{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7XA2EQDODP72HLPDKTRIAWES6L","short_pith_number":"pith:7XA2EQDO","canonical_record":{"source":{"id":"2005.08482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-05-18T06:46:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"132cda8b93934940bed62c980c2b351de09c0d1260679b74e1cadfb128ceea96","abstract_canon_sha256":"060e34de2bbc5aee635a8220cfa554ba497bf02bad998b15ed2b5cadc40c69de"},"schema_version":"1.0"},"canonical_sha256":"fdc1a2406e1bffa3ade354e2805892f2d2d0a1ccafd26381c4ae883b5aa15539","source":{"kind":"arxiv","id":"2005.08482","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08482","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08482v2","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08482","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"7XA2EQDODP72","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"pith_short_16","alias_value":"7XA2EQDODP72HLPD","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"pith_short_8","alias_value":"7XA2EQDO","created_at":"2026-07-05T04:22:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7XA2EQDODP72HLPDKTRIAWES6L","target":"record","payload":{"canonical_record":{"source":{"id":"2005.08482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-05-18T06:46:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"132cda8b93934940bed62c980c2b351de09c0d1260679b74e1cadfb128ceea96","abstract_canon_sha256":"060e34de2bbc5aee635a8220cfa554ba497bf02bad998b15ed2b5cadc40c69de"},"schema_version":"1.0"},"canonical_sha256":"fdc1a2406e1bffa3ade354e2805892f2d2d0a1ccafd26381c4ae883b5aa15539","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:49.189745Z","signature_b64":"WzioXrlKgMQw/r2kMbpqogzCLC5N+SsDLLfjkFp/nZGckO1HzYaqmyDWI4BiXfwokfLdtDw2o88+lAWTMgIZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdc1a2406e1bffa3ade354e2805892f2d2d0a1ccafd26381c4ae883b5aa15539","last_reissued_at":"2026-07-05T04:22:49.189229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:49.189229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.08482","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":"2026-07-05T04:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efNCEsuVauo4xAQEUQiYE7z6AQf0zfbOH+YH0VjQPuSBB9z8OfY5+pCF21bZrFXg5QYqRN1sgmy/whiSl8pyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:53:29.808942Z"},"content_sha256":"f9100689b0de1d2ce0da61fe5c46af7344ef9ff51944f807a11302265d10e6a9","schema_version":"1.0","event_id":"sha256:f9100689b0de1d2ce0da61fe5c46af7344ef9ff51944f807a11302265d10e6a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7XA2EQDODP72HLPDKTRIAWES6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Hyper-Encoding Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hieu-Chi Dam, Phuoc Nguyen, Santu Rana, Sunil Gupta, Svetha Venkatesh, Truyen Tran","submitted_at":"2020-05-18T06:46:09Z","abstract_excerpt":"We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters \\theta is drawn from a distribution p(\\theta) which is modeled by a hyper-level VAE. We propose a variational inference using Gaussian mixture models to implicitly encode the parameters \\theta into a low dimensional Gaussian distribution. Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(\\theta). HyperVAE can encode the parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08482","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.08482/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":"2026-07-05T04:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+7N8G7zEesWL+MyPsa/Oa4+h8Ho+6OAgawa2LlKwUPqAGG1dM1WoP8m6v30Tur7JtR2mjdTDdW/XpTqxwyWXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:53:29.809493Z"},"content_sha256":"e58df6393c2ef6ab932e800893ba53afca7f7cbba0c99a26b6bbf975c92b7103","schema_version":"1.0","event_id":"sha256:e58df6393c2ef6ab932e800893ba53afca7f7cbba0c99a26b6bbf975c92b7103"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XA2EQDODP72HLPDKTRIAWES6L/bundle.json","state_url":"https://pith.science/pith/7XA2EQDODP72HLPDKTRIAWES6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XA2EQDODP72HLPDKTRIAWES6L/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":"2026-08-10T17:53:29Z","links":{"resolver":"https://pith.science/pith/7XA2EQDODP72HLPDKTRIAWES6L","bundle":"https://pith.science/pith/7XA2EQDODP72HLPDKTRIAWES6L/bundle.json","state":"https://pith.science/pith/7XA2EQDODP72HLPDKTRIAWES6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XA2EQDODP72HLPDKTRIAWES6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7XA2EQDODP72HLPDKTRIAWES6L","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":"060e34de2bbc5aee635a8220cfa554ba497bf02bad998b15ed2b5cadc40c69de","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-05-18T06:46:09Z","title_canon_sha256":"132cda8b93934940bed62c980c2b351de09c0d1260679b74e1cadfb128ceea96"},"schema_version":"1.0","source":{"id":"2005.08482","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08482","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08482v2","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08482","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"7XA2EQDODP72","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"pith_short_16","alias_value":"7XA2EQDODP72HLPD","created_at":"2026-07-05T04:22:49Z"},{"alias_kind":"pith_short_8","alias_value":"7XA2EQDO","created_at":"2026-07-05T04:22:49Z"}],"graph_snapshots":[{"event_id":"sha256:e58df6393c2ef6ab932e800893ba53afca7f7cbba0c99a26b6bbf975c92b7103","target":"graph","created_at":"2026-07-05T04:22:49Z","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/2005.08482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters \\theta is drawn from a distribution p(\\theta) which is modeled by a hyper-level VAE. We propose a variational inference using Gaussian mixture models to implicitly encode the parameters \\theta into a low dimensional Gaussian distribution. Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(\\theta). HyperVAE can encode the parame","authors_text":"Hieu-Chi Dam, Phuoc Nguyen, Santu Rana, Sunil Gupta, Svetha Venkatesh, Truyen Tran","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-05-18T06:46:09Z","title":"Variational Hyper-Encoding Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08482","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:f9100689b0de1d2ce0da61fe5c46af7344ef9ff51944f807a11302265d10e6a9","target":"record","created_at":"2026-07-05T04:22:49Z","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":"060e34de2bbc5aee635a8220cfa554ba497bf02bad998b15ed2b5cadc40c69de","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-05-18T06:46:09Z","title_canon_sha256":"132cda8b93934940bed62c980c2b351de09c0d1260679b74e1cadfb128ceea96"},"schema_version":"1.0","source":{"id":"2005.08482","kind":"arxiv","version":2}},"canonical_sha256":"fdc1a2406e1bffa3ade354e2805892f2d2d0a1ccafd26381c4ae883b5aa15539","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdc1a2406e1bffa3ade354e2805892f2d2d0a1ccafd26381c4ae883b5aa15539","first_computed_at":"2026-07-05T04:22:49.189229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:49.189229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WzioXrlKgMQw/r2kMbpqogzCLC5N+SsDLLfjkFp/nZGckO1HzYaqmyDWI4BiXfwokfLdtDw2o88+lAWTMgIZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:49.189745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.08482","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9100689b0de1d2ce0da61fe5c46af7344ef9ff51944f807a11302265d10e6a9","sha256:e58df6393c2ef6ab932e800893ba53afca7f7cbba0c99a26b6bbf975c92b7103"],"state_sha256":"03bef800865f84f68da9e9ea8458f5cc40abc7dac12921f5cb928a141c863cab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p3mVvdW8lEX+p1/CDIg9PBXmG00cfQ1iTFNKVyInUKRtr97ON4Gzwg6UrdsE8G7RTHpCVcEse974yBqoPvKODw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:53:29.814226Z","bundle_sha256":"f69f78f9f8ed0e3013c47852ca3a31ccfd4f0e093e4798ac26add49cf230a812"}}