{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZI5LVV67CS2JEE54PME4DLACN5","short_pith_number":"pith:ZI5LVV67","schema_version":"1.0","canonical_sha256":"ca3abad7df14b49213bc7b09c1ac026f6db71f3e2d0b9e4f682e919774cd173c","source":{"kind":"arxiv","id":"2012.10630","version":4},"attestation_state":"computed","paper":{"title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Durga Sivasubramanian, Ganesh Ramakrishnan, Krishnateja Killamsetty, Rishabh Iyer","submitted_at":"2020-12-19T08:41:34Z","abstract_excerpt":"Large scale machine learning and deep models are extremely data-hungry. Unfortunately, obtaining large amounts of labeled data is expensive, and training state-of-the-art models (with hyperparameter tuning) requires significant computing resources and time. Secondly, real-world data is noisy and imbalanced. As a result, several recent papers try to make the training process more efficient and robust. However, most existing work either focuses on robustness or efficiency, but not both. In this work, we introduce Glister, a GeneraLIzation based data Subset selecTion for Efficient and Robust lear"},"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":"2012.10630","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-19T08:41:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a5206673da92e86e66373474f6cffa487511dd3d0704f9e6a18d7aae081d196","abstract_canon_sha256":"eef3cd4041d26fb78cc787d232d19ed4395f5814b948455c589f791c88a248b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:35.227007Z","signature_b64":"WDo2I91/i1VCYGkHBN3bXLnsrjQSs0ZiLEgAtUmovHzJydo34HtqHhUscR0rubiGrwj6QButX2vn+Zt8wX0CBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3abad7df14b49213bc7b09c1ac026f6db71f3e2d0b9e4f682e919774cd173c","last_reissued_at":"2026-07-05T02:48:35.226498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:35.226498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Durga Sivasubramanian, Ganesh Ramakrishnan, Krishnateja Killamsetty, Rishabh Iyer","submitted_at":"2020-12-19T08:41:34Z","abstract_excerpt":"Large scale machine learning and deep models are extremely data-hungry. Unfortunately, obtaining large amounts of labeled data is expensive, and training state-of-the-art models (with hyperparameter tuning) requires significant computing resources and time. Secondly, real-world data is noisy and imbalanced. As a result, several recent papers try to make the training process more efficient and robust. However, most existing work either focuses on robustness or efficiency, but not both. In this work, we introduce Glister, a GeneraLIzation based data Subset selecTion for Efficient and Robust lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10630","kind":"arxiv","version":4},"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/2012.10630/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":"2012.10630","created_at":"2026-07-05T02:48:35.226564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.10630v4","created_at":"2026-07-05T02:48:35.226564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10630","created_at":"2026-07-05T02:48:35.226564+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZI5LVV67CS2J","created_at":"2026-07-05T02:48:35.226564+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZI5LVV67CS2JEE54","created_at":"2026-07-05T02:48:35.226564+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZI5LVV67","created_at":"2026-07-05T02:48:35.226564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09404","citing_title":"Let the Target Select for Itself: Data Selection via Target-Aligned Paths","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5","json":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5.json","graph_json":"https://pith.science/api/pith-number/ZI5LVV67CS2JEE54PME4DLACN5/graph.json","events_json":"https://pith.science/api/pith-number/ZI5LVV67CS2JEE54PME4DLACN5/events.json","paper":"https://pith.science/paper/ZI5LVV67"},"agent_actions":{"view_html":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5","download_json":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5.json","view_paper":"https://pith.science/paper/ZI5LVV67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.10630&json=true","fetch_graph":"https://pith.science/api/pith-number/ZI5LVV67CS2JEE54PME4DLACN5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZI5LVV67CS2JEE54PME4DLACN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5/action/storage_attestation","attest_author":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5/action/author_attestation","sign_citation":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5/action/citation_signature","submit_replication":"https://pith.science/pith/ZI5LVV67CS2JEE54PME4DLACN5/action/replication_record"}},"created_at":"2026-07-05T02:48:35.226564+00:00","updated_at":"2026-07-05T02:48:35.226564+00:00"}