{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NADABC5SYCEP5RN7IYNEW2U4PY","short_pith_number":"pith:NADABC5S","schema_version":"1.0","canonical_sha256":"6806008bb2c088fec5bf461a4b6a9c7e246d25088f398c2c5a7606c9650b00cf","source":{"kind":"arxiv","id":"2201.10547","version":3},"attestation_state":"computed","paper":{"title":"Optimal Data Selection: An Online Distributed View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Anastasios Angelopoulos, Mariel Werner, Michael I. Jordan, Stephen Bates","submitted_at":"2022-01-25T18:56:16Z","abstract_excerpt":"The blessing of ubiquitous data also comes with a curse: the communication, storage, and labeling of massive, mostly redundant datasets. We seek to solve this problem at its core, collecting only valuable data and throwing out the rest via submodular maximization. Specifically, we develop algorithms for the online and distributed version of the problem, where data selection occurs in an uncoordinated fashion across multiple data streams. We design a general and flexible core selection routine for our algorithms which, given any stream of data, any assessment of its value, and any formulation o"},"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":"2201.10547","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T18:56:16Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"4bdf4fcc5aa3b65eaa1d86e8718b222b418bbbdee004c0bb4e047422ede38342","abstract_canon_sha256":"c0d78feeb2e93961f47caf2f18ea8804e0db1e333b0a32997c3164c7f14a5671"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:17.585128Z","signature_b64":"IUwipHX3i+Th6ehf2Uu5n4FzCscOp9Rp4aP5Y1hFiZ8DH9sBusVLh+1zY/IJrbpby7crwx+wOBJdt/o/4BDXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6806008bb2c088fec5bf461a4b6a9c7e246d25088f398c2c5a7606c9650b00cf","last_reissued_at":"2026-07-05T07:24:17.584565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:17.584565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Data Selection: An Online Distributed View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Anastasios Angelopoulos, Mariel Werner, Michael I. Jordan, Stephen Bates","submitted_at":"2022-01-25T18:56:16Z","abstract_excerpt":"The blessing of ubiquitous data also comes with a curse: the communication, storage, and labeling of massive, mostly redundant datasets. We seek to solve this problem at its core, collecting only valuable data and throwing out the rest via submodular maximization. Specifically, we develop algorithms for the online and distributed version of the problem, where data selection occurs in an uncoordinated fashion across multiple data streams. We design a general and flexible core selection routine for our algorithms which, given any stream of data, any assessment of its value, and any formulation o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10547","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/2201.10547/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":"2201.10547","created_at":"2026-07-05T07:24:17.584634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10547v3","created_at":"2026-07-05T07:24:17.584634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10547","created_at":"2026-07-05T07:24:17.584634+00:00"},{"alias_kind":"pith_short_12","alias_value":"NADABC5SYCEP","created_at":"2026-07-05T07:24:17.584634+00:00"},{"alias_kind":"pith_short_16","alias_value":"NADABC5SYCEP5RN7","created_at":"2026-07-05T07:24:17.584634+00:00"},{"alias_kind":"pith_short_8","alias_value":"NADABC5S","created_at":"2026-07-05T07:24:17.584634+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/NADABC5SYCEP5RN7IYNEW2U4PY","json":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY.json","graph_json":"https://pith.science/api/pith-number/NADABC5SYCEP5RN7IYNEW2U4PY/graph.json","events_json":"https://pith.science/api/pith-number/NADABC5SYCEP5RN7IYNEW2U4PY/events.json","paper":"https://pith.science/paper/NADABC5S"},"agent_actions":{"view_html":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY","download_json":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY.json","view_paper":"https://pith.science/paper/NADABC5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10547&json=true","fetch_graph":"https://pith.science/api/pith-number/NADABC5SYCEP5RN7IYNEW2U4PY/graph.json","fetch_events":"https://pith.science/api/pith-number/NADABC5SYCEP5RN7IYNEW2U4PY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/action/storage_attestation","attest_author":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/action/author_attestation","sign_citation":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/action/citation_signature","submit_replication":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/action/replication_record"}},"created_at":"2026-07-05T07:24:17.584634+00:00","updated_at":"2026-07-05T07:24:17.584634+00:00"}