{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:P6D75SXPJQXE757C74V2QLTHPH","short_pith_number":"pith:P6D75SXP","schema_version":"1.0","canonical_sha256":"7f87fecaef4c2e4ff7e2ff2ba82e6779e47e38dd33217256638e834cf58698aa","source":{"kind":"arxiv","id":"2110.08212","version":2},"attestation_state":"computed","paper":{"title":"NNK-Means: Data summarization using dictionary learning with non-negative kernel regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio Ortega, Sarath Shekkizhar","submitted_at":"2021-10-15T17:17:55Z","abstract_excerpt":"An increasing number of systems are being designed by gathering significant amounts of data and then optimizing the system parameters directly using the obtained data. Often this is done without analyzing the dataset structure. As task complexity, data size, and parameters all increase to millions or even billions, data summarization is becoming a major challenge. In this work, we investigate data summarization via dictionary learning~(DL), leveraging the properties of recently introduced non-negative kernel regression (NNK) graphs. Our proposed NNK-Means, unlike previous DL techniques, such a"},"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":"2110.08212","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T17:17:55Z","cross_cats_sorted":[],"title_canon_sha256":"ff643a0f0edcf437bc76662a1d1f73a86910d3c11a59f985ff82d62e80b27cf6","abstract_canon_sha256":"7e26058137aa8d861d50a048aace8458fd0826d49ddb4f5ba1c1f4ef89537b9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:11.283068Z","signature_b64":"+ExthWr1lpj2ZkU8r9liYU/MJHAaFuczqyjMcS7qiuN/kLgvQtTHN0eMAhh+MYpjRnteVb5s5bKWFN/r0w87Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f87fecaef4c2e4ff7e2ff2ba82e6779e47e38dd33217256638e834cf58698aa","last_reissued_at":"2026-07-05T04:31:11.282629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:11.282629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NNK-Means: Data summarization using dictionary learning with non-negative kernel regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio Ortega, Sarath Shekkizhar","submitted_at":"2021-10-15T17:17:55Z","abstract_excerpt":"An increasing number of systems are being designed by gathering significant amounts of data and then optimizing the system parameters directly using the obtained data. Often this is done without analyzing the dataset structure. As task complexity, data size, and parameters all increase to millions or even billions, data summarization is becoming a major challenge. In this work, we investigate data summarization via dictionary learning~(DL), leveraging the properties of recently introduced non-negative kernel regression (NNK) graphs. Our proposed NNK-Means, unlike previous DL techniques, such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08212","kind":"arxiv","version":2},"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/2110.08212/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":"2110.08212","created_at":"2026-07-05T04:31:11.282686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08212v2","created_at":"2026-07-05T04:31:11.282686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08212","created_at":"2026-07-05T04:31:11.282686+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6D75SXPJQXE","created_at":"2026-07-05T04:31:11.282686+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6D75SXPJQXE757C","created_at":"2026-07-05T04:31:11.282686+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6D75SXP","created_at":"2026-07-05T04:31:11.282686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01541","citing_title":"Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH","json":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH.json","graph_json":"https://pith.science/api/pith-number/P6D75SXPJQXE757C74V2QLTHPH/graph.json","events_json":"https://pith.science/api/pith-number/P6D75SXPJQXE757C74V2QLTHPH/events.json","paper":"https://pith.science/paper/P6D75SXP"},"agent_actions":{"view_html":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH","download_json":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH.json","view_paper":"https://pith.science/paper/P6D75SXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08212&json=true","fetch_graph":"https://pith.science/api/pith-number/P6D75SXPJQXE757C74V2QLTHPH/graph.json","fetch_events":"https://pith.science/api/pith-number/P6D75SXPJQXE757C74V2QLTHPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH/action/storage_attestation","attest_author":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH/action/author_attestation","sign_citation":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH/action/citation_signature","submit_replication":"https://pith.science/pith/P6D75SXPJQXE757C74V2QLTHPH/action/replication_record"}},"created_at":"2026-07-05T04:31:11.282686+00:00","updated_at":"2026-07-05T04:31:11.282686+00:00"}