{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PYKFZVMKOHGM5YDEWHVP4A2AQY","short_pith_number":"pith:PYKFZVMK","canonical_record":{"source":{"id":"2112.06868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T18:29:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d68b9e601d428496498af6b60e7c52fe2953dc405376085bb68b438bbed6f4dd","abstract_canon_sha256":"0dcb0ab9b143c186f6ba0bb22d67b2c1090b789067bf3a272565a34c9e4cae00"},"schema_version":"1.0"},"canonical_sha256":"7e145cd58a71cccee064b1eafe0340861e642d5428060812e2da90b47b6501fb","source":{"kind":"arxiv","id":"2112.06868","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06868","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06868v2","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06868","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"pith_short_12","alias_value":"PYKFZVMKOHGM","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"pith_short_16","alias_value":"PYKFZVMKOHGM5YDE","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"pith_short_8","alias_value":"PYKFZVMK","created_at":"2026-07-05T04:24:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PYKFZVMKOHGM5YDEWHVP4A2AQY","target":"record","payload":{"canonical_record":{"source":{"id":"2112.06868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T18:29:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d68b9e601d428496498af6b60e7c52fe2953dc405376085bb68b438bbed6f4dd","abstract_canon_sha256":"0dcb0ab9b143c186f6ba0bb22d67b2c1090b789067bf3a272565a34c9e4cae00"},"schema_version":"1.0"},"canonical_sha256":"7e145cd58a71cccee064b1eafe0340861e642d5428060812e2da90b47b6501fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:24.106033Z","signature_b64":"+v3/RYlfo/SXUtUVWrOScb6xHFi0gXPtedH9RKbv/ysz3OGdmNzaex9H4V103kyihnaF8LjOFnF93TZs3AM9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e145cd58a71cccee064b1eafe0340861e642d5428060812e2da90b47b6501fb","last_reissued_at":"2026-07-05T04:24:24.105546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:24.105546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.06868","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":"2026-07-05T04:24:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xSHwh8gzSm/IM+zl5JDc9kGZg2lNezDewwvivMLm2HxmG2VkltArcejnW0zC8Zg1ZFfsR1i4r50E2U3TKqiHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:35:09.847368Z"},"content_sha256":"2e2adc6eda373c58e51948298841b2acbe8f67f9850e0381996d9081b0d1ad5e","schema_version":"1.0","event_id":"sha256:2e2adc6eda373c58e51948298841b2acbe8f67f9850e0381996d9081b0d1ad5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PYKFZVMKOHGM5YDEWHVP4A2AQY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrej Risteski, Chenghui Zhou, Frederic Koehler, Viraj Mehta","submitted_at":"2021-12-13T18:29:49Z","abstract_excerpt":"Variational Autoencoders are one of the most commonly used generative models, particularly for image data. A prominent difficulty in training VAEs is data that is supported on a lower-dimensional manifold. Recent work by Dai and Wipf (2020) proposes a two-stage training algorithm for VAEs, based on a conjecture that in standard VAE training the generator will converge to a solution with 0 variance which is correctly supported on the ground truth manifold. They gave partial support for that conjecture by showing that some optima of the VAE loss do satisfy this property, but did not analyze the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06868","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/2112.06868/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":"2026-07-05T04:24:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ViFDHvMbmi5oDoJovaj9gAEK0+/WHC1vUtI5xxWL1+gq0n5ZLSgeWEihJFtYz7zUQ2UPmxU2ysvf5buaUmrmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:35:09.847876Z"},"content_sha256":"2cefb225853f1a46ec43351046c19a5349d14061ce5b2b9dff3cd49d214ef7da","schema_version":"1.0","event_id":"sha256:2cefb225853f1a46ec43351046c19a5349d14061ce5b2b9dff3cd49d214ef7da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYKFZVMKOHGM5YDEWHVP4A2AQY/bundle.json","state_url":"https://pith.science/pith/PYKFZVMKOHGM5YDEWHVP4A2AQY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYKFZVMKOHGM5YDEWHVP4A2AQY/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":"2026-08-20T22:35:09Z","links":{"resolver":"https://pith.science/pith/PYKFZVMKOHGM5YDEWHVP4A2AQY","bundle":"https://pith.science/pith/PYKFZVMKOHGM5YDEWHVP4A2AQY/bundle.json","state":"https://pith.science/pith/PYKFZVMKOHGM5YDEWHVP4A2AQY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYKFZVMKOHGM5YDEWHVP4A2AQY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PYKFZVMKOHGM5YDEWHVP4A2AQY","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":"0dcb0ab9b143c186f6ba0bb22d67b2c1090b789067bf3a272565a34c9e4cae00","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T18:29:49Z","title_canon_sha256":"d68b9e601d428496498af6b60e7c52fe2953dc405376085bb68b438bbed6f4dd"},"schema_version":"1.0","source":{"id":"2112.06868","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06868","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06868v2","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06868","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"pith_short_12","alias_value":"PYKFZVMKOHGM","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"pith_short_16","alias_value":"PYKFZVMKOHGM5YDE","created_at":"2026-07-05T04:24:24Z"},{"alias_kind":"pith_short_8","alias_value":"PYKFZVMK","created_at":"2026-07-05T04:24:24Z"}],"graph_snapshots":[{"event_id":"sha256:2cefb225853f1a46ec43351046c19a5349d14061ce5b2b9dff3cd49d214ef7da","target":"graph","created_at":"2026-07-05T04:24:24Z","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/2112.06868/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variational Autoencoders are one of the most commonly used generative models, particularly for image data. A prominent difficulty in training VAEs is data that is supported on a lower-dimensional manifold. Recent work by Dai and Wipf (2020) proposes a two-stage training algorithm for VAEs, based on a conjecture that in standard VAE training the generator will converge to a solution with 0 variance which is correctly supported on the ground truth manifold. They gave partial support for that conjecture by showing that some optima of the VAE loss do satisfy this property, but did not analyze the ","authors_text":"Andrej Risteski, Chenghui Zhou, Frederic Koehler, Viraj Mehta","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T18:29:49Z","title":"Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06868","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":"sha256:2e2adc6eda373c58e51948298841b2acbe8f67f9850e0381996d9081b0d1ad5e","target":"record","created_at":"2026-07-05T04:24:24Z","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":"0dcb0ab9b143c186f6ba0bb22d67b2c1090b789067bf3a272565a34c9e4cae00","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T18:29:49Z","title_canon_sha256":"d68b9e601d428496498af6b60e7c52fe2953dc405376085bb68b438bbed6f4dd"},"schema_version":"1.0","source":{"id":"2112.06868","kind":"arxiv","version":2}},"canonical_sha256":"7e145cd58a71cccee064b1eafe0340861e642d5428060812e2da90b47b6501fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e145cd58a71cccee064b1eafe0340861e642d5428060812e2da90b47b6501fb","first_computed_at":"2026-07-05T04:24:24.105546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:24.105546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+v3/RYlfo/SXUtUVWrOScb6xHFi0gXPtedH9RKbv/ysz3OGdmNzaex9H4V103kyihnaF8LjOFnF93TZs3AM9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:24.106033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06868","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e2adc6eda373c58e51948298841b2acbe8f67f9850e0381996d9081b0d1ad5e","sha256:2cefb225853f1a46ec43351046c19a5349d14061ce5b2b9dff3cd49d214ef7da"],"state_sha256":"d468a60f312f2a1ee804530063162bfd4027e44d7c51a8eaf1c9e4e8072885e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DXHZIRPxA1zvKHGg1gIrCrfQHTbnBbIO6HfW+nSCzSvLZWYhaC0FGj9u4F90TghfOqOlxN3FtdgMMhvHbNRkBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:35:09.851572Z","bundle_sha256":"a9df93cfb52d63039e2fcc1facdf7ecc92ce71a721fb4c3f3dd9a4a5dcac535b"}}