{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OZXZT3QI7JBHMTF3MSXCMKZAS3","short_pith_number":"pith:OZXZT3QI","schema_version":"1.0","canonical_sha256":"766f99ee08fa42764cbb64ae262b2096da9a604d176f6d9031b36a7e8b7803cc","source":{"kind":"arxiv","id":"2408.08670","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alessio Devoto, Federico Alvetreti, Jary Pomponi, Paolo Di Lorenzo, Pasquale Minervini, Simone Scardapane","submitted_at":"2024-08-16T11:27:52Z","abstract_excerpt":"Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this end, in this paper we introduce an efficient fine-tuning method for ViTs called $\\textbf{ALaST}$ ($\\textit{Adaptive Layer Selection Fine-Tuning for Vision Transformers}$) to speed up the fine-tuning process while reducing computational cost, memory load, and training time. Our approach is based on the observation that not all layers are equally critical dur"},"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":"2408.08670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-16T11:27:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71b886d5db472e19bcd95108a19a6ec96193cd30a4c90537fb94af8b1ae24681","abstract_canon_sha256":"013c824e6fd78ebdd98477c9d29afe82a21ce2340acadb54fe4d93028ae07b8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:07.577608Z","signature_b64":"UXxm0Dklrvmn8rX7j61hnQ3krE+0VdefDJQcvSTTD+aoRI1TA6qfZIvRtkEf9RaUc7xZn1my3DZVv7iJ91IUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"766f99ee08fa42764cbb64ae262b2096da9a604d176f6d9031b36a7e8b7803cc","last_reissued_at":"2026-07-05T08:56:07.577188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:07.577188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alessio Devoto, Federico Alvetreti, Jary Pomponi, Paolo Di Lorenzo, Pasquale Minervini, Simone Scardapane","submitted_at":"2024-08-16T11:27:52Z","abstract_excerpt":"Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this end, in this paper we introduce an efficient fine-tuning method for ViTs called $\\textbf{ALaST}$ ($\\textit{Adaptive Layer Selection Fine-Tuning for Vision Transformers}$) to speed up the fine-tuning process while reducing computational cost, memory load, and training time. Our approach is based on the observation that not all layers are equally critical dur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08670","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/2408.08670/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":"2408.08670","created_at":"2026-07-05T08:56:07.577239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08670v1","created_at":"2026-07-05T08:56:07.577239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08670","created_at":"2026-07-05T08:56:07.577239+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZXZT3QI7JBH","created_at":"2026-07-05T08:56:07.577239+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZXZT3QI7JBHMTF3","created_at":"2026-07-05T08:56:07.577239+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZXZT3QI","created_at":"2026-07-05T08:56:07.577239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04411","citing_title":"Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3","json":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3.json","graph_json":"https://pith.science/api/pith-number/OZXZT3QI7JBHMTF3MSXCMKZAS3/graph.json","events_json":"https://pith.science/api/pith-number/OZXZT3QI7JBHMTF3MSXCMKZAS3/events.json","paper":"https://pith.science/paper/OZXZT3QI"},"agent_actions":{"view_html":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3","download_json":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3.json","view_paper":"https://pith.science/paper/OZXZT3QI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08670&json=true","fetch_graph":"https://pith.science/api/pith-number/OZXZT3QI7JBHMTF3MSXCMKZAS3/graph.json","fetch_events":"https://pith.science/api/pith-number/OZXZT3QI7JBHMTF3MSXCMKZAS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3/action/storage_attestation","attest_author":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3/action/author_attestation","sign_citation":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3/action/citation_signature","submit_replication":"https://pith.science/pith/OZXZT3QI7JBHMTF3MSXCMKZAS3/action/replication_record"}},"created_at":"2026-07-05T08:56:07.577239+00:00","updated_at":"2026-07-05T08:56:07.577239+00:00"}