{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RS4C5KBRTYNOJCJEL6GYUB54J6","short_pith_number":"pith:RS4C5KBR","schema_version":"1.0","canonical_sha256":"8cb82ea8319e1ae489245f8d8a07bc4fa8ecccc37583045918aeaaf608593fea","source":{"kind":"arxiv","id":"2301.13287","version":4},"attestation_state":"computed","paper":{"title":"MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandre V. Evfimievski, Kiran Kate, Krishnateja Killamsetty, Lucian Popa, Rishabh Iyer, Tejaswini Pedapati","submitted_at":"2023-01-30T20:59:30Z","abstract_excerpt":"Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training data. Compared to simple adaptive random subset selection baselines, existing intelligent subset selection approaches are not competitive due to the time-consuming subset selection step, which involves computing model-dependent gradients and feature embeddings and applies greedy maximization of submodular objectives. Our key insight is that removing the reli"},"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":"2301.13287","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T20:59:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f350e166df10d5bc8bd8fd45a6265d264408d2edf121cdcb50df8c374bf1e40","abstract_canon_sha256":"86d7e79b5f1a1694f73fea7f26a1e85def347f5c7b008a86e91f4e5e08e99969"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:30.371015Z","signature_b64":"6fGrqtEj9pq72SyaXDFuTpFO3hSRESJHq5xwT2ra1jPAPqUU/7XCz4U6YK6QohuKSCrSEQrdHJjXAyK6ur7CAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cb82ea8319e1ae489245f8d8a07bc4fa8ecccc37583045918aeaaf608593fea","last_reissued_at":"2026-07-05T06:21:30.370578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:30.370578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandre V. Evfimievski, Kiran Kate, Krishnateja Killamsetty, Lucian Popa, Rishabh Iyer, Tejaswini Pedapati","submitted_at":"2023-01-30T20:59:30Z","abstract_excerpt":"Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training data. Compared to simple adaptive random subset selection baselines, existing intelligent subset selection approaches are not competitive due to the time-consuming subset selection step, which involves computing model-dependent gradients and feature embeddings and applies greedy maximization of submodular objectives. Our key insight is that removing the reli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13287","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/2301.13287/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":"2301.13287","created_at":"2026-07-05T06:21:30.370630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13287v4","created_at":"2026-07-05T06:21:30.370630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13287","created_at":"2026-07-05T06:21:30.370630+00:00"},{"alias_kind":"pith_short_12","alias_value":"RS4C5KBRTYNO","created_at":"2026-07-05T06:21:30.370630+00:00"},{"alias_kind":"pith_short_16","alias_value":"RS4C5KBRTYNOJCJE","created_at":"2026-07-05T06:21:30.370630+00:00"},{"alias_kind":"pith_short_8","alias_value":"RS4C5KBR","created_at":"2026-07-05T06:21:30.370630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18209","citing_title":"Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6","json":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6.json","graph_json":"https://pith.science/api/pith-number/RS4C5KBRTYNOJCJEL6GYUB54J6/graph.json","events_json":"https://pith.science/api/pith-number/RS4C5KBRTYNOJCJEL6GYUB54J6/events.json","paper":"https://pith.science/paper/RS4C5KBR"},"agent_actions":{"view_html":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6","download_json":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6.json","view_paper":"https://pith.science/paper/RS4C5KBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13287&json=true","fetch_graph":"https://pith.science/api/pith-number/RS4C5KBRTYNOJCJEL6GYUB54J6/graph.json","fetch_events":"https://pith.science/api/pith-number/RS4C5KBRTYNOJCJEL6GYUB54J6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6/action/storage_attestation","attest_author":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6/action/author_attestation","sign_citation":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6/action/citation_signature","submit_replication":"https://pith.science/pith/RS4C5KBRTYNOJCJEL6GYUB54J6/action/replication_record"}},"created_at":"2026-07-05T06:21:30.370630+00:00","updated_at":"2026-07-05T06:21:30.370630+00:00"}