{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DCEXBZBVNW4WGVNURPVLGA4WOX","short_pith_number":"pith:DCEXBZBV","schema_version":"1.0","canonical_sha256":"188970e4356db96355b48beab3039675d37a26411a292a957ca7b2e36761d374","source":{"kind":"arxiv","id":"1802.07382","version":3},"attestation_state":"computed","paper":{"title":"Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Dan Feldman, Elad Tolochinsky, Ibrahim Jubran","submitted_at":"2018-02-21T00:16:53Z","abstract_excerpt":"Coreset (or core-set) is a small weighted \\emph{subset} $Q$ of an input set $P$ with respect to a given \\emph{monotonic} function $f:\\mathbb{R}\\to\\mathbb{R}$ that \\emph{provably} approximates its fitting loss $\\sum_{p\\in P}f(p\\cdot x)$ to \\emph{any} given $x\\in\\mathbb{R}^d$. Using $Q$ we can obtain approximation of $x^*$ that minimizes this loss, by running \\emph{existing} optimization algorithms on $Q$. In this work we provide: (i) A lower bound which proves that there are sets with no coresets smaller than $n=|P|$ for general monotonic loss functions. (ii) A proof that, under a natural assum"},"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":"1802.07382","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T00:16:53Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"64b3bf03ae82fcc98fa9dbd8f58bbede9320048aae9e187a75a76b393337a11a","abstract_canon_sha256":"4ee51b36366c659333a086aebe21e80added97f1552278d1a907e544ba13fe92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:24.051880Z","signature_b64":"VIS3A6+zTa9ITr45SIfU2azazUXWK3zAGMLiGAjxbbq23/GPWSBpGphQmMOiEUgZu0tJHBVJuK+NHCq9cdWsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"188970e4356db96355b48beab3039675d37a26411a292a957ca7b2e36761d374","last_reissued_at":"2026-07-05T03:43:24.051413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:24.051413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Dan Feldman, Elad Tolochinsky, Ibrahim Jubran","submitted_at":"2018-02-21T00:16:53Z","abstract_excerpt":"Coreset (or core-set) is a small weighted \\emph{subset} $Q$ of an input set $P$ with respect to a given \\emph{monotonic} function $f:\\mathbb{R}\\to\\mathbb{R}$ that \\emph{provably} approximates its fitting loss $\\sum_{p\\in P}f(p\\cdot x)$ to \\emph{any} given $x\\in\\mathbb{R}^d$. Using $Q$ we can obtain approximation of $x^*$ that minimizes this loss, by running \\emph{existing} optimization algorithms on $Q$. In this work we provide: (i) A lower bound which proves that there are sets with no coresets smaller than $n=|P|$ for general monotonic loss functions. (ii) A proof that, under a natural assum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07382","kind":"arxiv","version":3},"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/1802.07382/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":"1802.07382","created_at":"2026-07-05T03:43:24.051485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.07382v3","created_at":"2026-07-05T03:43:24.051485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07382","created_at":"2026-07-05T03:43:24.051485+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCEXBZBVNW4W","created_at":"2026-07-05T03:43:24.051485+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCEXBZBVNW4WGVNU","created_at":"2026-07-05T03:43:24.051485+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCEXBZBV","created_at":"2026-07-05T03:43:24.051485+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/DCEXBZBVNW4WGVNURPVLGA4WOX","json":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX.json","graph_json":"https://pith.science/api/pith-number/DCEXBZBVNW4WGVNURPVLGA4WOX/graph.json","events_json":"https://pith.science/api/pith-number/DCEXBZBVNW4WGVNURPVLGA4WOX/events.json","paper":"https://pith.science/paper/DCEXBZBV"},"agent_actions":{"view_html":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX","download_json":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX.json","view_paper":"https://pith.science/paper/DCEXBZBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.07382&json=true","fetch_graph":"https://pith.science/api/pith-number/DCEXBZBVNW4WGVNURPVLGA4WOX/graph.json","fetch_events":"https://pith.science/api/pith-number/DCEXBZBVNW4WGVNURPVLGA4WOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX/action/storage_attestation","attest_author":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX/action/author_attestation","sign_citation":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX/action/citation_signature","submit_replication":"https://pith.science/pith/DCEXBZBVNW4WGVNURPVLGA4WOX/action/replication_record"}},"created_at":"2026-07-05T03:43:24.051485+00:00","updated_at":"2026-07-05T03:43:24.051485+00:00"}