{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZRRL35QKZRUORMVB4JS2SHFRW","short_pith_number":"pith:FZRRL35Q","schema_version":"1.0","canonical_sha256":"2e6315efb056634745950f132d48e58d8febb6d6f4ed27d458e6fe8f9ca6e317","source":{"kind":"arxiv","id":"2301.09880","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Bilevel Coreset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Renjie Pi, Tong Zhang, Weizhong Zhang, Xiao Zhou, Yong Lin","submitted_at":"2023-01-24T09:37:00Z","abstract_excerpt":"The goal of coreset selection in supervised learning is to produce a weighted subset of data, so that training only on the subset achieves similar performance as training on the entire dataset. Existing methods achieved promising results in resource-constrained scenarios such as continual learning and streaming. However, most of the existing algorithms are limited to traditional machine learning models. A few algorithms that can handle large models adopt greedy search approaches due to the difficulty in solving the discrete subset selection problem, which is computationally costly when coreset"},"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":"2301.09880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T09:37:00Z","cross_cats_sorted":[],"title_canon_sha256":"937c460e295500df3dfc2a151a41fad03466afc2d1cef81e2d93d5fd3481d891","abstract_canon_sha256":"788a3da39bc188dcf5ac0a5e0932accbe330ff6dc5ca160804758d7640e3a812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:35.370878Z","signature_b64":"FHR18G37kDIPsrScbUj1t51lY3wfyOgjQRVCahu/CTwCg0mmuOITjIz5jKOSo+WQ3XrmgaA/TbByVFd4IAA1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6315efb056634745950f132d48e58d8febb6d6f4ed27d458e6fe8f9ca6e317","last_reissued_at":"2026-07-05T05:35:35.370373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:35.370373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Bilevel Coreset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Renjie Pi, Tong Zhang, Weizhong Zhang, Xiao Zhou, Yong Lin","submitted_at":"2023-01-24T09:37:00Z","abstract_excerpt":"The goal of coreset selection in supervised learning is to produce a weighted subset of data, so that training only on the subset achieves similar performance as training on the entire dataset. Existing methods achieved promising results in resource-constrained scenarios such as continual learning and streaming. However, most of the existing algorithms are limited to traditional machine learning models. A few algorithms that can handle large models adopt greedy search approaches due to the difficulty in solving the discrete subset selection problem, which is computationally costly when coreset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09880","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.09880/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":"2301.09880","created_at":"2026-07-05T05:35:35.370443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.09880v1","created_at":"2026-07-05T05:35:35.370443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09880","created_at":"2026-07-05T05:35:35.370443+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZRRL35QKZRU","created_at":"2026-07-05T05:35:35.370443+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZRRL35QKZRUORMV","created_at":"2026-07-05T05:35:35.370443+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZRRL35Q","created_at":"2026-07-05T05:35:35.370443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07673","citing_title":"How Benchmark Prediction from Fewer Data Misses the Mark","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW","json":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW.json","graph_json":"https://pith.science/api/pith-number/FZRRL35QKZRUORMVB4JS2SHFRW/graph.json","events_json":"https://pith.science/api/pith-number/FZRRL35QKZRUORMVB4JS2SHFRW/events.json","paper":"https://pith.science/paper/FZRRL35Q"},"agent_actions":{"view_html":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW","download_json":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW.json","view_paper":"https://pith.science/paper/FZRRL35Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.09880&json=true","fetch_graph":"https://pith.science/api/pith-number/FZRRL35QKZRUORMVB4JS2SHFRW/graph.json","fetch_events":"https://pith.science/api/pith-number/FZRRL35QKZRUORMVB4JS2SHFRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW/action/storage_attestation","attest_author":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW/action/author_attestation","sign_citation":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW/action/citation_signature","submit_replication":"https://pith.science/pith/FZRRL35QKZRUORMVB4JS2SHFRW/action/replication_record"}},"created_at":"2026-07-05T05:35:35.370443+00:00","updated_at":"2026-07-05T05:35:35.370443+00:00"}