{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YELF6JXBNEUZRLCGDOM2KDL3KT","short_pith_number":"pith:YELF6JXB","schema_version":"1.0","canonical_sha256":"c1165f26e1692998ac461b99a50d7b54f35bbb9808f15b01ef6e912e62da4eda","source":{"kind":"arxiv","id":"2303.11114","version":2},"attestation_state":"computed","paper":{"title":"SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Song Park, Wonjae Kim","submitted_at":"2023-03-20T13:55:35Z","abstract_excerpt":"We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e.g., the LAION-4B dataset needs 240TB storage space). However, it has become challenging to deal with unlimited dataset storage with limited storage infrastructure. A number of storage-efficient training methods have been proposed to tackle the problem, but they are rarely scalable or suffer from severe damage to performance. In this paper, we propose a storage-efficient training strategy for vision classifiers for large-scale datasets (e.g., Ima"},"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":"2303.11114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T13:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"faddc47dc763064fcc0d75738883902f6000a4550830c00a5700361922b03244","abstract_canon_sha256":"ac8e73e96b79f1a5886fda05fb4adb25df9adc076e30b73508ed22f0e20bfe59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:20.426193Z","signature_b64":"Scg12JtM/kQdXWO3MK19hvhSTSC5epTIn2f8IYuhoRmFgtiaEZWqUl+fZCSQmsKq8s2tbZl8l65tHOfDfZ9IDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1165f26e1692998ac461b99a50d7b54f35bbb9808f15b01ef6e912e62da4eda","last_reissued_at":"2026-07-05T06:49:20.425693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:20.425693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Song Park, Wonjae Kim","submitted_at":"2023-03-20T13:55:35Z","abstract_excerpt":"We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e.g., the LAION-4B dataset needs 240TB storage space). However, it has become challenging to deal with unlimited dataset storage with limited storage infrastructure. A number of storage-efficient training methods have been proposed to tackle the problem, but they are rarely scalable or suffer from severe damage to performance. In this paper, we propose a storage-efficient training strategy for vision classifiers for large-scale datasets (e.g., Ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11114","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/2303.11114/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":"2303.11114","created_at":"2026-07-05T06:49:20.425745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11114v2","created_at":"2026-07-05T06:49:20.425745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11114","created_at":"2026-07-05T06:49:20.425745+00:00"},{"alias_kind":"pith_short_12","alias_value":"YELF6JXBNEUZ","created_at":"2026-07-05T06:49:20.425745+00:00"},{"alias_kind":"pith_short_16","alias_value":"YELF6JXBNEUZRLCG","created_at":"2026-07-05T06:49:20.425745+00:00"},{"alias_kind":"pith_short_8","alias_value":"YELF6JXB","created_at":"2026-07-05T06:49:20.425745+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/YELF6JXBNEUZRLCGDOM2KDL3KT","json":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT.json","graph_json":"https://pith.science/api/pith-number/YELF6JXBNEUZRLCGDOM2KDL3KT/graph.json","events_json":"https://pith.science/api/pith-number/YELF6JXBNEUZRLCGDOM2KDL3KT/events.json","paper":"https://pith.science/paper/YELF6JXB"},"agent_actions":{"view_html":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT","download_json":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT.json","view_paper":"https://pith.science/paper/YELF6JXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11114&json=true","fetch_graph":"https://pith.science/api/pith-number/YELF6JXBNEUZRLCGDOM2KDL3KT/graph.json","fetch_events":"https://pith.science/api/pith-number/YELF6JXBNEUZRLCGDOM2KDL3KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT/action/storage_attestation","attest_author":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT/action/author_attestation","sign_citation":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT/action/citation_signature","submit_replication":"https://pith.science/pith/YELF6JXBNEUZRLCGDOM2KDL3KT/action/replication_record"}},"created_at":"2026-07-05T06:49:20.425745+00:00","updated_at":"2026-07-05T06:49:20.425745+00:00"}