{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VTYHH3LBYGAVRXHFXIBVPCNMJQ","short_pith_number":"pith:VTYHH3LB","schema_version":"1.0","canonical_sha256":"acf073ed61c18158dce5ba035789ac4c055e04f80eeec1bffc11c581ce51a41e","source":{"kind":"arxiv","id":"2004.12585","version":2},"attestation_state":"computed","paper":{"title":"A Batch Normalized Inference Network Keeps the KL Vanishing Away","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dapeng Wu, Jianlin Su, Qile Zhu, Wei Bi, Xiaojiang Liu, Xiaolin Li, Xiyao Ma","submitted_at":"2020-04-27T05:20:01Z","abstract_excerpt":"Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when paired with strong autoregressive decoders, VAE often converges to a degenerated local optimum known as \"posterior collapse\". Previous approaches consider the Kullback Leibler divergence (KL) individual for each datapoint. We propose to let the KL follow a distribution across the whole dataset, and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.12585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-27T05:20:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"25eeff6c4ac20281aaf50b655611a72097dad7cdc6cc50a01c09b6458b15f0b3","abstract_canon_sha256":"f41fb53b822132702816d2ea5c0c230d86ce0912357db9d8dba9ffa3330a2ff8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:54.873087Z","signature_b64":"V8NZKQJXeXqff7i9lKxdI/9NA9vKAe7KqehTRoAunkwvQvSFNFyZGJ2XqVjhPdMMWc8Hp/Ui2mBxN/oitTX/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acf073ed61c18158dce5ba035789ac4c055e04f80eeec1bffc11c581ce51a41e","last_reissued_at":"2026-07-05T01:06:54.872626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:54.872626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Batch Normalized Inference Network Keeps the KL Vanishing Away","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dapeng Wu, Jianlin Su, Qile Zhu, Wei Bi, Xiaojiang Liu, Xiaolin Li, Xiyao Ma","submitted_at":"2020-04-27T05:20:01Z","abstract_excerpt":"Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when paired with strong autoregressive decoders, VAE often converges to a degenerated local optimum known as \"posterior collapse\". Previous approaches consider the Kullback Leibler divergence (KL) individual for each datapoint. We propose to let the KL follow a distribution across the whole dataset, and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12585","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/2004.12585/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.12585","created_at":"2026-07-05T01:06:54.872698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12585v2","created_at":"2026-07-05T01:06:54.872698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12585","created_at":"2026-07-05T01:06:54.872698+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTYHH3LBYGAV","created_at":"2026-07-05T01:06:54.872698+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTYHH3LBYGAVRXHF","created_at":"2026-07-05T01:06:54.872698+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTYHH3LB","created_at":"2026-07-05T01:06:54.872698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ","json":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ.json","graph_json":"https://pith.science/api/pith-number/VTYHH3LBYGAVRXHFXIBVPCNMJQ/graph.json","events_json":"https://pith.science/api/pith-number/VTYHH3LBYGAVRXHFXIBVPCNMJQ/events.json","paper":"https://pith.science/paper/VTYHH3LB"},"agent_actions":{"view_html":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ","download_json":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ.json","view_paper":"https://pith.science/paper/VTYHH3LB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12585&json=true","fetch_graph":"https://pith.science/api/pith-number/VTYHH3LBYGAVRXHFXIBVPCNMJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VTYHH3LBYGAVRXHFXIBVPCNMJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ/action/storage_attestation","attest_author":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ/action/author_attestation","sign_citation":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ/action/citation_signature","submit_replication":"https://pith.science/pith/VTYHH3LBYGAVRXHFXIBVPCNMJQ/action/replication_record"}},"created_at":"2026-07-05T01:06:54.872698+00:00","updated_at":"2026-07-05T01:06:54.872698+00:00"}