{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:NTWR5PNXXPCFRFQXH7KZQLR3LT","short_pith_number":"pith:NTWR5PNX","canonical_record":{"source":{"id":"1712.00287","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-01T12:08:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00babd4befe23c8c3b505a5eb9535411f4a1b545b92d41b33c13a6e9ef5533b9","abstract_canon_sha256":"4fc32e352edf4ae72fa4d53f4b5a03a02e6b296e9165bc17772ddb2a53eccdc8"},"schema_version":"1.0"},"canonical_sha256":"6ced1ebdb7bbc45896173fd5982e3b5cdfdf7bb1b502551b4cd1748f6c02c5ff","source":{"kind":"arxiv","id":"1712.00287","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00287","created_at":"2026-05-17T23:59:39Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00287v5","created_at":"2026-05-17T23:59:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00287","created_at":"2026-05-17T23:59:39Z"},{"alias_kind":"pith_short_12","alias_value":"NTWR5PNXXPCF","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NTWR5PNXXPCFRFQX","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NTWR5PNX","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:NTWR5PNXXPCFRFQXH7KZQLR3LT","target":"record","payload":{"canonical_record":{"source":{"id":"1712.00287","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-01T12:08:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00babd4befe23c8c3b505a5eb9535411f4a1b545b92d41b33c13a6e9ef5533b9","abstract_canon_sha256":"4fc32e352edf4ae72fa4d53f4b5a03a02e6b296e9165bc17772ddb2a53eccdc8"},"schema_version":"1.0"},"canonical_sha256":"6ced1ebdb7bbc45896173fd5982e3b5cdfdf7bb1b502551b4cd1748f6c02c5ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:39.387971Z","signature_b64":"D8bl5QUxFwGiYf+osYfUT8sjMWEFl8u+8AQYWdJU5JaUDFX1OUkm7NVIWHcYl9nbcqV8XCqEdnGBArFb3D7KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ced1ebdb7bbc45896173fd5982e3b5cdfdf7bb1b502551b4cd1748f6c02c5ff","last_reissued_at":"2026-05-17T23:59:39.387176Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:39.387176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.00287","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oMyqwXeT0GHE1yuBB/+di5WUzSniK1QdvpCdbI81oK5TAxxY4dQCngIg0AFuvFj2/okirnh4TdYK2RTuRH4/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:58:15.614823Z"},"content_sha256":"5ce95433356db0136c8999945f90373ba600c906fa3bb56c57c165d3f2b25618","schema_version":"1.0","event_id":"sha256:5ce95433356db0136c8999945f90373ba600c906fa3bb56c57c165d3f2b25618"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:NTWR5PNXXPCFRFQXH7KZQLR3LT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faithful Inversion of Generative Models for Effective Amortized Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam Golinski, Frank Wood, N. Siddharth, Robert Zinkov, Stefan Webb, Tom Rainforth, Yee Whye Teh","submitted_at":"2017-12-01T12:08:03Z","abstract_excerpt":"Inference amortization methods share information across multiple posterior-inference problems, allowing each to be carried out more efficiently. Generally, they require the inversion of the dependency structure in the generative model, as the modeller must learn a mapping from observations to distributions approximating the posterior. Previous approaches have involved inverting the dependency structure in a heuristic way that fails to capture these dependencies correctly, thereby limiting the achievable accuracy of the resulting approximations. We introduce an algorithm for faithfully, and min"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00287","kind":"arxiv","version":5},"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":"2026-05-17T23:59:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fz1k3Fd6xqswwdjZ3zhjXs74T2k2uVl9aiCjxhMLzxFVNSv1AcoWOak8hS/PXuxb961OYrmiqJ2CKy+R5cYbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:58:15.615500Z"},"content_sha256":"dd01f3271d293ec197ce67ced8d015228218cdae9942e1bbc3efff9239b152f7","schema_version":"1.0","event_id":"sha256:dd01f3271d293ec197ce67ced8d015228218cdae9942e1bbc3efff9239b152f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTWR5PNXXPCFRFQXH7KZQLR3LT/bundle.json","state_url":"https://pith.science/pith/NTWR5PNXXPCFRFQXH7KZQLR3LT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTWR5PNXXPCFRFQXH7KZQLR3LT/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":"2026-05-28T16:58:15Z","links":{"resolver":"https://pith.science/pith/NTWR5PNXXPCFRFQXH7KZQLR3LT","bundle":"https://pith.science/pith/NTWR5PNXXPCFRFQXH7KZQLR3LT/bundle.json","state":"https://pith.science/pith/NTWR5PNXXPCFRFQXH7KZQLR3LT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTWR5PNXXPCFRFQXH7KZQLR3LT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:NTWR5PNXXPCFRFQXH7KZQLR3LT","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":"4fc32e352edf4ae72fa4d53f4b5a03a02e6b296e9165bc17772ddb2a53eccdc8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-01T12:08:03Z","title_canon_sha256":"00babd4befe23c8c3b505a5eb9535411f4a1b545b92d41b33c13a6e9ef5533b9"},"schema_version":"1.0","source":{"id":"1712.00287","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00287","created_at":"2026-05-17T23:59:39Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00287v5","created_at":"2026-05-17T23:59:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00287","created_at":"2026-05-17T23:59:39Z"},{"alias_kind":"pith_short_12","alias_value":"NTWR5PNXXPCF","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NTWR5PNXXPCFRFQX","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NTWR5PNX","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:dd01f3271d293ec197ce67ced8d015228218cdae9942e1bbc3efff9239b152f7","target":"graph","created_at":"2026-05-17T23:59:39Z","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":"Inference amortization methods share information across multiple posterior-inference problems, allowing each to be carried out more efficiently. Generally, they require the inversion of the dependency structure in the generative model, as the modeller must learn a mapping from observations to distributions approximating the posterior. Previous approaches have involved inverting the dependency structure in a heuristic way that fails to capture these dependencies correctly, thereby limiting the achievable accuracy of the resulting approximations. We introduce an algorithm for faithfully, and min","authors_text":"Adam Golinski, Frank Wood, N. Siddharth, Robert Zinkov, Stefan Webb, Tom Rainforth, Yee Whye Teh","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-01T12:08:03Z","title":"Faithful Inversion of Generative Models for Effective Amortized Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00287","kind":"arxiv","version":5},"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":"sha256:5ce95433356db0136c8999945f90373ba600c906fa3bb56c57c165d3f2b25618","target":"record","created_at":"2026-05-17T23:59:39Z","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":"4fc32e352edf4ae72fa4d53f4b5a03a02e6b296e9165bc17772ddb2a53eccdc8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-01T12:08:03Z","title_canon_sha256":"00babd4befe23c8c3b505a5eb9535411f4a1b545b92d41b33c13a6e9ef5533b9"},"schema_version":"1.0","source":{"id":"1712.00287","kind":"arxiv","version":5}},"canonical_sha256":"6ced1ebdb7bbc45896173fd5982e3b5cdfdf7bb1b502551b4cd1748f6c02c5ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ced1ebdb7bbc45896173fd5982e3b5cdfdf7bb1b502551b4cd1748f6c02c5ff","first_computed_at":"2026-05-17T23:59:39.387176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:39.387176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D8bl5QUxFwGiYf+osYfUT8sjMWEFl8u+8AQYWdJU5JaUDFX1OUkm7NVIWHcYl9nbcqV8XCqEdnGBArFb3D7KCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:39.387971Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00287","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ce95433356db0136c8999945f90373ba600c906fa3bb56c57c165d3f2b25618","sha256:dd01f3271d293ec197ce67ced8d015228218cdae9942e1bbc3efff9239b152f7"],"state_sha256":"97783f2e60c8f989da8eced5f5f0f933909a9e4601221b7db57754eccff7b6e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"64TUgM7L0nH16FZI4AXMAjJJxqeNwZsNmLWWBH7LDhZYabA9QRcFVW6GUr9gcuZm02cLYjHvN71/ac6A/cbZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T16:58:15.618950Z","bundle_sha256":"5776a59544a9befab67ea474cd4ed988ba600bd19daffbb587cd2e94554d0e07"}}