{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TBRA4OIWIL2W5WQU7HQJXFKEBX","short_pith_number":"pith:TBRA4OIW","schema_version":"1.0","canonical_sha256":"98620e391642f56eda14f9e09b95440df4457a6f6c08a831ef1a8a96809593c8","source":{"kind":"arxiv","id":"2208.06218","version":1},"attestation_state":"computed","paper":{"title":"A sub-sampling algorithm preventing outliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"stat.ME","authors_text":"C. Tommasi, E. Pesce, L. Deldossi","submitted_at":"2022-08-12T11:03:57Z","abstract_excerpt":"Nowadays, in many different fields, massive data are available and for several reasons, it might be convenient to analyze just a subset of the data. The application of the D-optimality criterion can be helpful to optimally select a subsample of observations. However, it is well known that D-optimal support points lie on the boundary of the design space and if they go hand in hand with extreme response values, they can have a severe influence on the estimated linear model (leverage points with high influence). To overcome this problem, firstly, we propose an unsupervised exchange procedure that"},"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":"2208.06218","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2022-08-12T11:03:57Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"06f02cc5e776c131e5c35fd0cc87458f2e98f79c118af2600e5b3b31891c4388","abstract_canon_sha256":"ec4667be281cabce29bcf081315256210ef5452d29e8e950291e33cbf970dd9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:02.548575Z","signature_b64":"ckp9A9Q8LdJBpN2TAYT6enwvhvpbRE+gmGMuWVGq7de2dSCVZRCszkI0105bq+hXI+faz1KnSXb2sMDDPoLLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98620e391642f56eda14f9e09b95440df4457a6f6c08a831ef1a8a96809593c8","last_reissued_at":"2026-07-05T04:48:02.548208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:02.548208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A sub-sampling algorithm preventing outliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"stat.ME","authors_text":"C. Tommasi, E. Pesce, L. Deldossi","submitted_at":"2022-08-12T11:03:57Z","abstract_excerpt":"Nowadays, in many different fields, massive data are available and for several reasons, it might be convenient to analyze just a subset of the data. The application of the D-optimality criterion can be helpful to optimally select a subsample of observations. However, it is well known that D-optimal support points lie on the boundary of the design space and if they go hand in hand with extreme response values, they can have a severe influence on the estimated linear model (leverage points with high influence). To overcome this problem, firstly, we propose an unsupervised exchange procedure that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06218","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/2208.06218/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":"2208.06218","created_at":"2026-07-05T04:48:02.548264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.06218v1","created_at":"2026-07-05T04:48:02.548264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06218","created_at":"2026-07-05T04:48:02.548264+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBRA4OIWIL2W","created_at":"2026-07-05T04:48:02.548264+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBRA4OIWIL2W5WQU","created_at":"2026-07-05T04:48:02.548264+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBRA4OIW","created_at":"2026-07-05T04:48:02.548264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03126","citing_title":"A Robust Machine Learned Interatomic Potential for Nb: Collision Cascade Simulations with accurate Defect Configurations","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX","json":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX.json","graph_json":"https://pith.science/api/pith-number/TBRA4OIWIL2W5WQU7HQJXFKEBX/graph.json","events_json":"https://pith.science/api/pith-number/TBRA4OIWIL2W5WQU7HQJXFKEBX/events.json","paper":"https://pith.science/paper/TBRA4OIW"},"agent_actions":{"view_html":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX","download_json":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX.json","view_paper":"https://pith.science/paper/TBRA4OIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.06218&json=true","fetch_graph":"https://pith.science/api/pith-number/TBRA4OIWIL2W5WQU7HQJXFKEBX/graph.json","fetch_events":"https://pith.science/api/pith-number/TBRA4OIWIL2W5WQU7HQJXFKEBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX/action/storage_attestation","attest_author":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX/action/author_attestation","sign_citation":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX/action/citation_signature","submit_replication":"https://pith.science/pith/TBRA4OIWIL2W5WQU7HQJXFKEBX/action/replication_record"}},"created_at":"2026-07-05T04:48:02.548264+00:00","updated_at":"2026-07-05T04:48:02.548264+00:00"}