{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GG32WAEGYM3DXZMUK3BRT6IVHY","short_pith_number":"pith:GG32WAEG","schema_version":"1.0","canonical_sha256":"31b7ab0086c3363be59456c319f9153e39b26e9fbbfdfe2b04cc54151fd68786","source":{"kind":"arxiv","id":"2205.13535","version":3},"attestation_state":"computed","paper":{"title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Jiangliu Wang, Jue Wang, Ping Luo, Shoufa Chen, Yibing Song, Zhan Tong","submitted_at":"2022-05-26T17:56:15Z","abstract_excerpt":"Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and memory storage. Each model needs an independent and complete finetuning process to adapt to different tasks, which limits its transferability to different visual domains. To address this challenge, we propose an effective adaptation approach for Transformer, namely AdaptFormer, which can adapt the pre-trained ViTs into many different image and video tasks effic"},"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":"2205.13535","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-26T17:56:15Z","cross_cats_sorted":[],"title_canon_sha256":"b0da5aec128503f7d12c92b1aec8b67be7f9729edd67a8c282272584a94e98a7","abstract_canon_sha256":"01c54ee2a53a1abe32ed9e6ed7d4a3c6884768d387e29f3cc588f77b79cd35c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:58.785145Z","signature_b64":"gmVBiC+RHXMUjLtT4Yh4EU7HLUM92BoDjwF724ZPCEINJqTbYwIpiBKiGtmjOlkmSZytLWnl7mFKw5LeZOb9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31b7ab0086c3363be59456c319f9153e39b26e9fbbfdfe2b04cc54151fd68786","last_reissued_at":"2026-07-05T05:06:58.784516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:58.784516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Jiangliu Wang, Jue Wang, Ping Luo, Shoufa Chen, Yibing Song, Zhan Tong","submitted_at":"2022-05-26T17:56:15Z","abstract_excerpt":"Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and memory storage. Each model needs an independent and complete finetuning process to adapt to different tasks, which limits its transferability to different visual domains. To address this challenge, we propose an effective adaptation approach for Transformer, namely AdaptFormer, which can adapt the pre-trained ViTs into many different image and video tasks effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13535","kind":"arxiv","version":3},"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/2205.13535/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":"2205.13535","created_at":"2026-07-05T05:06:58.784595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13535v3","created_at":"2026-07-05T05:06:58.784595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13535","created_at":"2026-07-05T05:06:58.784595+00:00"},{"alias_kind":"pith_short_12","alias_value":"GG32WAEGYM3D","created_at":"2026-07-05T05:06:58.784595+00:00"},{"alias_kind":"pith_short_16","alias_value":"GG32WAEGYM3DXZMU","created_at":"2026-07-05T05:06:58.784595+00:00"},{"alias_kind":"pith_short_8","alias_value":"GG32WAEG","created_at":"2026-07-05T05:06:58.784595+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27962","citing_title":"Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29726","citing_title":"SLAD : Shared LoRA Adapters for Task Specific Distillation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17491","citing_title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10009","citing_title":"Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04420","citing_title":"Is Prompt Selection Necessary for Task-Free Online Continual Learning?","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY","json":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY.json","graph_json":"https://pith.science/api/pith-number/GG32WAEGYM3DXZMUK3BRT6IVHY/graph.json","events_json":"https://pith.science/api/pith-number/GG32WAEGYM3DXZMUK3BRT6IVHY/events.json","paper":"https://pith.science/paper/GG32WAEG"},"agent_actions":{"view_html":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY","download_json":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY.json","view_paper":"https://pith.science/paper/GG32WAEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13535&json=true","fetch_graph":"https://pith.science/api/pith-number/GG32WAEGYM3DXZMUK3BRT6IVHY/graph.json","fetch_events":"https://pith.science/api/pith-number/GG32WAEGYM3DXZMUK3BRT6IVHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY/action/storage_attestation","attest_author":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY/action/author_attestation","sign_citation":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY/action/citation_signature","submit_replication":"https://pith.science/pith/GG32WAEGYM3DXZMUK3BRT6IVHY/action/replication_record"}},"created_at":"2026-07-05T05:06:58.784595+00:00","updated_at":"2026-07-05T05:06:58.784595+00:00"}