{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OERHMJDSEVVK7OAH6BQWZCKFFN","short_pith_number":"pith:OERHMJDS","canonical_record":{"source":{"id":"2310.06643","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:06:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e5bf29cc0dc98cfd2b04cedf95fce98f155adb84a2360e4c1c700c6ee2c2279a","abstract_canon_sha256":"4b94c4750db350e12013cad5997bec975cf914849cc7b7acb417ca445dae5156"},"schema_version":"1.0"},"canonical_sha256":"7122762472256aafb807f0616c89452b449f9f72d9f7a373efae070622cfaeaf","source":{"kind":"arxiv","id":"2310.06643","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06643","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06643v3","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06643","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"OERHMJDSEVVK","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"OERHMJDSEVVK7OAH","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"OERHMJDS","created_at":"2026-07-05T07:10:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OERHMJDSEVVK7OAH6BQWZCKFFN","target":"record","payload":{"canonical_record":{"source":{"id":"2310.06643","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:06:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e5bf29cc0dc98cfd2b04cedf95fce98f155adb84a2360e4c1c700c6ee2c2279a","abstract_canon_sha256":"4b94c4750db350e12013cad5997bec975cf914849cc7b7acb417ca445dae5156"},"schema_version":"1.0"},"canonical_sha256":"7122762472256aafb807f0616c89452b449f9f72d9f7a373efae070622cfaeaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:50.126307Z","signature_b64":"e0N/wUznZYUVW7OsocFQ97TZOvLmzHIDcG5SiHkcvBJJsccVMSTB9tvneg7wWK+Y+HMpU/M4+wmexSExbcubAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7122762472256aafb807f0616c89452b449f9f72d9f7a373efae070622cfaeaf","last_reissued_at":"2026-07-05T07:10:50.125898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:50.125898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.06643","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MA6L4h9t1vqsbi8zd84uXj5HuSvYFh8KXZDgq3Ey6/qdyffi1g+T4PyrBEKylbyhAdCaVdxyWgSic7omnGXjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:34:14.002286Z"},"content_sha256":"0a999162f542e86fe58fa75df1b74f8fe2f32cc2cbb6ebb434973322a2d8b7fb","schema_version":"1.0","event_id":"sha256:0a999162f542e86fe58fa75df1b74f8fe2f32cc2cbb6ebb434973322a2d8b7fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OERHMJDSEVVK7OAH6BQWZCKFFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Variational Inference for High-Dimensional Posteriors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anshuk Uppal, Jes Frellsen, Kristoffer Stensbo-Smidt, Wouter Boomsma","submitted_at":"2023-10-10T14:06:56Z","abstract_excerpt":"In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex multimodal and correlated posteriors in high-dimensional spaces. Our approach introduces novel bounds for approximate inference using implicit distributions by locally linearising the neural sampler. This is distinct from existing methods that rely on additional discriminator networks and unstable adversarial objectives. Furthermore, we present a new sampler a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06643","kind":"arxiv","version":3},"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/2310.06643/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":"2026-07-05T07:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OfFxldLXoK+l8C9krXrIRnhJvEUDp6NzoK14OUBq48oYOIDk7PCLGEPUCG/yPdJ+jVGZgEEnUUT9t+6Dvlb2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:34:14.002659Z"},"content_sha256":"bfb213972b9e14957c5fdbfc7aa8056200b9329fe9f0d06e5587456a359cd586","schema_version":"1.0","event_id":"sha256:bfb213972b9e14957c5fdbfc7aa8056200b9329fe9f0d06e5587456a359cd586"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OERHMJDSEVVK7OAH6BQWZCKFFN/bundle.json","state_url":"https://pith.science/pith/OERHMJDSEVVK7OAH6BQWZCKFFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OERHMJDSEVVK7OAH6BQWZCKFFN/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":"2026-08-05T01:34:14Z","links":{"resolver":"https://pith.science/pith/OERHMJDSEVVK7OAH6BQWZCKFFN","bundle":"https://pith.science/pith/OERHMJDSEVVK7OAH6BQWZCKFFN/bundle.json","state":"https://pith.science/pith/OERHMJDSEVVK7OAH6BQWZCKFFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OERHMJDSEVVK7OAH6BQWZCKFFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OERHMJDSEVVK7OAH6BQWZCKFFN","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":"4b94c4750db350e12013cad5997bec975cf914849cc7b7acb417ca445dae5156","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:06:56Z","title_canon_sha256":"e5bf29cc0dc98cfd2b04cedf95fce98f155adb84a2360e4c1c700c6ee2c2279a"},"schema_version":"1.0","source":{"id":"2310.06643","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06643","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06643v3","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06643","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"OERHMJDSEVVK","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"OERHMJDSEVVK7OAH","created_at":"2026-07-05T07:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"OERHMJDS","created_at":"2026-07-05T07:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:bfb213972b9e14957c5fdbfc7aa8056200b9329fe9f0d06e5587456a359cd586","target":"graph","created_at":"2026-07-05T07:10:50Z","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/2310.06643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex multimodal and correlated posteriors in high-dimensional spaces. Our approach introduces novel bounds for approximate inference using implicit distributions by locally linearising the neural sampler. This is distinct from existing methods that rely on additional discriminator networks and unstable adversarial objectives. Furthermore, we present a new sampler a","authors_text":"Anshuk Uppal, Jes Frellsen, Kristoffer Stensbo-Smidt, Wouter Boomsma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:06:56Z","title":"Implicit Variational Inference for High-Dimensional Posteriors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06643","kind":"arxiv","version":3},"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":"sha256:0a999162f542e86fe58fa75df1b74f8fe2f32cc2cbb6ebb434973322a2d8b7fb","target":"record","created_at":"2026-07-05T07:10:50Z","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":"4b94c4750db350e12013cad5997bec975cf914849cc7b7acb417ca445dae5156","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:06:56Z","title_canon_sha256":"e5bf29cc0dc98cfd2b04cedf95fce98f155adb84a2360e4c1c700c6ee2c2279a"},"schema_version":"1.0","source":{"id":"2310.06643","kind":"arxiv","version":3}},"canonical_sha256":"7122762472256aafb807f0616c89452b449f9f72d9f7a373efae070622cfaeaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7122762472256aafb807f0616c89452b449f9f72d9f7a373efae070622cfaeaf","first_computed_at":"2026-07-05T07:10:50.125898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:50.125898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e0N/wUznZYUVW7OsocFQ97TZOvLmzHIDcG5SiHkcvBJJsccVMSTB9tvneg7wWK+Y+HMpU/M4+wmexSExbcubAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:50.126307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06643","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a999162f542e86fe58fa75df1b74f8fe2f32cc2cbb6ebb434973322a2d8b7fb","sha256:bfb213972b9e14957c5fdbfc7aa8056200b9329fe9f0d06e5587456a359cd586"],"state_sha256":"dd97ceeac082879d4e30fa3ca4a885e12ba4ccd9fdb762ae65581a8f33725a4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZ3LGfhLA3YT+0647LJ8Ztk08Gj5ifxA+nW1iulxHkDtbD7XCUkV0bIJp6XaPrVodFpzqrmLCrpofj82dXbwDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:34:14.005131Z","bundle_sha256":"803ea51e6bd6923de1c3180a5a7b9b9bad0b3a4d169b0cc8e762ac4d2dcb7638"}}