{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XGOV3FP6UIVDVKDT47AWACOBED","short_pith_number":"pith:XGOV3FP6","canonical_record":{"source":{"id":"1706.03643","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T10:13:00Z","cross_cats_sorted":[],"title_canon_sha256":"17468efade2b98f6f625b0019a95a64d9333709bb341f9f04b56b8e4f6e98440","abstract_canon_sha256":"ed447da39f99f5fbf95905bc7f915e0d8643875af1e36ec4cd09faf0f6b8a2e0"},"schema_version":"1.0"},"canonical_sha256":"b99d5d95fea22a3aa873e7c16009c120cdae2e44767130bfa8510e33ec756731","source":{"kind":"arxiv","id":"1706.03643","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03643","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03643v2","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03643","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"XGOV3FP6UIVD","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XGOV3FP6UIVDVKDT","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XGOV3FP6","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XGOV3FP6UIVDVKDT47AWACOBED","target":"record","payload":{"canonical_record":{"source":{"id":"1706.03643","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T10:13:00Z","cross_cats_sorted":[],"title_canon_sha256":"17468efade2b98f6f625b0019a95a64d9333709bb341f9f04b56b8e4f6e98440","abstract_canon_sha256":"ed447da39f99f5fbf95905bc7f915e0d8643875af1e36ec4cd09faf0f6b8a2e0"},"schema_version":"1.0"},"canonical_sha256":"b99d5d95fea22a3aa873e7c16009c120cdae2e44767130bfa8510e33ec756731","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:35.544671Z","signature_b64":"iGpvdJuLKkLoV2N/E8BzNuuA6qv41NHRZIX3DYhB5gt6zatHmemIflVAfu8Eip3ZVwf6VfbLCcRiNDYKkobwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b99d5d95fea22a3aa873e7c16009c120cdae2e44767130bfa8510e33ec756731","last_reissued_at":"2026-05-18T00:38:35.544290Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:35.544290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.03643","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":"2026-05-18T00:38:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06LOR0xs1PUloEs3SOLkcw8nqa5ZAkv6XMvvc0EKIOdPsRy0ifmT/4gpnKSmlCVFBIEIXqqAc2/jbX0Lg1cvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T07:30:25.140940Z"},"content_sha256":"a8aa6e6d35b44cfbb03f0012659d32f3dc18b87e9f9194551e3de812074172c5","schema_version":"1.0","event_id":"sha256:a8aa6e6d35b44cfbb03f0012659d32f3dc18b87e9f9194551e3de812074172c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XGOV3FP6UIVDVKDT47AWACOBED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tackling Over-pruning in Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anitha Kannan, Li Fei-Fei, Serena Yeung, Yann Dauphin","submitted_at":"2017-06-09T10:13:00Z","abstract_excerpt":"Variational autoencoders (VAE) are directed generative models that learn factorial latent variables. As noted by Burda et al. (2015), these models exhibit the problem of factor over-pruning where a significant number of stochastic factors fail to learn anything and become inactive. This can limit their modeling power and their ability to learn diverse and meaningful latent representations. In this paper, we evaluate several methods to address this problem and propose a more effective model-based approach called the epitomic variational autoencoder (eVAE). The so-called epitomes of this model a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03643","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":""},"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":"2026-05-18T00:38:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IirZWhbwDRwZ36ugHCkw/7Vl2ltRTftqqWc5mRmrZHN/9bVI1HzyWxSOi90s4rOfiGwM7LZ0dYqhSUuSK/CgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T07:30:25.141283Z"},"content_sha256":"d4605f7a6846085f067cf92476d5a7334c93766dd2ba31ebe8bc869f5b181663","schema_version":"1.0","event_id":"sha256:d4605f7a6846085f067cf92476d5a7334c93766dd2ba31ebe8bc869f5b181663"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGOV3FP6UIVDVKDT47AWACOBED/bundle.json","state_url":"https://pith.science/pith/XGOV3FP6UIVDVKDT47AWACOBED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGOV3FP6UIVDVKDT47AWACOBED/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":"2026-05-28T07:30:25Z","links":{"resolver":"https://pith.science/pith/XGOV3FP6UIVDVKDT47AWACOBED","bundle":"https://pith.science/pith/XGOV3FP6UIVDVKDT47AWACOBED/bundle.json","state":"https://pith.science/pith/XGOV3FP6UIVDVKDT47AWACOBED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGOV3FP6UIVDVKDT47AWACOBED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XGOV3FP6UIVDVKDT47AWACOBED","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":"ed447da39f99f5fbf95905bc7f915e0d8643875af1e36ec4cd09faf0f6b8a2e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T10:13:00Z","title_canon_sha256":"17468efade2b98f6f625b0019a95a64d9333709bb341f9f04b56b8e4f6e98440"},"schema_version":"1.0","source":{"id":"1706.03643","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03643","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03643v2","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03643","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"XGOV3FP6UIVD","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XGOV3FP6UIVDVKDT","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XGOV3FP6","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:d4605f7a6846085f067cf92476d5a7334c93766dd2ba31ebe8bc869f5b181663","target":"graph","created_at":"2026-05-18T00:38:35Z","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":"Variational autoencoders (VAE) are directed generative models that learn factorial latent variables. As noted by Burda et al. (2015), these models exhibit the problem of factor over-pruning where a significant number of stochastic factors fail to learn anything and become inactive. This can limit their modeling power and their ability to learn diverse and meaningful latent representations. In this paper, we evaluate several methods to address this problem and propose a more effective model-based approach called the epitomic variational autoencoder (eVAE). The so-called epitomes of this model a","authors_text":"Anitha Kannan, Li Fei-Fei, Serena Yeung, Yann Dauphin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T10:13:00Z","title":"Tackling Over-pruning in Variational Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03643","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:a8aa6e6d35b44cfbb03f0012659d32f3dc18b87e9f9194551e3de812074172c5","target":"record","created_at":"2026-05-18T00:38:35Z","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":"ed447da39f99f5fbf95905bc7f915e0d8643875af1e36ec4cd09faf0f6b8a2e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-09T10:13:00Z","title_canon_sha256":"17468efade2b98f6f625b0019a95a64d9333709bb341f9f04b56b8e4f6e98440"},"schema_version":"1.0","source":{"id":"1706.03643","kind":"arxiv","version":2}},"canonical_sha256":"b99d5d95fea22a3aa873e7c16009c120cdae2e44767130bfa8510e33ec756731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b99d5d95fea22a3aa873e7c16009c120cdae2e44767130bfa8510e33ec756731","first_computed_at":"2026-05-18T00:38:35.544290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:35.544290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iGpvdJuLKkLoV2N/E8BzNuuA6qv41NHRZIX3DYhB5gt6zatHmemIflVAfu8Eip3ZVwf6VfbLCcRiNDYKkobwAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:35.544671Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.03643","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8aa6e6d35b44cfbb03f0012659d32f3dc18b87e9f9194551e3de812074172c5","sha256:d4605f7a6846085f067cf92476d5a7334c93766dd2ba31ebe8bc869f5b181663"],"state_sha256":"c84975e58114a7a5b53be98aef78422759ad176df62b2d1bdd3b09b58722df6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YG3stmHXOYA2uHOS2h5aqT8fneaoDWvZZnuDUGO1sZmp7Qf0zPv7gfkOurEtntY0jP9uW5McJj6uLLZonZWgBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T07:30:25.143162Z","bundle_sha256":"b11bc80f5fa5f48bc5a80e53776f42b7b5adffd42d7fe77aa5a769868124b356"}}