{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GGIHFDM63ODFG6RODLFTR6LVWE","short_pith_number":"pith:GGIHFDM6","schema_version":"1.0","canonical_sha256":"3190728d9edb86537a2e1acb38f975b11dc708205981329f941e46a048ba0b34","source":{"kind":"arxiv","id":"1709.03708","version":1},"attestation_state":"computed","paper":{"title":"PQk-means: Billion-scale Clustering for Product-quantized Codes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Keisuke Ogaki, Kiyoharu Aizawa, Toshihiko Yamasaki, Yusuke Matsui","submitted_at":"2017-09-12T07:00:18Z","abstract_excerpt":"Data clustering is a fundamental operation in data analysis. For handling large-scale data, the standard k-means clustering method is not only slow, but also memory-inefficient. We propose an efficient clustering method for billion-scale feature vectors, called PQk-means. By first compressing input vectors into short product-quantized (PQ) codes, PQk-means achieves fast and memory-efficient clustering, even for high-dimensional vectors. Similar to k-means, PQk-means repeats the assignment and update steps, both of which can be performed in the PQ-code domain. Experimental results show that eve"},"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":"1709.03708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-12T07:00:18Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"ca4843e98a4fb89fb6cb11f444ae01d23f55c8383fc64c8eadf851806873dbce","abstract_canon_sha256":"f5ed05801e2a588765e62e37984c61ff10751ed0c8c1506ba40077af5e305342"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:29.727294Z","signature_b64":"A+2FRrQnTaKv0TSFHnzUxNIGv8WWdykpUh+nnsrl/KUh2dSfGp3sOtkGZ7dYUOKFnx+FQey1WzWI8hS5W0cDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3190728d9edb86537a2e1acb38f975b11dc708205981329f941e46a048ba0b34","last_reissued_at":"2026-05-18T00:35:29.726577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:29.726577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PQk-means: Billion-scale Clustering for Product-quantized Codes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Keisuke Ogaki, Kiyoharu Aizawa, Toshihiko Yamasaki, Yusuke Matsui","submitted_at":"2017-09-12T07:00:18Z","abstract_excerpt":"Data clustering is a fundamental operation in data analysis. For handling large-scale data, the standard k-means clustering method is not only slow, but also memory-inefficient. We propose an efficient clustering method for billion-scale feature vectors, called PQk-means. By first compressing input vectors into short product-quantized (PQ) codes, PQk-means achieves fast and memory-efficient clustering, even for high-dimensional vectors. Similar to k-means, PQk-means repeats the assignment and update steps, both of which can be performed in the PQ-code domain. Experimental results show that eve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03708","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":""},"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":"1709.03708","created_at":"2026-05-18T00:35:29.726682+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.03708v1","created_at":"2026-05-18T00:35:29.726682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03708","created_at":"2026-05-18T00:35:29.726682+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGIHFDM63ODF","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGIHFDM63ODFG6RO","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGIHFDM6","created_at":"2026-05-18T12:31:15.632608+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/GGIHFDM63ODFG6RODLFTR6LVWE","json":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE.json","graph_json":"https://pith.science/api/pith-number/GGIHFDM63ODFG6RODLFTR6LVWE/graph.json","events_json":"https://pith.science/api/pith-number/GGIHFDM63ODFG6RODLFTR6LVWE/events.json","paper":"https://pith.science/paper/GGIHFDM6"},"agent_actions":{"view_html":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE","download_json":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE.json","view_paper":"https://pith.science/paper/GGIHFDM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.03708&json=true","fetch_graph":"https://pith.science/api/pith-number/GGIHFDM63ODFG6RODLFTR6LVWE/graph.json","fetch_events":"https://pith.science/api/pith-number/GGIHFDM63ODFG6RODLFTR6LVWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE/action/storage_attestation","attest_author":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE/action/author_attestation","sign_citation":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE/action/citation_signature","submit_replication":"https://pith.science/pith/GGIHFDM63ODFG6RODLFTR6LVWE/action/replication_record"}},"created_at":"2026-05-18T00:35:29.726682+00:00","updated_at":"2026-05-18T00:35:29.726682+00:00"}