{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DELNMQWHXLEXCVFI7CQDUODMUK","short_pith_number":"pith:DELNMQWH","schema_version":"1.0","canonical_sha256":"1916d642c7bac97154a8f8a03a386ca289af2b96f0096afa5c9aa58bc731bb92","source":{"kind":"arxiv","id":"2210.00990","version":1},"attestation_state":"computed","paper":{"title":"Visual Prompt Tuning for Generative Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Zhang, Huiwen Chang, Irfan Essa, Jos\\'e Lezama, Kihyuk Sohn, Luisa Polania, Lu Jiang, Yuan Hao","submitted_at":"2022-10-03T14:56:05Z","abstract_excerpt":"Transferring knowledge from an image synthesis model trained on a large dataset is a promising direction for learning generative image models from various domains efficiently. While previous works have studied GAN models, we present a recipe for learning vision transformers by generative knowledge transfer. We base our framework on state-of-the-art generative vision transformers that represent an image as a sequence of visual tokens to the autoregressive or non-autoregressive transformers. To adapt to a new domain, we employ prompt tuning, which prepends learnable tokens called prompt to the i"},"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":"2210.00990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T14:56:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25f514e598df4715bfadb31ec8b9de2791182c681a321b83b05ace216c943b1b","abstract_canon_sha256":"26dc3b769e0fc0a528fc02627a335889cb76a09aab5267aa9c081625dd98d957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:50.001726Z","signature_b64":"mJWfQaWpDYuUoKKh4YE++3vI44kknXzkQFnrdHMjYS2YrH5JbJzdTsfS68hU0yuVRFnJD1yIbIZN2vj1AnLDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1916d642c7bac97154a8f8a03a386ca289af2b96f0096afa5c9aa58bc731bb92","last_reissued_at":"2026-07-05T05:02:50.001285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:50.001285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Prompt Tuning for Generative Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Zhang, Huiwen Chang, Irfan Essa, Jos\\'e Lezama, Kihyuk Sohn, Luisa Polania, Lu Jiang, Yuan Hao","submitted_at":"2022-10-03T14:56:05Z","abstract_excerpt":"Transferring knowledge from an image synthesis model trained on a large dataset is a promising direction for learning generative image models from various domains efficiently. While previous works have studied GAN models, we present a recipe for learning vision transformers by generative knowledge transfer. We base our framework on state-of-the-art generative vision transformers that represent an image as a sequence of visual tokens to the autoregressive or non-autoregressive transformers. To adapt to a new domain, we employ prompt tuning, which prepends learnable tokens called prompt to the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00990","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/2210.00990/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":"2210.00990","created_at":"2026-07-05T05:02:50.001359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00990v1","created_at":"2026-07-05T05:02:50.001359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00990","created_at":"2026-07-05T05:02:50.001359+00:00"},{"alias_kind":"pith_short_12","alias_value":"DELNMQWHXLEX","created_at":"2026-07-05T05:02:50.001359+00:00"},{"alias_kind":"pith_short_16","alias_value":"DELNMQWHXLEXCVFI","created_at":"2026-07-05T05:02:50.001359+00:00"},{"alias_kind":"pith_short_8","alias_value":"DELNMQWH","created_at":"2026-07-05T05:02:50.001359+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.05737","citing_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK","json":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK.json","graph_json":"https://pith.science/api/pith-number/DELNMQWHXLEXCVFI7CQDUODMUK/graph.json","events_json":"https://pith.science/api/pith-number/DELNMQWHXLEXCVFI7CQDUODMUK/events.json","paper":"https://pith.science/paper/DELNMQWH"},"agent_actions":{"view_html":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK","download_json":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK.json","view_paper":"https://pith.science/paper/DELNMQWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00990&json=true","fetch_graph":"https://pith.science/api/pith-number/DELNMQWHXLEXCVFI7CQDUODMUK/graph.json","fetch_events":"https://pith.science/api/pith-number/DELNMQWHXLEXCVFI7CQDUODMUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK/action/storage_attestation","attest_author":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK/action/author_attestation","sign_citation":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK/action/citation_signature","submit_replication":"https://pith.science/pith/DELNMQWHXLEXCVFI7CQDUODMUK/action/replication_record"}},"created_at":"2026-07-05T05:02:50.001359+00:00","updated_at":"2026-07-05T05:02:50.001359+00:00"}