{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KXW34T4TTWMDNON2BEJEUV7CNG","short_pith_number":"pith:KXW34T4T","schema_version":"1.0","canonical_sha256":"55edbe4f939d9836b9ba09124a57e269a6cf66ac10fbfc28ba065de3228b58c8","source":{"kind":"arxiv","id":"2404.19286","version":2},"attestation_state":"computed","paper":{"title":"Soft Prompt Generation for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Badong Chen, Shuanghao Bai, Wanqi Zhou, Yuedi Zhang, Zhirong Luan","submitted_at":"2024-04-30T06:33:07Z","abstract_excerpt":"Large pre-trained vision language models (VLMs) have shown impressive zero-shot ability on downstream tasks with manually designed prompt. To further adapt VLMs to downstream tasks, soft prompt is proposed to replace manually designed prompt, which undergoes fine-tuning based on specific domain data. Prior prompt learning methods primarily learn a fixed prompt or residuled prompt from training samples. However, the learned prompts lack diversity and ignore information about unseen domains. In this paper, we reframe the prompt learning framework from a generative perspective and propose a simpl"},"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":"2404.19286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T06:33:07Z","cross_cats_sorted":[],"title_canon_sha256":"50a0241fb968535bd7e76b8f0ff7ca23437d3ff76ce06889a439f4f0ee863f8a","abstract_canon_sha256":"15ae13ef72734f1fc4ddb64b07349c28685f6c754fe792cd7aaba114eb0806ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:10.023409Z","signature_b64":"OD2c/rRwhLRdzzR4NdgEWcQ0qrJtmOV5SxU+xWXFt1ied8H06q95G7wipBWJt11yL/0DiPnY15fLQt0HgNcgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55edbe4f939d9836b9ba09124a57e269a6cf66ac10fbfc28ba065de3228b58c8","last_reissued_at":"2026-07-05T08:43:10.022921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:10.022921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Prompt Generation for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Badong Chen, Shuanghao Bai, Wanqi Zhou, Yuedi Zhang, Zhirong Luan","submitted_at":"2024-04-30T06:33:07Z","abstract_excerpt":"Large pre-trained vision language models (VLMs) have shown impressive zero-shot ability on downstream tasks with manually designed prompt. To further adapt VLMs to downstream tasks, soft prompt is proposed to replace manually designed prompt, which undergoes fine-tuning based on specific domain data. Prior prompt learning methods primarily learn a fixed prompt or residuled prompt from training samples. However, the learned prompts lack diversity and ignore information about unseen domains. In this paper, we reframe the prompt learning framework from a generative perspective and propose a simpl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19286","kind":"arxiv","version":2},"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/2404.19286/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":"2404.19286","created_at":"2026-07-05T08:43:10.022966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19286v2","created_at":"2026-07-05T08:43:10.022966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19286","created_at":"2026-07-05T08:43:10.022966+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXW34T4TTWMD","created_at":"2026-07-05T08:43:10.022966+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXW34T4TTWMDNON2","created_at":"2026-07-05T08:43:10.022966+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXW34T4T","created_at":"2026-07-05T08:43:10.022966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.14280","citing_title":"CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG","json":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG.json","graph_json":"https://pith.science/api/pith-number/KXW34T4TTWMDNON2BEJEUV7CNG/graph.json","events_json":"https://pith.science/api/pith-number/KXW34T4TTWMDNON2BEJEUV7CNG/events.json","paper":"https://pith.science/paper/KXW34T4T"},"agent_actions":{"view_html":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG","download_json":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG.json","view_paper":"https://pith.science/paper/KXW34T4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19286&json=true","fetch_graph":"https://pith.science/api/pith-number/KXW34T4TTWMDNON2BEJEUV7CNG/graph.json","fetch_events":"https://pith.science/api/pith-number/KXW34T4TTWMDNON2BEJEUV7CNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG/action/storage_attestation","attest_author":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG/action/author_attestation","sign_citation":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG/action/citation_signature","submit_replication":"https://pith.science/pith/KXW34T4TTWMDNON2BEJEUV7CNG/action/replication_record"}},"created_at":"2026-07-05T08:43:10.022966+00:00","updated_at":"2026-07-05T08:43:10.022966+00:00"}