{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YS6ECKWRN3WUYGGFEKWRQ647X4","short_pith_number":"pith:YS6ECKWR","schema_version":"1.0","canonical_sha256":"c4bc412ad16eed4c18c522ad187b9fbf0a4cd4c597f245deffc0f7ff16737e8d","source":{"kind":"arxiv","id":"1805.11063","version":2},"attestation_state":"computed","paper":{"title":"Theory and Experiments on Vector Quantized Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arvind Neelakantan, Ashish Vaswani, Aurko Roy, Niki Parmar","submitted_at":"2018-05-28T17:16:20Z","abstract_excerpt":"Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a surge in interest in discrete latent variable models, however, despite several recent improvements, the training of discrete latent variable models has remained challenging and their performance has mostly failed to match their continuous counterparts. Recent work on vector quantized autoencoders (VQ-VAE) has made substantial progress in this direction, with its perplexity almost matching that of a VAE on datasets such"},"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":"1805.11063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T17:16:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2b8479dcbd959c11182d9dac90ae543de2eecd9c65ef42d3b58da85b08c4067a","abstract_canon_sha256":"e4abded591594449a5506382e586b6a35c3eb07c4d8225eff3e02b21cd159fef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:16.682410Z","signature_b64":"rhxpEObhB8gQQFiY4M00wXGozxDWqAhjwsRyagCgSePO1T/yuTUHfUqZp9zREJ+PpgS+z2wtLqc2qEhbjnloCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4bc412ad16eed4c18c522ad187b9fbf0a4cd4c597f245deffc0f7ff16737e8d","last_reissued_at":"2026-05-18T00:10:16.681966Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:16.681966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theory and Experiments on Vector Quantized Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arvind Neelakantan, Ashish Vaswani, Aurko Roy, Niki Parmar","submitted_at":"2018-05-28T17:16:20Z","abstract_excerpt":"Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a surge in interest in discrete latent variable models, however, despite several recent improvements, the training of discrete latent variable models has remained challenging and their performance has mostly failed to match their continuous counterparts. Recent work on vector quantized autoencoders (VQ-VAE) has made substantial progress in this direction, with its perplexity almost matching that of a VAE on datasets such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11063","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.11063","created_at":"2026-05-18T00:10:16.682042+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11063v2","created_at":"2026-05-18T00:10:16.682042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11063","created_at":"2026-05-18T00:10:16.682042+00:00"},{"alias_kind":"pith_short_12","alias_value":"YS6ECKWRN3WU","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YS6ECKWRN3WUYGGF","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YS6ECKWR","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.05019","citing_title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2309.15505","citing_title":"Finite Scalar Quantization: VQ-VAE Made Simple","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4","json":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4.json","graph_json":"https://pith.science/api/pith-number/YS6ECKWRN3WUYGGFEKWRQ647X4/graph.json","events_json":"https://pith.science/api/pith-number/YS6ECKWRN3WUYGGFEKWRQ647X4/events.json","paper":"https://pith.science/paper/YS6ECKWR"},"agent_actions":{"view_html":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4","download_json":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4.json","view_paper":"https://pith.science/paper/YS6ECKWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11063&json=true","fetch_graph":"https://pith.science/api/pith-number/YS6ECKWRN3WUYGGFEKWRQ647X4/graph.json","fetch_events":"https://pith.science/api/pith-number/YS6ECKWRN3WUYGGFEKWRQ647X4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4/action/storage_attestation","attest_author":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4/action/author_attestation","sign_citation":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4/action/citation_signature","submit_replication":"https://pith.science/pith/YS6ECKWRN3WUYGGFEKWRQ647X4/action/replication_record"}},"created_at":"2026-05-18T00:10:16.682042+00:00","updated_at":"2026-05-18T00:10:16.682042+00:00"}