{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VLTNUFDJX34ZB6BZK22H45L2NB","short_pith_number":"pith:VLTNUFDJ","schema_version":"1.0","canonical_sha256":"aae6da1469bef990f83956b47e757a684041d79836086c71587e2c7abed2468a","source":{"kind":"arxiv","id":"2209.15006","version":1},"attestation_state":"computed","paper":{"title":"Effective Vision Transformer Training: A Data-Centric Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjia Zhou, Fan Wang, Jun Wan, Pichao Wang, Yanyan Liang","submitted_at":"2022-09-29T17:59:46Z","abstract_excerpt":"Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we define several metrics, including Dynamic Data Proportion (DDP) and Knowledge Assimilation Rate (KAR), to investigate the training process, and divide it into three periods accordingly: formation, growth and exploration. In particular, at the last stage of training, we observe that only a tiny portion of training examples is used to optimize the model. Given the data-hungry nature of ViTs, we thus ask a simple but i"},"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":"2209.15006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T17:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"4a149dea73cf708c5439298ac8a218ac2bc6c508be0d0251c03a2a5f56835110","abstract_canon_sha256":"3855c67bfc326271b77fb74e462a3656595363394af91f79569983fd9c7173c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:07.678685Z","signature_b64":"qSY8ONYAiDjls0PebBIbEaDyMsffH6eCE41ERRqFGB+OD9Yk5bkA0qKpY58CbyLDp36u7yrq3vGGAo0e6/eVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aae6da1469bef990f83956b47e757a684041d79836086c71587e2c7abed2468a","last_reissued_at":"2026-07-05T05:02:07.678252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:07.678252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Vision Transformer Training: A Data-Centric Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjia Zhou, Fan Wang, Jun Wan, Pichao Wang, Yanyan Liang","submitted_at":"2022-09-29T17:59:46Z","abstract_excerpt":"Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we define several metrics, including Dynamic Data Proportion (DDP) and Knowledge Assimilation Rate (KAR), to investigate the training process, and divide it into three periods accordingly: formation, growth and exploration. In particular, at the last stage of training, we observe that only a tiny portion of training examples is used to optimize the model. Given the data-hungry nature of ViTs, we thus ask a simple but i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15006","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/2209.15006/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":"2209.15006","created_at":"2026-07-05T05:02:07.678307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15006v1","created_at":"2026-07-05T05:02:07.678307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15006","created_at":"2026-07-05T05:02:07.678307+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLTNUFDJX34Z","created_at":"2026-07-05T05:02:07.678307+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLTNUFDJX34ZB6BZ","created_at":"2026-07-05T05:02:07.678307+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLTNUFDJ","created_at":"2026-07-05T05:02:07.678307+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/VLTNUFDJX34ZB6BZK22H45L2NB","json":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB.json","graph_json":"https://pith.science/api/pith-number/VLTNUFDJX34ZB6BZK22H45L2NB/graph.json","events_json":"https://pith.science/api/pith-number/VLTNUFDJX34ZB6BZK22H45L2NB/events.json","paper":"https://pith.science/paper/VLTNUFDJ"},"agent_actions":{"view_html":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB","download_json":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB.json","view_paper":"https://pith.science/paper/VLTNUFDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15006&json=true","fetch_graph":"https://pith.science/api/pith-number/VLTNUFDJX34ZB6BZK22H45L2NB/graph.json","fetch_events":"https://pith.science/api/pith-number/VLTNUFDJX34ZB6BZK22H45L2NB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB/action/storage_attestation","attest_author":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB/action/author_attestation","sign_citation":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB/action/citation_signature","submit_replication":"https://pith.science/pith/VLTNUFDJX34ZB6BZK22H45L2NB/action/replication_record"}},"created_at":"2026-07-05T05:02:07.678307+00:00","updated_at":"2026-07-05T05:02:07.678307+00:00"}