{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VXZRRLT63M4C4FPEMLXE24UBYC","short_pith_number":"pith:VXZRRLT6","schema_version":"1.0","canonical_sha256":"adf318ae7edb382e15e462ee4d7281c0b97374746ceb716689e7213e74e5c092","source":{"kind":"arxiv","id":"2404.00851","version":1},"attestation_state":"computed","paper":{"title":"Prompt Learning via Meta-Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyunwoo J. Kim, Jinyoung Park, Juyeon Ko","submitted_at":"2024-04-01T01:42:23Z","abstract_excerpt":"Pre-trained vision-language models have shown impressive success on various computer vision tasks with their zero-shot generalizability. Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language models to a variety of downstream tasks. However, most existing prompt learning methods suffer from task overfitting since the general knowledge of the pre-trained vision language models is forgotten while the prompts are finetuned on a small data set from a specific target task. To address this issue, we propose a Prompt Meta-Regularization (ProMe"},"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":"2404.00851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T01:42:23Z","cross_cats_sorted":[],"title_canon_sha256":"f960a814aa0d87ad809c0971a3c290323c61e9ca56841eb4b2ca47c6f2208e74","abstract_canon_sha256":"020c845c19c0dbdfa437d88a23627bf7fef1ef51cc5a1a81be0ceb8c722a0f6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:57.454650Z","signature_b64":"xhIQHBjsXIhXxIQgs20DroTzkrWe7rRmRqkajiT/WuRQS1l9JS3WaFg2VqReAqhj68QjjfLs28kdH4F0kK/ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adf318ae7edb382e15e462ee4d7281c0b97374746ceb716689e7213e74e5c092","last_reissued_at":"2026-07-05T08:02:57.454198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:57.454198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Learning via Meta-Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyunwoo J. Kim, Jinyoung Park, Juyeon Ko","submitted_at":"2024-04-01T01:42:23Z","abstract_excerpt":"Pre-trained vision-language models have shown impressive success on various computer vision tasks with their zero-shot generalizability. Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language models to a variety of downstream tasks. However, most existing prompt learning methods suffer from task overfitting since the general knowledge of the pre-trained vision language models is forgotten while the prompts are finetuned on a small data set from a specific target task. To address this issue, we propose a Prompt Meta-Regularization (ProMe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00851","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/2404.00851/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":"2404.00851","created_at":"2026-07-05T08:02:57.454268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00851v1","created_at":"2026-07-05T08:02:57.454268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00851","created_at":"2026-07-05T08:02:57.454268+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXZRRLT63M4C","created_at":"2026-07-05T08:02:57.454268+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXZRRLT63M4C4FPE","created_at":"2026-07-05T08:02:57.454268+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXZRRLT6","created_at":"2026-07-05T08:02:57.454268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08410","citing_title":"Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC","json":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC.json","graph_json":"https://pith.science/api/pith-number/VXZRRLT63M4C4FPEMLXE24UBYC/graph.json","events_json":"https://pith.science/api/pith-number/VXZRRLT63M4C4FPEMLXE24UBYC/events.json","paper":"https://pith.science/paper/VXZRRLT6"},"agent_actions":{"view_html":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC","download_json":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC.json","view_paper":"https://pith.science/paper/VXZRRLT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00851&json=true","fetch_graph":"https://pith.science/api/pith-number/VXZRRLT63M4C4FPEMLXE24UBYC/graph.json","fetch_events":"https://pith.science/api/pith-number/VXZRRLT63M4C4FPEMLXE24UBYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC/action/storage_attestation","attest_author":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC/action/author_attestation","sign_citation":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC/action/citation_signature","submit_replication":"https://pith.science/pith/VXZRRLT63M4C4FPEMLXE24UBYC/action/replication_record"}},"created_at":"2026-07-05T08:02:57.454268+00:00","updated_at":"2026-07-05T08:02:57.454268+00:00"}