{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QC5RT2CQ2WCIK62SJT574KDAFO","short_pith_number":"pith:QC5RT2CQ","schema_version":"1.0","canonical_sha256":"80bb19e850d584857b524cfbfe28602ba7f1c0f0224bfa07885ac72d4e0bcb56","source":{"kind":"arxiv","id":"2208.08914","version":1},"attestation_state":"computed","paper":{"title":"Prompt Vision Transformer for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Wang, Xiangyu Yue, Yang You, Zangwei Zheng","submitted_at":"2022-08-18T15:34:13Z","abstract_excerpt":"Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previous domain generalization algorithms. In this paper, we propose a novel approach DoPrompt based on prompt learning to embed the knowledge of source domains in domain prompts for target domain prediction. Specifically, domain prompts are prepended before ViT input tokens from the corresponding source domain. Each domain prompt learns domain-specific knowledge efficiently since it is optimized only for one domain. Meanwh"},"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":"2208.08914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T15:34:13Z","cross_cats_sorted":[],"title_canon_sha256":"c1fab625db09829d107afe7e713fb47c2931d04ce32bca61b97ba5cc4b20dbd4","abstract_canon_sha256":"e58ea04098ad0c8dda4356cf1b05e4d6e3cd159d85a05bad2ddc417da075773d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:39.696913Z","signature_b64":"1b2bwv6OOBbgsjiHt6f5dKG7VSeXA41cUomgs9D73dK0D4/WoyL/F+BKZ/33o0iJQoTwPcjzC3Gx2Fpoa3D0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80bb19e850d584857b524cfbfe28602ba7f1c0f0224bfa07885ac72d4e0bcb56","last_reissued_at":"2026-07-05T04:49:39.696502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:39.696502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Vision Transformer for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Wang, Xiangyu Yue, Yang You, Zangwei Zheng","submitted_at":"2022-08-18T15:34:13Z","abstract_excerpt":"Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previous domain generalization algorithms. In this paper, we propose a novel approach DoPrompt based on prompt learning to embed the knowledge of source domains in domain prompts for target domain prediction. Specifically, domain prompts are prepended before ViT input tokens from the corresponding source domain. Each domain prompt learns domain-specific knowledge efficiently since it is optimized only for one domain. Meanwh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08914","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/2208.08914/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":"2208.08914","created_at":"2026-07-05T04:49:39.696559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08914v1","created_at":"2026-07-05T04:49:39.696559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08914","created_at":"2026-07-05T04:49:39.696559+00:00"},{"alias_kind":"pith_short_12","alias_value":"QC5RT2CQ2WCI","created_at":"2026-07-05T04:49:39.696559+00:00"},{"alias_kind":"pith_short_16","alias_value":"QC5RT2CQ2WCIK62S","created_at":"2026-07-05T04:49:39.696559+00:00"},{"alias_kind":"pith_short_8","alias_value":"QC5RT2CQ","created_at":"2026-07-05T04:49:39.696559+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.15599","citing_title":"FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO","json":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO.json","graph_json":"https://pith.science/api/pith-number/QC5RT2CQ2WCIK62SJT574KDAFO/graph.json","events_json":"https://pith.science/api/pith-number/QC5RT2CQ2WCIK62SJT574KDAFO/events.json","paper":"https://pith.science/paper/QC5RT2CQ"},"agent_actions":{"view_html":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO","download_json":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO.json","view_paper":"https://pith.science/paper/QC5RT2CQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08914&json=true","fetch_graph":"https://pith.science/api/pith-number/QC5RT2CQ2WCIK62SJT574KDAFO/graph.json","fetch_events":"https://pith.science/api/pith-number/QC5RT2CQ2WCIK62SJT574KDAFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO/action/storage_attestation","attest_author":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO/action/author_attestation","sign_citation":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO/action/citation_signature","submit_replication":"https://pith.science/pith/QC5RT2CQ2WCIK62SJT574KDAFO/action/replication_record"}},"created_at":"2026-07-05T04:49:39.696559+00:00","updated_at":"2026-07-05T04:49:39.696559+00:00"}