{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KRDJIMRQWHGSC4OTRLPJZFGL3F","short_pith_number":"pith:KRDJIMRQ","schema_version":"1.0","canonical_sha256":"5446943230b1cd2171d38ade9c94cbd97a89ac2d1ef3e3d2572828c7d46bf8e4","source":{"kind":"arxiv","id":"2110.03613","version":2},"attestation_state":"computed","paper":{"title":"A Data-Centric Approach for Training Deep Neural Networks with Less Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mohammad Motamedi, Nikolay Sakharnykh, Tim Kaldewey","submitted_at":"2021-10-07T16:41:52Z","abstract_excerpt":"While the availability of large datasets is perceived to be a key requirement for training deep neural networks, it is possible to train such models with relatively little data. However, compensating for the absence of large datasets demands a series of actions to enhance the quality of the existing samples and to generate new ones. This paper summarizes our winning submission to the \"Data-Centric AI\" competition. We discuss some of the challenges that arise while training with a small dataset, offer a principled approach for systematic data quality enhancement, and propose a GAN-based solutio"},"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":"2110.03613","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-10-07T16:41:52Z","cross_cats_sorted":[],"title_canon_sha256":"b401bc36ab84cc1b0b38c03ac80a9f49ae57ac766b738b7dbaae3c7a5492dd26","abstract_canon_sha256":"88c201074cb2bfef5a7c1b0698240a2b6b8d7457504288991a2024df5a2a1ac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:36.156870Z","signature_b64":"gIDSjCy9QNow1PTFV9/K57p7UgRXPjdFkROJ1zelosiNqS/uODat06HRLXElF3j63uqRnDIMj7cenFc8hoxlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5446943230b1cd2171d38ade9c94cbd97a89ac2d1ef3e3d2572828c7d46bf8e4","last_reissued_at":"2026-07-05T03:27:36.156369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:36.156369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Data-Centric Approach for Training Deep Neural Networks with Less Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mohammad Motamedi, Nikolay Sakharnykh, Tim Kaldewey","submitted_at":"2021-10-07T16:41:52Z","abstract_excerpt":"While the availability of large datasets is perceived to be a key requirement for training deep neural networks, it is possible to train such models with relatively little data. However, compensating for the absence of large datasets demands a series of actions to enhance the quality of the existing samples and to generate new ones. This paper summarizes our winning submission to the \"Data-Centric AI\" competition. We discuss some of the challenges that arise while training with a small dataset, offer a principled approach for systematic data quality enhancement, and propose a GAN-based solutio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03613","kind":"arxiv","version":2},"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/2110.03613/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":"2110.03613","created_at":"2026-07-05T03:27:36.156423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03613v2","created_at":"2026-07-05T03:27:36.156423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03613","created_at":"2026-07-05T03:27:36.156423+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRDJIMRQWHGS","created_at":"2026-07-05T03:27:36.156423+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRDJIMRQWHGSC4OT","created_at":"2026-07-05T03:27:36.156423+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRDJIMRQ","created_at":"2026-07-05T03:27:36.156423+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/KRDJIMRQWHGSC4OTRLPJZFGL3F","json":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F.json","graph_json":"https://pith.science/api/pith-number/KRDJIMRQWHGSC4OTRLPJZFGL3F/graph.json","events_json":"https://pith.science/api/pith-number/KRDJIMRQWHGSC4OTRLPJZFGL3F/events.json","paper":"https://pith.science/paper/KRDJIMRQ"},"agent_actions":{"view_html":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F","download_json":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F.json","view_paper":"https://pith.science/paper/KRDJIMRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03613&json=true","fetch_graph":"https://pith.science/api/pith-number/KRDJIMRQWHGSC4OTRLPJZFGL3F/graph.json","fetch_events":"https://pith.science/api/pith-number/KRDJIMRQWHGSC4OTRLPJZFGL3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F/action/storage_attestation","attest_author":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F/action/author_attestation","sign_citation":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F/action/citation_signature","submit_replication":"https://pith.science/pith/KRDJIMRQWHGSC4OTRLPJZFGL3F/action/replication_record"}},"created_at":"2026-07-05T03:27:36.156423+00:00","updated_at":"2026-07-05T03:27:36.156423+00:00"}