{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3SHOO2AF5NF3QVQJG53NMPI7Q5","short_pith_number":"pith:3SHOO2AF","canonical_record":{"source":{"id":"1711.00937","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T21:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"4b02e7f75d8fb0a0110d8f7284cfeb667abde7dff14bfc151ea589e660ef7aa3","abstract_canon_sha256":"aabf5350c2855ebd931aa448ceb98e96ce9c512bc4a1a3564b8ce30e166d8a4a"},"schema_version":"1.0"},"canonical_sha256":"dc8ee76805eb4bb856093776d63d1f874ed946dd2752342b375e28402104b229","source":{"kind":"arxiv","id":"1711.00937","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00937","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00937v2","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00937","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"pith_short_12","alias_value":"3SHOO2AF5NF3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3SHOO2AF5NF3QVQJ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3SHOO2AF","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3SHOO2AF5NF3QVQJG53NMPI7Q5","target":"record","payload":{"canonical_record":{"source":{"id":"1711.00937","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T21:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"4b02e7f75d8fb0a0110d8f7284cfeb667abde7dff14bfc151ea589e660ef7aa3","abstract_canon_sha256":"aabf5350c2855ebd931aa448ceb98e96ce9c512bc4a1a3564b8ce30e166d8a4a"},"schema_version":"1.0"},"canonical_sha256":"dc8ee76805eb4bb856093776d63d1f874ed946dd2752342b375e28402104b229","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:40.798036Z","signature_b64":"N6CibVAUIRG00C4di8Svb3G7yPDL+ARm0iXbsQHEH4IKihG9gTVWlZIluHpQjTv6NDun3EELOozkXzLgVwFPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc8ee76805eb4bb856093776d63d1f874ed946dd2752342b375e28402104b229","last_reissued_at":"2026-05-18T00:14:40.797504Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:40.797504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.00937","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":"2026-05-18T00:14:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pp9Hev4ix4+EN1FUmu1Edv7xlFxgPdc8oIhdlRr1gAfpfrcivwXXvWsj+w71Zr6LWH7pGGOhTRSCCD11OiU9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:31:57.291088Z"},"content_sha256":"ebe6488042596f3bde3dd893db39538dd78460c46d203a30662d6d1a376d1f09","schema_version":"1.0","event_id":"sha256:ebe6488042596f3bde3dd893db39538dd78460c46d203a30662d6d1a376d1f09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3SHOO2AF5NF3QVQJG53NMPI7Q5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Discrete Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron van den Oord, Koray Kavukcuoglu, Oriol Vinyals","submitted_at":"2017-11-02T21:14:44Z","abstract_excerpt":"Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discrete latent representation, we incorporate ideas from vector quantisation (VQ). Using the VQ method allows the model to circumvent issues of \"posterior colla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00937","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":"2026-05-18T00:14:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smFyzrLEkj55KRkN50BuKPyE6oTLz2umL0VqZRykl9ofuTQOGzOBpD/gahwPr54DXQZFq4ddFbJNvAR9u71xAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:31:57.291460Z"},"content_sha256":"23581f4a87e2254d98ea3b1727946de899c2fe71ece979f1cf96d24dc5a12b25","schema_version":"1.0","event_id":"sha256:23581f4a87e2254d98ea3b1727946de899c2fe71ece979f1cf96d24dc5a12b25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3SHOO2AF5NF3QVQJG53NMPI7Q5/bundle.json","state_url":"https://pith.science/pith/3SHOO2AF5NF3QVQJG53NMPI7Q5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3SHOO2AF5NF3QVQJG53NMPI7Q5/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":"2026-05-28T13:31:57Z","links":{"resolver":"https://pith.science/pith/3SHOO2AF5NF3QVQJG53NMPI7Q5","bundle":"https://pith.science/pith/3SHOO2AF5NF3QVQJG53NMPI7Q5/bundle.json","state":"https://pith.science/pith/3SHOO2AF5NF3QVQJG53NMPI7Q5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3SHOO2AF5NF3QVQJG53NMPI7Q5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3SHOO2AF5NF3QVQJG53NMPI7Q5","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":"aabf5350c2855ebd931aa448ceb98e96ce9c512bc4a1a3564b8ce30e166d8a4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T21:14:44Z","title_canon_sha256":"4b02e7f75d8fb0a0110d8f7284cfeb667abde7dff14bfc151ea589e660ef7aa3"},"schema_version":"1.0","source":{"id":"1711.00937","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00937","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00937v2","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00937","created_at":"2026-05-18T00:14:40Z"},{"alias_kind":"pith_short_12","alias_value":"3SHOO2AF5NF3","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3SHOO2AF5NF3QVQJ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3SHOO2AF","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:23581f4a87e2254d98ea3b1727946de899c2fe71ece979f1cf96d24dc5a12b25","target":"graph","created_at":"2026-05-18T00:14:40Z","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":"Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discrete latent representation, we incorporate ideas from vector quantisation (VQ). Using the VQ method allows the model to circumvent issues of \"posterior colla","authors_text":"Aaron van den Oord, Koray Kavukcuoglu, Oriol Vinyals","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T21:14:44Z","title":"Neural Discrete Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00937","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:ebe6488042596f3bde3dd893db39538dd78460c46d203a30662d6d1a376d1f09","target":"record","created_at":"2026-05-18T00:14:40Z","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":"aabf5350c2855ebd931aa448ceb98e96ce9c512bc4a1a3564b8ce30e166d8a4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T21:14:44Z","title_canon_sha256":"4b02e7f75d8fb0a0110d8f7284cfeb667abde7dff14bfc151ea589e660ef7aa3"},"schema_version":"1.0","source":{"id":"1711.00937","kind":"arxiv","version":2}},"canonical_sha256":"dc8ee76805eb4bb856093776d63d1f874ed946dd2752342b375e28402104b229","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc8ee76805eb4bb856093776d63d1f874ed946dd2752342b375e28402104b229","first_computed_at":"2026-05-18T00:14:40.797504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:40.797504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N6CibVAUIRG00C4di8Svb3G7yPDL+ARm0iXbsQHEH4IKihG9gTVWlZIluHpQjTv6NDun3EELOozkXzLgVwFPDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:40.798036Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00937","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebe6488042596f3bde3dd893db39538dd78460c46d203a30662d6d1a376d1f09","sha256:23581f4a87e2254d98ea3b1727946de899c2fe71ece979f1cf96d24dc5a12b25"],"state_sha256":"5b29a6f0f5f2ee960d2dabce9d59a36f0d7f95498cc8f23a24221519d38dbb4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zGvCcbyhmKA5EMI+SwffhMsBKkCc5RC5pJW3ZkjPzIhUmEhUY3lYh6vKrIT/wlbaquUMzGv63hCZPU5BqlE+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:31:57.293664Z","bundle_sha256":"8928fbce2d781f8228a9047d3c71aaa1d871ce0e64958add44769e6fdcd1a0da"}}