{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QC2NWNGSFBRUN2B7ZQVVNMIKUZ","short_pith_number":"pith:QC2NWNGS","schema_version":"1.0","canonical_sha256":"80b4db34d2286346e83fcc2b56b10aa65f5254a7f2b0326a41b090cbfb0ca5ea","source":{"kind":"arxiv","id":"2310.05393","version":4},"attestation_state":"computed","paper":{"title":"Hierarchical Side-Tuning for Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Huang, Lianwen Jin, Mingxin Huang, Weifeng Lin, Wentao Yang, Ziheng Wu","submitted_at":"2023-10-09T04:16:35Z","abstract_excerpt":"Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial computational and memory costs, posing a considerable challenge. Recent advancements in Parameter-Efficient Transfer Learning (PETL) have shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning. However, their effectiveness is primarily observed in simple tasks like image classification, while they encounter challeng"},"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":"2310.05393","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-09T04:16:35Z","cross_cats_sorted":[],"title_canon_sha256":"d258ffff4678ca4640a5b67661ddd56f4b450f8b4e33129f215518e30d04a5c3","abstract_canon_sha256":"e8a1840d11f187ece3fe0ac0a6cdd704e66f2184a3c050df8b1b8409b13fa808"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:20.592891Z","signature_b64":"iOWd5F3naOZYCv/MOCtsWna8X36kUSt6OyPtRJmIxTNzXRWaqQ9+hh7cnkkWVeViDGrezwdANXu2UD8foWZaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80b4db34d2286346e83fcc2b56b10aa65f5254a7f2b0326a41b090cbfb0ca5ea","last_reissued_at":"2026-07-05T08:19:20.592345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:20.592345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Side-Tuning for Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Huang, Lianwen Jin, Mingxin Huang, Weifeng Lin, Wentao Yang, Ziheng Wu","submitted_at":"2023-10-09T04:16:35Z","abstract_excerpt":"Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. Yet, the demand for individualized and comprehensive fine-tuning processes for each task entails substantial computational and memory costs, posing a considerable challenge. Recent advancements in Parameter-Efficient Transfer Learning (PETL) have shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning. However, their effectiveness is primarily observed in simple tasks like image classification, while they encounter challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05393","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/2310.05393/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":"2310.05393","created_at":"2026-07-05T08:19:20.592430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05393v4","created_at":"2026-07-05T08:19:20.592430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05393","created_at":"2026-07-05T08:19:20.592430+00:00"},{"alias_kind":"pith_short_12","alias_value":"QC2NWNGSFBRU","created_at":"2026-07-05T08:19:20.592430+00:00"},{"alias_kind":"pith_short_16","alias_value":"QC2NWNGSFBRUN2B7","created_at":"2026-07-05T08:19:20.592430+00:00"},{"alias_kind":"pith_short_8","alias_value":"QC2NWNGS","created_at":"2026-07-05T08:19:20.592430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01168","citing_title":"Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09088","citing_title":"Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04058","citing_title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ","json":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ.json","graph_json":"https://pith.science/api/pith-number/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/graph.json","events_json":"https://pith.science/api/pith-number/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/events.json","paper":"https://pith.science/paper/QC2NWNGS"},"agent_actions":{"view_html":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ","download_json":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ.json","view_paper":"https://pith.science/paper/QC2NWNGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05393&json=true","fetch_graph":"https://pith.science/api/pith-number/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/action/storage_attestation","attest_author":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/action/author_attestation","sign_citation":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/action/citation_signature","submit_replication":"https://pith.science/pith/QC2NWNGSFBRUN2B7ZQVVNMIKUZ/action/replication_record"}},"created_at":"2026-07-05T08:19:20.592430+00:00","updated_at":"2026-07-05T08:19:20.592430+00:00"}