{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JD4QHS3LI2YUCA6UQI6BGCHQ6Y","short_pith_number":"pith:JD4QHS3L","schema_version":"1.0","canonical_sha256":"48f903cb6b46b14103d4823c1308f0f60f30b07e3bd075e65b8ede9ab079b998","source":{"kind":"arxiv","id":"1808.01842","version":1},"attestation_state":"computed","paper":{"title":"Beyond $1/2$-Approximation for Submodular Maximization on Massive Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aida Mousavifar, Amir Zandieh, Ashkan Norouzi-Fard, Jakub Tarnawski, Ola Svensson, Slobodan Mitrovi\\'c","submitted_at":"2018-08-06T12:23:42Z","abstract_excerpt":"Many tasks in machine learning and data mining, such as data diversification, non-parametric learning, kernel machines, clustering etc., require extracting a small but representative summary from a massive dataset. Often, such problems can be posed as maximizing a submodular set function subject to a cardinality constraint. We consider this question in the streaming setting, where elements arrive over time at a fast pace and thus we need to design an efficient, low-memory algorithm. One such method, proposed by Badanidiyuru et al. (2014), always finds a $0.5$-approximate solution. Can this app"},"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":"1808.01842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-06T12:23:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"91dc3837f08a507fb0dc67e9ec3b82e7d24d52cc8ad9fbf80a2ea9f8bce040e0","abstract_canon_sha256":"8342fce06ead0df6a04d655a87a8c6a2b98c2b149fc8534c2a7b37867a7c1cfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:45.131915Z","signature_b64":"TWNS7i2asuFO8T96F7QEY9v7MIoeroIwYRyEXwOPBk7+api4UysBD7cFPLfpZx9N/ZVvFl2nvoVgrte58cB5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48f903cb6b46b14103d4823c1308f0f60f30b07e3bd075e65b8ede9ab079b998","last_reissued_at":"2026-05-18T00:05:45.131340Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:45.131340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond $1/2$-Approximation for Submodular Maximization on Massive Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aida Mousavifar, Amir Zandieh, Ashkan Norouzi-Fard, Jakub Tarnawski, Ola Svensson, Slobodan Mitrovi\\'c","submitted_at":"2018-08-06T12:23:42Z","abstract_excerpt":"Many tasks in machine learning and data mining, such as data diversification, non-parametric learning, kernel machines, clustering etc., require extracting a small but representative summary from a massive dataset. Often, such problems can be posed as maximizing a submodular set function subject to a cardinality constraint. We consider this question in the streaming setting, where elements arrive over time at a fast pace and thus we need to design an efficient, low-memory algorithm. One such method, proposed by Badanidiyuru et al. (2014), always finds a $0.5$-approximate solution. Can this app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01842","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":"1808.01842","created_at":"2026-05-18T00:05:45.131443+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01842v1","created_at":"2026-05-18T00:05:45.131443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01842","created_at":"2026-05-18T00:05:45.131443+00:00"},{"alias_kind":"pith_short_12","alias_value":"JD4QHS3LI2YU","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JD4QHS3LI2YUCA6U","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JD4QHS3L","created_at":"2026-05-18T12:32:31.084164+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/JD4QHS3LI2YUCA6UQI6BGCHQ6Y","json":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y.json","graph_json":"https://pith.science/api/pith-number/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/graph.json","events_json":"https://pith.science/api/pith-number/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/events.json","paper":"https://pith.science/paper/JD4QHS3L"},"agent_actions":{"view_html":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y","download_json":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y.json","view_paper":"https://pith.science/paper/JD4QHS3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01842&json=true","fetch_graph":"https://pith.science/api/pith-number/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/action/storage_attestation","attest_author":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/action/author_attestation","sign_citation":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/action/citation_signature","submit_replication":"https://pith.science/pith/JD4QHS3LI2YUCA6UQI6BGCHQ6Y/action/replication_record"}},"created_at":"2026-05-18T00:05:45.131443+00:00","updated_at":"2026-05-18T00:05:45.131443+00:00"}