{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MHYTIQKWLX67XMWUDZ63XDULDV","short_pith_number":"pith:MHYTIQKW","schema_version":"1.0","canonical_sha256":"61f13441565dfdfbb2d41e7dbb8e8b1d7c7e9e85559c23a645c0c3137388e66b","source":{"kind":"arxiv","id":"2110.00936","version":1},"attestation_state":"computed","paper":{"title":"A Sequential Addressing Subsampling Method for Massive Data Analysis under Memory Constraint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ME","authors_text":"Baishan Guo, Hansheng Wang, Rui Pan, Xuening Zhu, Yingqiu Zhu","submitted_at":"2021-10-03T06:20:47Z","abstract_excerpt":"The emergence of massive data in recent years brings challenges to automatic statistical inference. This is particularly true if the data are too numerous to be read into memory as a whole. Accordingly, new sampling techniques are needed to sample data from a hard drive. In this paper, we propose a sequential addressing subsampling (SAS) method, that can sample data directly from the hard drive. The newly proposed SAS method is time saving in terms of addressing cost compared to that of the random addressing subsampling (RAS) method. Estimators (e.g., the sample mean) based on the SAS subsampl"},"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":"2110.00936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2021-10-03T06:20:47Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"ba36a0422de7aeb0b2654b3257adb66bf90fd0f48f3f1960af975db1c796f49c","abstract_canon_sha256":"59bd89a4d433c56e3eb54e99fc18c915ff63e1ee935d5674e16e9e351805fc8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:50.085307Z","signature_b64":"SpwsZG9YxXAqrv5QYyHNRrzeoy0ALrPxP9bOQrPwdG6nVKirPWMeaEfKkof+ZOQywFo4UUeR4T52F6p9+5zEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61f13441565dfdfbb2d41e7dbb8e8b1d7c7e9e85559c23a645c0c3137388e66b","last_reissued_at":"2026-07-05T03:19:50.084805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:50.084805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sequential Addressing Subsampling Method for Massive Data Analysis under Memory Constraint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ME","authors_text":"Baishan Guo, Hansheng Wang, Rui Pan, Xuening Zhu, Yingqiu Zhu","submitted_at":"2021-10-03T06:20:47Z","abstract_excerpt":"The emergence of massive data in recent years brings challenges to automatic statistical inference. This is particularly true if the data are too numerous to be read into memory as a whole. Accordingly, new sampling techniques are needed to sample data from a hard drive. In this paper, we propose a sequential addressing subsampling (SAS) method, that can sample data directly from the hard drive. The newly proposed SAS method is time saving in terms of addressing cost compared to that of the random addressing subsampling (RAS) method. Estimators (e.g., the sample mean) based on the SAS subsampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00936","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.00936/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.00936","created_at":"2026-07-05T03:19:50.084867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.00936v1","created_at":"2026-07-05T03:19:50.084867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00936","created_at":"2026-07-05T03:19:50.084867+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHYTIQKWLX67","created_at":"2026-07-05T03:19:50.084867+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHYTIQKWLX67XMWU","created_at":"2026-07-05T03:19:50.084867+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHYTIQKW","created_at":"2026-07-05T03:19:50.084867+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/MHYTIQKWLX67XMWUDZ63XDULDV","json":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV.json","graph_json":"https://pith.science/api/pith-number/MHYTIQKWLX67XMWUDZ63XDULDV/graph.json","events_json":"https://pith.science/api/pith-number/MHYTIQKWLX67XMWUDZ63XDULDV/events.json","paper":"https://pith.science/paper/MHYTIQKW"},"agent_actions":{"view_html":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV","download_json":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV.json","view_paper":"https://pith.science/paper/MHYTIQKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.00936&json=true","fetch_graph":"https://pith.science/api/pith-number/MHYTIQKWLX67XMWUDZ63XDULDV/graph.json","fetch_events":"https://pith.science/api/pith-number/MHYTIQKWLX67XMWUDZ63XDULDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV/action/storage_attestation","attest_author":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV/action/author_attestation","sign_citation":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV/action/citation_signature","submit_replication":"https://pith.science/pith/MHYTIQKWLX67XMWUDZ63XDULDV/action/replication_record"}},"created_at":"2026-07-05T03:19:50.084867+00:00","updated_at":"2026-07-05T03:19:50.084867+00:00"}