{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6FH7HKDVSSD3VJCVNH3G2AB5ZC","short_pith_number":"pith:6FH7HKDV","schema_version":"1.0","canonical_sha256":"f14ff3a8759487baa45569f66d003dc890848c0fd80b484512feb5476a02bfb2","source":{"kind":"arxiv","id":"2606.19483","version":1},"attestation_state":"computed","paper":{"title":"LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Wong, Ashton Lee, Jiaqi Zhang, John Zou, Randall Balestriero, Sami BuGhanem","submitted_at":"2026-06-17T18:14:51Z","abstract_excerpt":"Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirements of backbones often necessitate distillation into smaller architectures for edge deployment. Feature-based knowledge distillation (KD) often suffers from the teacher-student gap; the student struggles to imitate teacher's complex feature map due to its limited capacity. To mitigate this bottleneck, we propose LEAP: Layer-skipping Efficiency via Adaptive Progression, a training"},"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":"2606.19483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T18:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"079d53d1f8fc6851a58148f47d113f97642c69f9a2b6a907b9fed9f938573b84","abstract_canon_sha256":"8facabc58437d2a34ea8288f9fddf6648d9d45b16b60f36dd7b1c731fdcbe8cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:26.956744Z","signature_b64":"DtpKm6HpF2fbKPN03kjHGVPAFrRnxp9GPXDuVEK+DqV7onVLddJPG6gOk9wCVDhN4tSZ5pv44bXyPND9HjS2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f14ff3a8759487baa45569f66d003dc890848c0fd80b484512feb5476a02bfb2","last_reissued_at":"2026-06-19T16:12:26.956392Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:26.956392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Wong, Ashton Lee, Jiaqi Zhang, John Zou, Randall Balestriero, Sami BuGhanem","submitted_at":"2026-06-17T18:14:51Z","abstract_excerpt":"Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirements of backbones often necessitate distillation into smaller architectures for edge deployment. Feature-based knowledge distillation (KD) often suffers from the teacher-student gap; the student struggles to imitate teacher's complex feature map due to its limited capacity. To mitigate this bottleneck, we propose LEAP: Layer-skipping Efficiency via Adaptive Progression, a training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19483","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/2606.19483/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":"2606.19483","created_at":"2026-06-19T16:12:26.956457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19483v1","created_at":"2026-06-19T16:12:26.956457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19483","created_at":"2026-06-19T16:12:26.956457+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FH7HKDVSSD3","created_at":"2026-06-19T16:12:26.956457+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FH7HKDVSSD3VJCV","created_at":"2026-06-19T16:12:26.956457+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FH7HKDV","created_at":"2026-06-19T16:12:26.956457+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/6FH7HKDVSSD3VJCVNH3G2AB5ZC","json":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC.json","graph_json":"https://pith.science/api/pith-number/6FH7HKDVSSD3VJCVNH3G2AB5ZC/graph.json","events_json":"https://pith.science/api/pith-number/6FH7HKDVSSD3VJCVNH3G2AB5ZC/events.json","paper":"https://pith.science/paper/6FH7HKDV"},"agent_actions":{"view_html":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC","download_json":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC.json","view_paper":"https://pith.science/paper/6FH7HKDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19483&json=true","fetch_graph":"https://pith.science/api/pith-number/6FH7HKDVSSD3VJCVNH3G2AB5ZC/graph.json","fetch_events":"https://pith.science/api/pith-number/6FH7HKDVSSD3VJCVNH3G2AB5ZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC/action/storage_attestation","attest_author":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC/action/author_attestation","sign_citation":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC/action/citation_signature","submit_replication":"https://pith.science/pith/6FH7HKDVSSD3VJCVNH3G2AB5ZC/action/replication_record"}},"created_at":"2026-06-19T16:12:26.956457+00:00","updated_at":"2026-06-19T16:12:26.956457+00:00"}