{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:R77XM6ZKVTSX6TCXSYZ6QPTAZ2","short_pith_number":"pith:R77XM6ZK","canonical_record":{"source":{"id":"1807.04629","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2018-07-12T15:08:31Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"83425a6b1886883b0951b3063b4e4c93937b582cd2e73c9c938d911ee2bad889","abstract_canon_sha256":"c21ead5e2d8b0caecd7a1aabcafa0e172e0610a8371e73bb70f42e3e572500e2"},"schema_version":"1.0"},"canonical_sha256":"8fff767b2aace57f4c579633e83e60ce9e6fafd9cd4405b980634461fb432604","source":{"kind":"arxiv","id":"1807.04629","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.04629","created_at":"2026-05-17T23:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"1807.04629v4","created_at":"2026-05-17T23:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04629","created_at":"2026-05-17T23:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"R77XM6ZKVTSX","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"R77XM6ZKVTSX6TCX","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"R77XM6ZK","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:R77XM6ZKVTSX6TCXSYZ6QPTAZ2","target":"record","payload":{"canonical_record":{"source":{"id":"1807.04629","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2018-07-12T15:08:31Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"83425a6b1886883b0951b3063b4e4c93937b582cd2e73c9c938d911ee2bad889","abstract_canon_sha256":"c21ead5e2d8b0caecd7a1aabcafa0e172e0610a8371e73bb70f42e3e572500e2"},"schema_version":"1.0"},"canonical_sha256":"8fff767b2aace57f4c579633e83e60ce9e6fafd9cd4405b980634461fb432604","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:15.911443Z","signature_b64":"EaA9OoR3kzhfub7SSq9nsXMYN/WfXoQwqNuhiWa1hcNKSxiuXsNeePKN2YGxxP2s57+nWlJr45om4feKtQT1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fff767b2aace57f4c579633e83e60ce9e6fafd9cd4405b980634461fb432604","last_reissued_at":"2026-05-17T23:52:15.910642Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:15.910642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.04629","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75WnUNVK8l3+aH155w1wRI50mnJwUGGQYRDwvauZDT2gGfEijrqvKkWmZDY8m7lwk1e/HjpKMUrHNp7TQHJkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:34:23.269811Z"},"content_sha256":"9d04041fb390f05014fb0a1923a9fdcefe16160bc85d66af8cf2071f4b3a0d09","schema_version":"1.0","event_id":"sha256:9d04041fb390f05014fb0a1923a9fdcefe16160bc85d66af8cf2071f4b3a0d09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:R77XM6ZKVTSX6TCXSYZ6QPTAZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Hanwei Wu, Markus Flierl","submitted_at":"2018-07-12T15:08:31Z","abstract_excerpt":"Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation learning for downstream tasks, such as image retrieval. We first describe the VQ-VAE in the context of an information-theoretic framework. We show that the regularization term on the learned representation is determined by the size of the embedded codebook before the training and it affects the generalization ability of the model. As a result, we introduce a hyper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04629","kind":"arxiv","version":4},"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":"2026-05-17T23:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"syKFMEZgXvtPGmyOCKpB1ROtAQaQaoS55iYw5WHMvNzd3o8scfBO0xb90HDmMtIdn3t9jciEM+Hc4w1TbgtdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:34:23.273401Z"},"content_sha256":"c04176dc09c79f5e01795e21d2c6d9c252dc0f271bb4b22fa5d195c0ee45fbed","schema_version":"1.0","event_id":"sha256:c04176dc09c79f5e01795e21d2c6d9c252dc0f271bb4b22fa5d195c0ee45fbed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/bundle.json","state_url":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/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":"2026-08-07T18:34:23Z","links":{"resolver":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2","bundle":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/bundle.json","state":"https://pith.science/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R77XM6ZKVTSX6TCXSYZ6QPTAZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:R77XM6ZKVTSX6TCXSYZ6QPTAZ2","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":"c21ead5e2d8b0caecd7a1aabcafa0e172e0610a8371e73bb70f42e3e572500e2","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2018-07-12T15:08:31Z","title_canon_sha256":"83425a6b1886883b0951b3063b4e4c93937b582cd2e73c9c938d911ee2bad889"},"schema_version":"1.0","source":{"id":"1807.04629","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.04629","created_at":"2026-05-17T23:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"1807.04629v4","created_at":"2026-05-17T23:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04629","created_at":"2026-05-17T23:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"R77XM6ZKVTSX","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"R77XM6ZKVTSX6TCX","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"R77XM6ZK","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:c04176dc09c79f5e01795e21d2c6d9c252dc0f271bb4b22fa5d195c0ee45fbed","target":"graph","created_at":"2026-05-17T23:52:15Z","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":"Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation learning for downstream tasks, such as image retrieval. We first describe the VQ-VAE in the context of an information-theoretic framework. We show that the regularization term on the learned representation is determined by the size of the embedded codebook before the training and it affects the generalization ability of the model. As a result, we introduce a hyper","authors_text":"Hanwei Wu, Markus Flierl","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2018-07-12T15:08:31Z","title":"Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04629","kind":"arxiv","version":4},"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":"sha256:9d04041fb390f05014fb0a1923a9fdcefe16160bc85d66af8cf2071f4b3a0d09","target":"record","created_at":"2026-05-17T23:52:15Z","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":"c21ead5e2d8b0caecd7a1aabcafa0e172e0610a8371e73bb70f42e3e572500e2","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2018-07-12T15:08:31Z","title_canon_sha256":"83425a6b1886883b0951b3063b4e4c93937b582cd2e73c9c938d911ee2bad889"},"schema_version":"1.0","source":{"id":"1807.04629","kind":"arxiv","version":4}},"canonical_sha256":"8fff767b2aace57f4c579633e83e60ce9e6fafd9cd4405b980634461fb432604","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fff767b2aace57f4c579633e83e60ce9e6fafd9cd4405b980634461fb432604","first_computed_at":"2026-05-17T23:52:15.910642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:15.910642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EaA9OoR3kzhfub7SSq9nsXMYN/WfXoQwqNuhiWa1hcNKSxiuXsNeePKN2YGxxP2s57+nWlJr45om4feKtQT1Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:15.911443Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.04629","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d04041fb390f05014fb0a1923a9fdcefe16160bc85d66af8cf2071f4b3a0d09","sha256:c04176dc09c79f5e01795e21d2c6d9c252dc0f271bb4b22fa5d195c0ee45fbed"],"state_sha256":"96fe11ec76c00a8779511c76faefcf3c54ac159f77c8d2dbe1ba8d19c61840b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FBhkkxO2V31i+O75wvpPMX1kOD+tR1vj9YQAE1jC+xV3QI4U5izLvS1RiW3+EfKn8HKtt3Y8UpE4FH3g1i8dAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:34:23.289272Z","bundle_sha256":"e43f7be72921cc9f0a517ac776c69de469040aa587e130c5b20a6dcbb310132a"}}