{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TTONUSZ4WZBUUM5VZREZLJ56RV","short_pith_number":"pith:TTONUSZ4","canonical_record":{"source":{"id":"1912.05075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T01:43:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b8ec8336353625cb0123e91b2aa84cd925d3654707851714c9fe20f0bdb1764","abstract_canon_sha256":"b1b8f2d0da0208918866138a951f1f702c54728a5fd699ab7884b68c98eb4d33"},"schema_version":"1.0"},"canonical_sha256":"9cdcda4b3cb6434a33b5cc4995a7be8d66d39b6bda460bff0b943c36c7d1ad28","source":{"kind":"arxiv","id":"1912.05075","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05075","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05075v1","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05075","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"TTONUSZ4WZBU","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"TTONUSZ4WZBUUM5V","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"TTONUSZ4","created_at":"2026-07-05T00:25:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TTONUSZ4WZBUUM5VZREZLJ56RV","target":"record","payload":{"canonical_record":{"source":{"id":"1912.05075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T01:43:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b8ec8336353625cb0123e91b2aa84cd925d3654707851714c9fe20f0bdb1764","abstract_canon_sha256":"b1b8f2d0da0208918866138a951f1f702c54728a5fd699ab7884b68c98eb4d33"},"schema_version":"1.0"},"canonical_sha256":"9cdcda4b3cb6434a33b5cc4995a7be8d66d39b6bda460bff0b943c36c7d1ad28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:31.725743Z","signature_b64":"+jIWoZ1e5AqIVSAhpc3zN+ls7Ism1eq/kngE8kI252VkqkJK8toC/fyyRKD3V233hVpLbBCUUP0qKR+J/5ZwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cdcda4b3cb6434a33b5cc4995a7be8d66d39b6bda460bff0b943c36c7d1ad28","last_reissued_at":"2026-07-05T00:25:31.725257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:31.725257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.05075","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":"2026-07-05T00:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LlOdMBV5iqvmEtAXRI5GyIf5mOX7yUiHiVBLbodpo3cK/m3u+UQX/7iWc3htfvrG13P9ge4A9s97YbwT45ODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:52:17.223820Z"},"content_sha256":"1d6889fea42955e48267806991f53e7df6aed98b6e966cc2391b7f24c4bb84c0","schema_version":"1.0","event_id":"sha256:1d6889fea42955e48267806991f53e7df6aed98b6e966cc2391b7f24c4bb84c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TTONUSZ4WZBUUM5VZREZLJ56RV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Generative Models for Compositional Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mike Wu, Noah Goodman","submitted_at":"2019-12-11T01:43:56Z","abstract_excerpt":"As deep neural networks become more adept at traditional tasks, many of the most exciting new challenges concern multimodality---observations that combine diverse types, such as image and text. In this paper, we introduce a family of multimodal deep generative models derived from variational bounds on the evidence (data marginal likelihood). As part of our derivation we find that many previous multimodal variational autoencoders used objectives that do not correctly bound the joint marginal likelihood across modalities. We further generalize our objective to work with several types of deep gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05075","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.05075/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":"2026-07-05T00:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06bz/ezYWsv+aw2/PfJezlgs6gEV4oxHlHcoFSEgvZZkW+cAE1BGTz45jSwAMC53shV7OQ6Pb2YqdQah2nmeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:52:17.224879Z"},"content_sha256":"a576149b2603279f2d2e229058c7656f47682a54ce5411d86dfd6030d80b33d6","schema_version":"1.0","event_id":"sha256:a576149b2603279f2d2e229058c7656f47682a54ce5411d86dfd6030d80b33d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTONUSZ4WZBUUM5VZREZLJ56RV/bundle.json","state_url":"https://pith.science/pith/TTONUSZ4WZBUUM5VZREZLJ56RV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTONUSZ4WZBUUM5VZREZLJ56RV/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":"2026-08-13T13:52:17Z","links":{"resolver":"https://pith.science/pith/TTONUSZ4WZBUUM5VZREZLJ56RV","bundle":"https://pith.science/pith/TTONUSZ4WZBUUM5VZREZLJ56RV/bundle.json","state":"https://pith.science/pith/TTONUSZ4WZBUUM5VZREZLJ56RV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTONUSZ4WZBUUM5VZREZLJ56RV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TTONUSZ4WZBUUM5VZREZLJ56RV","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":"b1b8f2d0da0208918866138a951f1f702c54728a5fd699ab7884b68c98eb4d33","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T01:43:56Z","title_canon_sha256":"5b8ec8336353625cb0123e91b2aa84cd925d3654707851714c9fe20f0bdb1764"},"schema_version":"1.0","source":{"id":"1912.05075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05075","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05075v1","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05075","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"TTONUSZ4WZBU","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"TTONUSZ4WZBUUM5V","created_at":"2026-07-05T00:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"TTONUSZ4","created_at":"2026-07-05T00:25:31Z"}],"graph_snapshots":[{"event_id":"sha256:a576149b2603279f2d2e229058c7656f47682a54ce5411d86dfd6030d80b33d6","target":"graph","created_at":"2026-07-05T00:25:31Z","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/1912.05075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As deep neural networks become more adept at traditional tasks, many of the most exciting new challenges concern multimodality---observations that combine diverse types, such as image and text. In this paper, we introduce a family of multimodal deep generative models derived from variational bounds on the evidence (data marginal likelihood). As part of our derivation we find that many previous multimodal variational autoencoders used objectives that do not correctly bound the joint marginal likelihood across modalities. We further generalize our objective to work with several types of deep gen","authors_text":"Mike Wu, Noah Goodman","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T01:43:56Z","title":"Multimodal Generative Models for Compositional Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05075","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":"sha256:1d6889fea42955e48267806991f53e7df6aed98b6e966cc2391b7f24c4bb84c0","target":"record","created_at":"2026-07-05T00:25:31Z","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":"b1b8f2d0da0208918866138a951f1f702c54728a5fd699ab7884b68c98eb4d33","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T01:43:56Z","title_canon_sha256":"5b8ec8336353625cb0123e91b2aa84cd925d3654707851714c9fe20f0bdb1764"},"schema_version":"1.0","source":{"id":"1912.05075","kind":"arxiv","version":1}},"canonical_sha256":"9cdcda4b3cb6434a33b5cc4995a7be8d66d39b6bda460bff0b943c36c7d1ad28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cdcda4b3cb6434a33b5cc4995a7be8d66d39b6bda460bff0b943c36c7d1ad28","first_computed_at":"2026-07-05T00:25:31.725257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:31.725257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+jIWoZ1e5AqIVSAhpc3zN+ls7Ism1eq/kngE8kI252VkqkJK8toC/fyyRKD3V233hVpLbBCUUP0qKR+J/5ZwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:31.725743Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d6889fea42955e48267806991f53e7df6aed98b6e966cc2391b7f24c4bb84c0","sha256:a576149b2603279f2d2e229058c7656f47682a54ce5411d86dfd6030d80b33d6"],"state_sha256":"07c8a6a4734e4c82187c1b5cc98d5a759e44ab71a4a4a3b2455e6e43625b093e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HmINfzeRIICQ6jXjheYkls4GMYlxcn4v8DXlqpCWizppQbr7mbTsP2BLECu4ZsISVyAl2wBoCQgyd3BMh3BnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:52:17.231782Z","bundle_sha256":"2cff42642461d79602d7f182a88ed2458177b73d3776d4e7c828c6a7d0c99647"}}