{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CCG4MYONYN4JO3MWSUBRAU3O6I","short_pith_number":"pith:CCG4MYON","schema_version":"1.0","canonical_sha256":"108dc661cdc378976d96950310536ef216194a1e8450980eff55c9273662b689","source":{"kind":"arxiv","id":"2211.00224","version":2},"attestation_state":"computed","paper":{"title":"SOLAR: A Highly Optimized Data Loading Framework for Distributed Training of CNN-based Scientific Surrogates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Baixi Sun, Chengming Zhang, Dingwen Tao, Jiannan Tian, Kamil Iskra, Pete Beckman, Sian Jin, Tao Zhou, Tekin Bicer, Xiaodong Yu","submitted_at":"2022-11-01T02:25:55Z","abstract_excerpt":"CNN-based surrogates have become prevalent in scientific applications to replace conventional time-consuming physical approaches. Although these surrogates can yield satisfactory results with significantly lower computation costs over small training datasets, our benchmarking results show that data-loading overhead becomes the major performance bottleneck when training surrogates with large datasets. In practice, surrogates are usually trained with high-resolution scientific data, which can easily reach the terabyte scale. Several state-of-the-art data loaders are proposed to improve the loadi"},"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":"2211.00224","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-11-01T02:25:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"131aa3e8067c4c0d0647c14e5936fb9db0b00584995e44609bc56f32c0c9ea85","abstract_canon_sha256":"527d09e4122861b0266d60d766b425b1f20060d45f254d1970c2d00c6485f2c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:10.851474Z","signature_b64":"LrGFc2YJj9It5qUgFYZODUIZtdowQYUNK+rfxFBHb+6h+dljIL2H4Pwulva7zuIXggTmztdPbR+cvCEyW9rWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"108dc661cdc378976d96950310536ef216194a1e8450980eff55c9273662b689","last_reissued_at":"2026-07-05T05:13:10.851132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:10.851132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOLAR: A Highly Optimized Data Loading Framework for Distributed Training of CNN-based Scientific Surrogates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Baixi Sun, Chengming Zhang, Dingwen Tao, Jiannan Tian, Kamil Iskra, Pete Beckman, Sian Jin, Tao Zhou, Tekin Bicer, Xiaodong Yu","submitted_at":"2022-11-01T02:25:55Z","abstract_excerpt":"CNN-based surrogates have become prevalent in scientific applications to replace conventional time-consuming physical approaches. Although these surrogates can yield satisfactory results with significantly lower computation costs over small training datasets, our benchmarking results show that data-loading overhead becomes the major performance bottleneck when training surrogates with large datasets. In practice, surrogates are usually trained with high-resolution scientific data, which can easily reach the terabyte scale. Several state-of-the-art data loaders are proposed to improve the loadi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00224","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/2211.00224/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":"2211.00224","created_at":"2026-07-05T05:13:10.851186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00224v2","created_at":"2026-07-05T05:13:10.851186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00224","created_at":"2026-07-05T05:13:10.851186+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCG4MYONYN4J","created_at":"2026-07-05T05:13:10.851186+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCG4MYONYN4JO3MW","created_at":"2026-07-05T05:13:10.851186+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCG4MYON","created_at":"2026-07-05T05:13:10.851186+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/CCG4MYONYN4JO3MWSUBRAU3O6I","json":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I.json","graph_json":"https://pith.science/api/pith-number/CCG4MYONYN4JO3MWSUBRAU3O6I/graph.json","events_json":"https://pith.science/api/pith-number/CCG4MYONYN4JO3MWSUBRAU3O6I/events.json","paper":"https://pith.science/paper/CCG4MYON"},"agent_actions":{"view_html":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I","download_json":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I.json","view_paper":"https://pith.science/paper/CCG4MYON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00224&json=true","fetch_graph":"https://pith.science/api/pith-number/CCG4MYONYN4JO3MWSUBRAU3O6I/graph.json","fetch_events":"https://pith.science/api/pith-number/CCG4MYONYN4JO3MWSUBRAU3O6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I/action/storage_attestation","attest_author":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I/action/author_attestation","sign_citation":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I/action/citation_signature","submit_replication":"https://pith.science/pith/CCG4MYONYN4JO3MWSUBRAU3O6I/action/replication_record"}},"created_at":"2026-07-05T05:13:10.851186+00:00","updated_at":"2026-07-05T05:13:10.851186+00:00"}