{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:57PJXYZ5V54QDA7FCNP6N6KYDO","short_pith_number":"pith:57PJXYZ5","schema_version":"1.0","canonical_sha256":"efde9be33daf790183e5135fe6f9581b8ab3dbc3611f4a011c28d46a298beced","source":{"kind":"arxiv","id":"1808.02083","version":1},"attestation_state":"computed","paper":{"title":"Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.CO","authors_text":"Andrea Giovannucci, Cengiz Pehlevan, Dmitri B. Chklovskii, Victor Minden","submitted_at":"2018-08-06T19:37:56Z","abstract_excerpt":"Big data problems frequently require processing datasets in a streaming fashion, either because all data are available at once but collectively are larger than available memory or because the data intrinsically arrive one data point at a time and must be processed online. Here, we introduce a computationally efficient version of similarity matching, a framework for online dimensionality reduction that incrementally estimates the top K-dimensional principal subspace of streamed data while keeping in memory only the last sample and the current iterate. To assess the performance of our approach, "},"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":"1808.02083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2018-08-06T19:37:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"51ee585b914134368776ca99827b2e25eaa1a2e8f3e20c33366cd9b20a5bfeec","abstract_canon_sha256":"617dd0e0fab45ddd1ca05d96019fc62d9ea56be95bf79149f1cbfa44718fb74f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:47.672714Z","signature_b64":"uYlv9TVvo1lydSgKHu6wBf84dNCqq5SaGQPF+dASYfmkv+1xNjGyve9ulZ4aTkWqcUuDCVtmXKTvaBN8lfZuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efde9be33daf790183e5135fe6f9581b8ab3dbc3611f4a011c28d46a298beced","last_reissued_at":"2026-05-18T00:08:47.672148Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:47.672148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.CO","authors_text":"Andrea Giovannucci, Cengiz Pehlevan, Dmitri B. Chklovskii, Victor Minden","submitted_at":"2018-08-06T19:37:56Z","abstract_excerpt":"Big data problems frequently require processing datasets in a streaming fashion, either because all data are available at once but collectively are larger than available memory or because the data intrinsically arrive one data point at a time and must be processed online. Here, we introduce a computationally efficient version of similarity matching, a framework for online dimensionality reduction that incrementally estimates the top K-dimensional principal subspace of streamed data while keeping in memory only the last sample and the current iterate. To assess the performance of our approach, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02083","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":"1808.02083","created_at":"2026-05-18T00:08:47.672226+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02083v1","created_at":"2026-05-18T00:08:47.672226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02083","created_at":"2026-05-18T00:08:47.672226+00:00"},{"alias_kind":"pith_short_12","alias_value":"57PJXYZ5V54Q","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"57PJXYZ5V54QDA7F","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"57PJXYZ5","created_at":"2026-05-18T12:32:08.215937+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/57PJXYZ5V54QDA7FCNP6N6KYDO","json":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO.json","graph_json":"https://pith.science/api/pith-number/57PJXYZ5V54QDA7FCNP6N6KYDO/graph.json","events_json":"https://pith.science/api/pith-number/57PJXYZ5V54QDA7FCNP6N6KYDO/events.json","paper":"https://pith.science/paper/57PJXYZ5"},"agent_actions":{"view_html":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO","download_json":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO.json","view_paper":"https://pith.science/paper/57PJXYZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02083&json=true","fetch_graph":"https://pith.science/api/pith-number/57PJXYZ5V54QDA7FCNP6N6KYDO/graph.json","fetch_events":"https://pith.science/api/pith-number/57PJXYZ5V54QDA7FCNP6N6KYDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO/action/storage_attestation","attest_author":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO/action/author_attestation","sign_citation":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO/action/citation_signature","submit_replication":"https://pith.science/pith/57PJXYZ5V54QDA7FCNP6N6KYDO/action/replication_record"}},"created_at":"2026-05-18T00:08:47.672226+00:00","updated_at":"2026-05-18T00:08:47.672226+00:00"}