{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NVNGFGTSWT34MMASI75VI2GAHD","short_pith_number":"pith:NVNGFGTS","schema_version":"1.0","canonical_sha256":"6d5a629a72b4f7c6301247fb5468c038f3f45c41ccdd6d7ec0edbe4270b617e1","source":{"kind":"arxiv","id":"2107.03227","version":1},"attestation_state":"computed","paper":{"title":"Scalable Data Balancing for Unlabeled Satellite Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Anirudh Koul, Deep Patel, Erin Gao, Meher Anand Kasam, Siddha Ganju","submitted_at":"2021-07-07T13:58:15Z","abstract_excerpt":"Data imbalance is a ubiquitous problem in machine learning. In large scale collected and annotated datasets, data imbalance is either mitigated manually by undersampling frequent classes and oversampling rare classes, or planned for with imputation and augmentation techniques. In both cases balancing data requires labels. In other words, only annotated data can be balanced. Collecting fully annotated datasets is challenging, especially for large scale satellite systems such as the unlabeled NASA's 35 PB Earth Imagery dataset. Although the NASA Earth Imagery dataset is unlabeled, there are impl"},"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":"2107.03227","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T13:58:15Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"720e4167b0fb42e66d1873b4489d723ed67bcd03d878675af89bc322fa9bd3f0","abstract_canon_sha256":"6994862df8ab2c801e5fd39eba2a098f7bc187db1de2dadae390d17b8ab7096d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:43.763884Z","signature_b64":"AbnEwBxdtFwqO42RKL/B7nDG1vzuhG1Nv/Rk50I3ZqlWCilWKB08KQP4m7YzEc/US5jBLUupFZIuZSUNXpEJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5a629a72b4f7c6301247fb5468c038f3f45c41ccdd6d7ec0edbe4270b617e1","last_reissued_at":"2026-07-05T02:58:43.763428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:43.763428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Data Balancing for Unlabeled Satellite Imagery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Anirudh Koul, Deep Patel, Erin Gao, Meher Anand Kasam, Siddha Ganju","submitted_at":"2021-07-07T13:58:15Z","abstract_excerpt":"Data imbalance is a ubiquitous problem in machine learning. In large scale collected and annotated datasets, data imbalance is either mitigated manually by undersampling frequent classes and oversampling rare classes, or planned for with imputation and augmentation techniques. In both cases balancing data requires labels. In other words, only annotated data can be balanced. Collecting fully annotated datasets is challenging, especially for large scale satellite systems such as the unlabeled NASA's 35 PB Earth Imagery dataset. Although the NASA Earth Imagery dataset is unlabeled, there are impl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03227","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/2107.03227/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":"2107.03227","created_at":"2026-07-05T02:58:43.763497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03227v1","created_at":"2026-07-05T02:58:43.763497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03227","created_at":"2026-07-05T02:58:43.763497+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVNGFGTSWT34","created_at":"2026-07-05T02:58:43.763497+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVNGFGTSWT34MMAS","created_at":"2026-07-05T02:58:43.763497+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVNGFGTS","created_at":"2026-07-05T02:58:43.763497+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/NVNGFGTSWT34MMASI75VI2GAHD","json":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD.json","graph_json":"https://pith.science/api/pith-number/NVNGFGTSWT34MMASI75VI2GAHD/graph.json","events_json":"https://pith.science/api/pith-number/NVNGFGTSWT34MMASI75VI2GAHD/events.json","paper":"https://pith.science/paper/NVNGFGTS"},"agent_actions":{"view_html":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD","download_json":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD.json","view_paper":"https://pith.science/paper/NVNGFGTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03227&json=true","fetch_graph":"https://pith.science/api/pith-number/NVNGFGTSWT34MMASI75VI2GAHD/graph.json","fetch_events":"https://pith.science/api/pith-number/NVNGFGTSWT34MMASI75VI2GAHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD/action/storage_attestation","attest_author":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD/action/author_attestation","sign_citation":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD/action/citation_signature","submit_replication":"https://pith.science/pith/NVNGFGTSWT34MMASI75VI2GAHD/action/replication_record"}},"created_at":"2026-07-05T02:58:43.763497+00:00","updated_at":"2026-07-05T02:58:43.763497+00:00"}