{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KTMV44XZ6YYHPZ7GJHUWKYZUMB","short_pith_number":"pith:KTMV44XZ","schema_version":"1.0","canonical_sha256":"54d95e72f9f63077e7e649e9656334605d8e74c870f7b5d1dcaa794ead64c41a","source":{"kind":"arxiv","id":"2210.03117","version":3},"attestation_state":"computed","paper":{"title":"MaPLe: Multi-modal Prompt Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","submitted_at":"2022-10-06T17:59:56Z","abstract_excerpt":"Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Processing (NLP) literature, recent CLIP adaptation approaches learn prompts as the textual inputs to fine-tune CLIP for downstream tasks. We note that using prompting to adapt representations in a single branch of CLIP (language or vision) is sub-optimal since it does not allow the flexibility to dynamically adjust"},"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":"2210.03117","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-06T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"4807122f6a965abe4c2bd2ad13b6cdc712f1c198198c2b797140ab33fefac06e","abstract_canon_sha256":"fe001d0100706a4331c39578a67cf32953e6f3cdaabb18b9f59d4cb4c1fdd370"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:54.793733Z","signature_b64":"kqRTjS1NFI1z+/tDbExWqt79F0fyJxBV10gBGeq4eDbwiOLKFCud/eTd1g0GYFV+kLpwJK0zt4hXwh8JeKdKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d95e72f9f63077e7e649e9656334605d8e74c870f7b5d1dcaa794ead64c41a","last_reissued_at":"2026-07-05T05:56:54.793275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:54.793275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaPLe: Multi-modal Prompt Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","submitted_at":"2022-10-06T17:59:56Z","abstract_excerpt":"Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Processing (NLP) literature, recent CLIP adaptation approaches learn prompts as the textual inputs to fine-tune CLIP for downstream tasks. We note that using prompting to adapt representations in a single branch of CLIP (language or vision) is sub-optimal since it does not allow the flexibility to dynamically adjust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03117","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/2210.03117/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":"2210.03117","created_at":"2026-07-05T05:56:54.793335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03117v3","created_at":"2026-07-05T05:56:54.793335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03117","created_at":"2026-07-05T05:56:54.793335+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTMV44XZ6YYH","created_at":"2026-07-05T05:56:54.793335+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTMV44XZ6YYHPZ7G","created_at":"2026-07-05T05:56:54.793335+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTMV44XZ","created_at":"2026-07-05T05:56:54.793335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01657","citing_title":"Domain Generalization via Text-Anchored Information Bottleneck","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08156","citing_title":"LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB","json":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB.json","graph_json":"https://pith.science/api/pith-number/KTMV44XZ6YYHPZ7GJHUWKYZUMB/graph.json","events_json":"https://pith.science/api/pith-number/KTMV44XZ6YYHPZ7GJHUWKYZUMB/events.json","paper":"https://pith.science/paper/KTMV44XZ"},"agent_actions":{"view_html":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB","download_json":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB.json","view_paper":"https://pith.science/paper/KTMV44XZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03117&json=true","fetch_graph":"https://pith.science/api/pith-number/KTMV44XZ6YYHPZ7GJHUWKYZUMB/graph.json","fetch_events":"https://pith.science/api/pith-number/KTMV44XZ6YYHPZ7GJHUWKYZUMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/action/storage_attestation","attest_author":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/action/author_attestation","sign_citation":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/action/citation_signature","submit_replication":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/action/replication_record"}},"created_at":"2026-07-05T05:56:54.793335+00:00","updated_at":"2026-07-05T05:56:54.793335+00:00"}