{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z4S7ADJ47IQ5JSXVM3CV4Y4JQH","short_pith_number":"pith:Z4S7ADJ4","schema_version":"1.0","canonical_sha256":"cf25f00d3cfa21d4caf566c55e638981e85cd333069d4a2977b7de3cf7446e72","source":{"kind":"arxiv","id":"2005.08520","version":1},"attestation_state":"computed","paper":{"title":"Robust Training of Vector Quantized Bottleneck Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian {\\L}a\\'ncucki, Antoine Laurent, Guillaume Sanchez, Hans J.G.A. Dolfing, Jan Chorowski, Nanxin Chen, Ricard Marxer, Sameer Khurana, Tanel Alum\\\"ae","submitted_at":"2020-05-18T08:23:41Z","abstract_excerpt":"In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial representations of speech, applicable to unsupervised voice conversion and reaching state-of-the-art performance on unit discovery tasks. For unsupervised representation learning, they became viable alternatives to continuous latent variable models such as the Variational Auto-Encoder (VAE). However, training deep discrete variable models is challenging, due to th"},"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":"2005.08520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-18T08:23:41Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"977a735ce2ab951f7be203efd4560a6b6dc3ea084301a0eb0b10ec9d1ff941a2","abstract_canon_sha256":"58a0023c7cdc34cf9dc667d126de3dbd4e3a14780a4a2b98fb6026f69bfe909b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:58.362364Z","signature_b64":"HtMP4LYpmn3F/8iy5/K5oqyD4U1YkZklgfdi2urmDOVq/YTOeQyZnP3J9Q+j1J0B2CyQs9poMM95bIIHJ6WADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf25f00d3cfa21d4caf566c55e638981e85cd333069d4a2977b7de3cf7446e72","last_reissued_at":"2026-07-05T09:05:58.361896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:58.361896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Training of Vector Quantized Bottleneck Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian {\\L}a\\'ncucki, Antoine Laurent, Guillaume Sanchez, Hans J.G.A. Dolfing, Jan Chorowski, Nanxin Chen, Ricard Marxer, Sameer Khurana, Tanel Alum\\\"ae","submitted_at":"2020-05-18T08:23:41Z","abstract_excerpt":"In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial representations of speech, applicable to unsupervised voice conversion and reaching state-of-the-art performance on unit discovery tasks. For unsupervised representation learning, they became viable alternatives to continuous latent variable models such as the Variational Auto-Encoder (VAE). However, training deep discrete variable models is challenging, due to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08520","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/2005.08520/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":"2005.08520","created_at":"2026-07-05T09:05:58.361952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08520v1","created_at":"2026-07-05T09:05:58.361952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08520","created_at":"2026-07-05T09:05:58.361952+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4S7ADJ47IQ5","created_at":"2026-07-05T09:05:58.361952+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4S7ADJ47IQ5JSXV","created_at":"2026-07-05T09:05:58.361952+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4S7ADJ4","created_at":"2026-07-05T09:05:58.361952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15282","citing_title":"Exploring In-Image Machine Translation with Real-World Background","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH","json":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH.json","graph_json":"https://pith.science/api/pith-number/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/graph.json","events_json":"https://pith.science/api/pith-number/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/events.json","paper":"https://pith.science/paper/Z4S7ADJ4"},"agent_actions":{"view_html":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH","download_json":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH.json","view_paper":"https://pith.science/paper/Z4S7ADJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08520&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/action/storage_attestation","attest_author":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/action/author_attestation","sign_citation":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/action/citation_signature","submit_replication":"https://pith.science/pith/Z4S7ADJ47IQ5JSXVM3CV4Y4JQH/action/replication_record"}},"created_at":"2026-07-05T09:05:58.361952+00:00","updated_at":"2026-07-05T09:05:58.361952+00:00"}