{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UBCZ26BJWWGLO37DEXZPEMJ7IA","short_pith_number":"pith:UBCZ26BJ","schema_version":"1.0","canonical_sha256":"a0459d7829b58cb76fe325f2f2313f401d531d2eba13a62c78977f50b4264429","source":{"kind":"arxiv","id":"2104.13794","version":1},"attestation_state":"computed","paper":{"title":"Finding High-Value Training Data Subset through Differentiable Convex Programming","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arshdeep Singh, Saptarshi Chatterjee, Soumi Das, Sourangshu Bhattacharya, Suparna Bhattacharya","submitted_at":"2021-04-28T14:33:26Z","abstract_excerpt":"Finding valuable training data points for deep neural networks has been a core research challenge with many applications. In recent years, various techniques for calculating the \"value\" of individual training datapoints have been proposed for explaining trained models. However, the value of a training datapoint also depends on other selected training datapoints - a notion that is not explicitly captured by existing methods. In this paper, we study the problem of selecting high-value subsets of training data. The key idea is to design a learnable framework for online subset selection, which can"},"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":"2104.13794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-28T14:33:26Z","cross_cats_sorted":[],"title_canon_sha256":"f5bad71a48063344ec8af9eaba5c45bb3ea89abb386f87824b6a0d3efa9e9c7d","abstract_canon_sha256":"2ec113b03f52809a34f14a7548c58f12136abf1f34cf403f31dea90a6c48d95c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:04.259947Z","signature_b64":"woQETp8pyZkeoHxfn3MBWid/iT7SQ2YvAxHIum1w11nGSWlhV3lxik7X8n9WO5icmypw4Tn6QJN0Kwz8fyDlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0459d7829b58cb76fe325f2f2313f401d531d2eba13a62c78977f50b4264429","last_reissued_at":"2026-07-05T02:36:04.259469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:04.259469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding High-Value Training Data Subset through Differentiable Convex Programming","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arshdeep Singh, Saptarshi Chatterjee, Soumi Das, Sourangshu Bhattacharya, Suparna Bhattacharya","submitted_at":"2021-04-28T14:33:26Z","abstract_excerpt":"Finding valuable training data points for deep neural networks has been a core research challenge with many applications. In recent years, various techniques for calculating the \"value\" of individual training datapoints have been proposed for explaining trained models. However, the value of a training datapoint also depends on other selected training datapoints - a notion that is not explicitly captured by existing methods. In this paper, we study the problem of selecting high-value subsets of training data. The key idea is to design a learnable framework for online subset selection, which can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13794","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/2104.13794/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":"2104.13794","created_at":"2026-07-05T02:36:04.259527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13794v1","created_at":"2026-07-05T02:36:04.259527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13794","created_at":"2026-07-05T02:36:04.259527+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBCZ26BJWWGL","created_at":"2026-07-05T02:36:04.259527+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBCZ26BJWWGLO37D","created_at":"2026-07-05T02:36:04.259527+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBCZ26BJ","created_at":"2026-07-05T02:36:04.259527+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/UBCZ26BJWWGLO37DEXZPEMJ7IA","json":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA.json","graph_json":"https://pith.science/api/pith-number/UBCZ26BJWWGLO37DEXZPEMJ7IA/graph.json","events_json":"https://pith.science/api/pith-number/UBCZ26BJWWGLO37DEXZPEMJ7IA/events.json","paper":"https://pith.science/paper/UBCZ26BJ"},"agent_actions":{"view_html":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA","download_json":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA.json","view_paper":"https://pith.science/paper/UBCZ26BJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13794&json=true","fetch_graph":"https://pith.science/api/pith-number/UBCZ26BJWWGLO37DEXZPEMJ7IA/graph.json","fetch_events":"https://pith.science/api/pith-number/UBCZ26BJWWGLO37DEXZPEMJ7IA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA/action/storage_attestation","attest_author":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA/action/author_attestation","sign_citation":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA/action/citation_signature","submit_replication":"https://pith.science/pith/UBCZ26BJWWGLO37DEXZPEMJ7IA/action/replication_record"}},"created_at":"2026-07-05T02:36:04.259527+00:00","updated_at":"2026-07-05T02:36:04.259527+00:00"}