{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SXJBW5FNM5677VE25SCUFNHLCK","short_pith_number":"pith:SXJBW5FN","schema_version":"1.0","canonical_sha256":"95d21b74ad677dffd49aec8542b4eb1291e259c8be69400d9f8349e9906db30d","source":{"kind":"arxiv","id":"2104.05704","version":4},"attestation_state":"computed","paper":{"title":"Escaping the Big Data Paradigm with Compact Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abulikemu Abuduweili, Ali Hassani, Humphrey Shi, Jiachen Li, Nikhil Shah, Steven Walton","submitted_at":"2021-04-12T17:58:56Z","abstract_excerpt":"With the rise of Transformers as the standard for language processing, and their advancements in computer vision, there has been a corresponding growth in parameter size and amounts of training data. Many have come to believe that because of this, transformers are not suitable for small sets of data. This trend leads to concerns such as: limited availability of data in certain scientific domains and the exclusion of those with limited resource from research in the field. In this paper, we aim to present an approach for small-scale learning by introducing Compact Transformers. We show for the f"},"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":"2104.05704","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T17:58:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"977accd037d24392beeaee20293b69151729b6ecb7200125f292365014085932","abstract_canon_sha256":"a4cac06a7a23ea853950cd2894cf82259c7ea949af2bc44e2f47d52baa096830"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:03.078940Z","signature_b64":"7hJI7iy/br/+WHiKW1FqwQeU9JaBj5OPQ3k9fupIIWjyO1dfmOFOteuPjxwMQMzdB9n8MNIO9Uy2rHFnPtf5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d21b74ad677dffd49aec8542b4eb1291e259c8be69400d9f8349e9906db30d","last_reissued_at":"2026-07-05T04:30:03.078465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:03.078465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Escaping the Big Data Paradigm with Compact Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abulikemu Abuduweili, Ali Hassani, Humphrey Shi, Jiachen Li, Nikhil Shah, Steven Walton","submitted_at":"2021-04-12T17:58:56Z","abstract_excerpt":"With the rise of Transformers as the standard for language processing, and their advancements in computer vision, there has been a corresponding growth in parameter size and amounts of training data. Many have come to believe that because of this, transformers are not suitable for small sets of data. This trend leads to concerns such as: limited availability of data in certain scientific domains and the exclusion of those with limited resource from research in the field. In this paper, we aim to present an approach for small-scale learning by introducing Compact Transformers. We show for the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05704","kind":"arxiv","version":4},"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/2104.05704/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":"2104.05704","created_at":"2026-07-05T04:30:03.078522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05704v4","created_at":"2026-07-05T04:30:03.078522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05704","created_at":"2026-07-05T04:30:03.078522+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXJBW5FNM567","created_at":"2026-07-05T04:30:03.078522+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXJBW5FNM5677VE2","created_at":"2026-07-05T04:30:03.078522+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXJBW5FN","created_at":"2026-07-05T04:30:03.078522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00277","citing_title":"AEGIS: A Multi-Task Joint-Embedding Predictive Architecture for Mammography","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04106","citing_title":"Building The Ph(ysical)AI Layer Of Machine Intelligence","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03258","citing_title":"IAFormer: Interaction-Aware Transformer network for collider data analysis","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21171","citing_title":"FTerViT: Fully Ternary Vision Transformer","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14689","citing_title":"Are Candidate Models Really Needed for Active Learning?","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02457","citing_title":"Street-Legal Physical-World Adversarial Rim for License Plates","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01298","citing_title":"Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK","json":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK.json","graph_json":"https://pith.science/api/pith-number/SXJBW5FNM5677VE25SCUFNHLCK/graph.json","events_json":"https://pith.science/api/pith-number/SXJBW5FNM5677VE25SCUFNHLCK/events.json","paper":"https://pith.science/paper/SXJBW5FN"},"agent_actions":{"view_html":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK","download_json":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK.json","view_paper":"https://pith.science/paper/SXJBW5FN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05704&json=true","fetch_graph":"https://pith.science/api/pith-number/SXJBW5FNM5677VE25SCUFNHLCK/graph.json","fetch_events":"https://pith.science/api/pith-number/SXJBW5FNM5677VE25SCUFNHLCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK/action/storage_attestation","attest_author":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK/action/author_attestation","sign_citation":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK/action/citation_signature","submit_replication":"https://pith.science/pith/SXJBW5FNM5677VE25SCUFNHLCK/action/replication_record"}},"created_at":"2026-07-05T04:30:03.078522+00:00","updated_at":"2026-07-05T04:30:03.078522+00:00"}