{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P5IL5YSH6AVFNFVMOY3FW6EDDA","short_pith_number":"pith:P5IL5YSH","schema_version":"1.0","canonical_sha256":"7f50bee247f02a5696ac76365b788318310f8f58d03025ccc4677f62c72bb60f","source":{"kind":"arxiv","id":"2306.01244","version":1},"attestation_state":"computed","paper":{"title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baharan Mirzasoleiman, Hao Kang, Yu Yang","submitted_at":"2023-06-02T02:51:08Z","abstract_excerpt":"To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly deep networks. To guarantee convergence to a stationary point of a non-convex function, CREST models the non-convex loss as a series of quadratic functions and extracts a coreset for each quadratic sub-region. In addition, to ensure faster convergence of stochastic gradient methods such as (mini-batch) SGD, CREST iteratively extracts multiple mini-batch corese"},"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":"2306.01244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T02:51:08Z","cross_cats_sorted":[],"title_canon_sha256":"185791fd0a6f211bc0c52d4763ae41e83dd9dc9b9537f9f35ed9e3ef0f05cb66","abstract_canon_sha256":"37cf177cb277219f1bd09c5c9a78c4b91dea183d5300774d70a11ee3a0dc8a6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:39.835473Z","signature_b64":"UFeBVXXgTMDPgtD3ES9JRCoCm2mxfi/Vfu99A+wbIyYr6RWkUrfZ3PjyiRX16KWrzezN6LFpELXTfzgKwljLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f50bee247f02a5696ac76365b788318310f8f58d03025ccc4677f62c72bb60f","last_reissued_at":"2026-07-05T06:16:39.835044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:39.835044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baharan Mirzasoleiman, Hao Kang, Yu Yang","submitted_at":"2023-06-02T02:51:08Z","abstract_excerpt":"To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly deep networks. To guarantee convergence to a stationary point of a non-convex function, CREST models the non-convex loss as a series of quadratic functions and extracts a coreset for each quadratic sub-region. In addition, to ensure faster convergence of stochastic gradient methods such as (mini-batch) SGD, CREST iteratively extracts multiple mini-batch corese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01244","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/2306.01244/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":"2306.01244","created_at":"2026-07-05T06:16:39.835110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01244v1","created_at":"2026-07-05T06:16:39.835110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01244","created_at":"2026-07-05T06:16:39.835110+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5IL5YSH6AVF","created_at":"2026-07-05T06:16:39.835110+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5IL5YSH6AVFNFVM","created_at":"2026-07-05T06:16:39.835110+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5IL5YSH","created_at":"2026-07-05T06:16:39.835110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02332","citing_title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","ref_index":1982,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA","json":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA.json","graph_json":"https://pith.science/api/pith-number/P5IL5YSH6AVFNFVMOY3FW6EDDA/graph.json","events_json":"https://pith.science/api/pith-number/P5IL5YSH6AVFNFVMOY3FW6EDDA/events.json","paper":"https://pith.science/paper/P5IL5YSH"},"agent_actions":{"view_html":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA","download_json":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA.json","view_paper":"https://pith.science/paper/P5IL5YSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01244&json=true","fetch_graph":"https://pith.science/api/pith-number/P5IL5YSH6AVFNFVMOY3FW6EDDA/graph.json","fetch_events":"https://pith.science/api/pith-number/P5IL5YSH6AVFNFVMOY3FW6EDDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA/action/storage_attestation","attest_author":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA/action/author_attestation","sign_citation":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA/action/citation_signature","submit_replication":"https://pith.science/pith/P5IL5YSH6AVFNFVMOY3FW6EDDA/action/replication_record"}},"created_at":"2026-07-05T06:16:39.835110+00:00","updated_at":"2026-07-05T06:16:39.835110+00:00"}