{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:P2STPAL6MOB67J25BI7POXXQQJ","short_pith_number":"pith:P2STPAL6","schema_version":"1.0","canonical_sha256":"7ea537817e6383efa75d0a3ef75ef0824f761d0bc14d44270b52f1f61959727f","source":{"kind":"arxiv","id":"1605.00519","version":1},"attestation_state":"computed","paper":{"title":"Linear-time Outlier Detection via Sensitivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem","submitted_at":"2016-05-02T15:17:02Z","abstract_excerpt":"Outliers are ubiquitous in modern data sets. Distance-based techniques are a popular non-parametric approach to outlier detection as they require no prior assumptions on the data generating distribution and are simple to implement. Scaling these techniques to massive data sets without sacrificing accuracy is a challenging task. We propose a novel algorithm based on the intuition that outliers have a significant influence on the quality of divergence-based clustering solutions. We propose sensitivity - the worst-case impact of a data point on the clustering objective - as a measure of outlierne"},"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":"1605.00519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-02T15:17:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4bf699157abbb0720f93de7c74996821378a08c0dd103f678a5d0733b121e75f","abstract_canon_sha256":"5c3a66f74d8f306b05e22c7937784bb40ac448bd58e89f1e82c68a40a6accac7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:48.443177Z","signature_b64":"HS2geL9/WQFk1LCY97mv+yEHg8ne9swhd3TMNOsBRMw79ZWFQ8ByTn6nCBWtw7lPIMirucR4DGK+FZneInPrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ea537817e6383efa75d0a3ef75ef0824f761d0bc14d44270b52f1f61959727f","last_reissued_at":"2026-05-18T01:15:48.442688Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:48.442688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear-time Outlier Detection via Sensitivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem","submitted_at":"2016-05-02T15:17:02Z","abstract_excerpt":"Outliers are ubiquitous in modern data sets. Distance-based techniques are a popular non-parametric approach to outlier detection as they require no prior assumptions on the data generating distribution and are simple to implement. Scaling these techniques to massive data sets without sacrificing accuracy is a challenging task. We propose a novel algorithm based on the intuition that outliers have a significant influence on the quality of divergence-based clustering solutions. We propose sensitivity - the worst-case impact of a data point on the clustering objective - as a measure of outlierne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.00519","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":"1605.00519","created_at":"2026-05-18T01:15:48.442771+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.00519v1","created_at":"2026-05-18T01:15:48.442771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.00519","created_at":"2026-05-18T01:15:48.442771+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2STPAL6MOB6","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2STPAL6MOB67J25","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2STPAL6","created_at":"2026-05-18T12:30:36.002864+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/P2STPAL6MOB67J25BI7POXXQQJ","json":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ.json","graph_json":"https://pith.science/api/pith-number/P2STPAL6MOB67J25BI7POXXQQJ/graph.json","events_json":"https://pith.science/api/pith-number/P2STPAL6MOB67J25BI7POXXQQJ/events.json","paper":"https://pith.science/paper/P2STPAL6"},"agent_actions":{"view_html":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ","download_json":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ.json","view_paper":"https://pith.science/paper/P2STPAL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.00519&json=true","fetch_graph":"https://pith.science/api/pith-number/P2STPAL6MOB67J25BI7POXXQQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/P2STPAL6MOB67J25BI7POXXQQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ/action/storage_attestation","attest_author":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ/action/author_attestation","sign_citation":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ/action/citation_signature","submit_replication":"https://pith.science/pith/P2STPAL6MOB67J25BI7POXXQQJ/action/replication_record"}},"created_at":"2026-05-18T01:15:48.442771+00:00","updated_at":"2026-05-18T01:15:48.442771+00:00"}