{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VHMGUENR3GPAZHZJXWAAKLDGK7","short_pith_number":"pith:VHMGUENR","schema_version":"1.0","canonical_sha256":"a9d86a11b1d99e0c9f29bd80052c6657f0224e2cba74e77be5fbdaa67f487884","source":{"kind":"arxiv","id":"2309.02617","version":1},"attestation_state":"computed","paper":{"title":"Compressing Vision Transformers for Low-Resource Visual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Youn, Sai Mitheran J, Sanjana Prabhu, Siyuan Chen","submitted_at":"2023-09-05T23:33:39Z","abstract_excerpt":"Vision transformer (ViT) and its variants have swept through visual learning leaderboards and offer state-of-the-art accuracy in tasks such as image classification, object detection, and semantic segmentation by attending to different parts of the visual input and capturing long-range spatial dependencies. However, these models are large and computation-heavy. For instance, the recently proposed ViT-B model has 86M parameters making it impractical for deployment on resource-constrained devices. As a result, their deployment on mobile and edge scenarios is limited. In our work, we aim to take a"},"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":"2309.02617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T23:33:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bf19578598ecd66c082adda44a3d4ce3da6652fea003bd775dc143fee3ec5934","abstract_canon_sha256":"33685d522d3e9599097d7472f7e14c0e66aec2b3789e80ac6138e7557d9fe6f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:15.011787Z","signature_b64":"gZn3J94TvGTYe7ah5gEz3wlLdP/kLw2NHtdw4PyA88roVRboeJ45QWAP4gTebZPi5JtdGgn428Yzpg4oSGedDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9d86a11b1d99e0c9f29bd80052c6657f0224e2cba74e77be5fbdaa67f487884","last_reissued_at":"2026-07-05T06:48:15.011455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:15.011455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressing Vision Transformers for Low-Resource Visual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Youn, Sai Mitheran J, Sanjana Prabhu, Siyuan Chen","submitted_at":"2023-09-05T23:33:39Z","abstract_excerpt":"Vision transformer (ViT) and its variants have swept through visual learning leaderboards and offer state-of-the-art accuracy in tasks such as image classification, object detection, and semantic segmentation by attending to different parts of the visual input and capturing long-range spatial dependencies. However, these models are large and computation-heavy. For instance, the recently proposed ViT-B model has 86M parameters making it impractical for deployment on resource-constrained devices. As a result, their deployment on mobile and edge scenarios is limited. In our work, we aim to take a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02617","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/2309.02617/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":"2309.02617","created_at":"2026-07-05T06:48:15.011509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02617v1","created_at":"2026-07-05T06:48:15.011509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02617","created_at":"2026-07-05T06:48:15.011509+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHMGUENR3GPA","created_at":"2026-07-05T06:48:15.011509+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHMGUENR3GPAZHZJ","created_at":"2026-07-05T06:48:15.011509+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHMGUENR","created_at":"2026-07-05T06:48:15.011509+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/VHMGUENR3GPAZHZJXWAAKLDGK7","json":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7.json","graph_json":"https://pith.science/api/pith-number/VHMGUENR3GPAZHZJXWAAKLDGK7/graph.json","events_json":"https://pith.science/api/pith-number/VHMGUENR3GPAZHZJXWAAKLDGK7/events.json","paper":"https://pith.science/paper/VHMGUENR"},"agent_actions":{"view_html":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7","download_json":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7.json","view_paper":"https://pith.science/paper/VHMGUENR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02617&json=true","fetch_graph":"https://pith.science/api/pith-number/VHMGUENR3GPAZHZJXWAAKLDGK7/graph.json","fetch_events":"https://pith.science/api/pith-number/VHMGUENR3GPAZHZJXWAAKLDGK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7/action/storage_attestation","attest_author":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7/action/author_attestation","sign_citation":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7/action/citation_signature","submit_replication":"https://pith.science/pith/VHMGUENR3GPAZHZJXWAAKLDGK7/action/replication_record"}},"created_at":"2026-07-05T06:48:15.011509+00:00","updated_at":"2026-07-05T06:48:15.011509+00:00"}