_version":"1.0"},"canonical_sha256":"94fa66f838b9127dc2c0ccb251af8d80ecd469dfd66e055c4e44a68c04032470","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:29.353340Z","signature_b64":"7jF3WyXTBojL0MogtTC8ErUdzlolf66ORdadCLF6Om9OkeHlUDgeUdysr0k6ATmmYNno13CBZg+Ac0dIT+NQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94fa66f838b9127dc2c0ccb251af8d80ecd469dfd66e055c4e44a68c04032470","last_reissued_at":"2026-05-18T00:11:29.352881Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:29.352881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01604","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":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbE32FF2JNmfCLZMDuDHrClZQbhsLaQdn3fTSVbidSaw0oNOLLhowbZJl6hUQ6RvrROpEtUZbjiq1JSFYJa6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T08:18:22.578710Z"},"content_sha256":"f9477d5c632731061eee4b09f343900fe66fe10e2a4336aa5e589132d7f34a8f","schema_version":"1.0","event_id":"sha256:f9477d5c632731061eee4b09f343900fe66fe10e2a4336aa5e589132d7f34a8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ST5GN6BYXEJH3QWAZSZFDL4NQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quasi-Monte Carlo Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Buchholz, Florian Wenzel, Stephan Mandt","submitted_at":"2018-07-04T14:14:30Z","abstract_excerpt":"Many machine learning problems involve Monte Carlo gradient estimators. As a prominent example, we focus on Monte Carlo variational inference (MCVI) in this paper. The performance of MCVI crucially depends on the variance of its stochastic gradients. We propose variance reduction by means of Quasi-Monte Carlo (QMC) sampling. QMC replaces N i.i.d. samples from a uniform probability distribution by a deterministic sequence of samples of length N. This sequence covers the underlying random variable space more evenly than i.i.d. draws, reducing the variance of the gradient estimator. With our nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01604","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":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C55SwU0ieZCsKZIYwvZTXhz5jVum9nZ69BhX2zajkAK7gCyCtEaRsBpgB2bDf7DVCnRl8C7PuoravZZXdt1mCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T08:18:22.579056Z"},"content_sha256":"e9053c29e57e72c4ed1a2cb31df14bcfe3786ae93efe7e3b7ae87c22d8a43956","schema_version":"1.0","event_id":"sha256:e9053c29e57e72c4ed1a2cb31df14bcfe3786ae93efe7e3b7ae87c22d8a43956"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ST5GN6BYXEJH3QWAZSZFDL4NQD/bundle.json","state_url":"https://pith.science/pith/ST5GN6BYXEJH3QWAZSZFDL4NQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ST5GN6BYXEJH3QWAZSZFDL4NQD/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":"2026-05-28T08:18:22Z","links":{"resolver":"https://pith.science/pith/ST5GN6BYXEJH3QWAZSZFDL4NQD","bundle":"https://pith.science/pith/ST5GN6BYXEJH3QWAZSZFDL4NQD/bundle.json","state":"https://pith.science/pith/ST5GN6BYXEJH3QWAZSZFDL4NQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ST5GN6BYXEJH3QWAZSZFDL4NQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ST5GN6BYXEJH3QWAZSZFDL4NQD","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":"430793343446ac6d2439ec51f9e6577cbda740d28ba9ea951359c16bdd5c479a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T14:14:30Z","title_canon_sha256":"8e4c872f8250a696571f2fd1d78ea21c1709aa9f279eef2e1188b8283511727e"},"schema_version":"1.0","source":{"id":"1807.01604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01604","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01604v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01604","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"ST5GN6BYXEJH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"ST5GN6BYXEJH3QWA","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"ST5GN6BY","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:e9053c29e57e72c4ed1a2cb31df14bcfe3786ae93efe7e3b7ae87c22d8a43956","target":"graph","created_at":"2026-05-18T00:11:29Z","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":"Many machine learning problems involve Monte Carlo gradient estimators. As a prominent example, we focus on Monte Carlo variational inference (MCVI) in this paper. The performance of MCVI crucially depends on the variance of its stochastic gradients. We propose variance reduction by means of Quasi-Monte Carlo (QMC) sampling. QMC replaces N i.i.d. samples from a uniform probability distribution by a deterministic sequence of samples of length N. This sequence covers the underlying random variable space more evenly than i.i.d. draws, reducing the variance of the gradient estimator. With our nove","authors_text":"Alexander Buchholz, Florian Wenzel, Stephan Mandt","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T14:14:30Z","title":"Quasi-Monte Carlo Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01604","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:f9477d5c632731061eee4b09f343900fe66fe10e2a4336aa5e589132d7f34a8f","target":"record","created_at":"2026-05-18T00:11:29Z","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":"430793343446ac6d2439ec51f9e6577cbda740d28ba9ea951359c16bdd5c479a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T14:14:30Z","title_canon_sha256":"8e4c872f8250a696571f2fd1d78ea21c1709aa9f279eef2e1188b8283511727e"},"schema_version":"1.0","source":{"id":"1807.01604","kind":"arxiv","version":1}},"canonical_sha256":"94fa66f838b9127dc2c0ccb251af8d80ecd469dfd66e055c4e44a68c04032470","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94fa66f838b9127dc2c0ccb251af8d80ecd469dfd66e055c4e44a68c04032470","first_computed_at":"2026-05-18T00:11:29.352881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:29.352881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7jF3WyXTBojL0MogtTC8ErUdzlolf66ORdadCLF6Om9OkeHlUDgeUdysr0k6ATmmYNno13CBZg+Ac0dIT+NQCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:29.353340Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9477d5c632731061eee4b09f343900fe66fe10e2a4336aa5e589132d7f34a8f","sha256:e9053c29e57e72c4ed1a2cb31df14bcfe3786ae93efe7e3b7ae87c22d8a43956"],"state_sha256":"61d6e3338c8beb39ddac2078ddd1fe228dc7612d97d75fe9093e901a892c329e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CD9EmVFhPlDl+fGoUI7mjZ22+Q6rXUBc1K/scWEf7EXl3rEQKtIHD8x+6g8T+p5OkfqADtYUC59mKQ1dmwHlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T08:18:22.581093Z","bundle_sha256":"c1323dc84e60aae09fc8b790a7104f5b95ba4f790e79d9ccec944e61147e7ef3"}}