{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N6LD7VCKMELLX3TINBE2MJURYY","short_pith_number":"pith:N6LD7VCK","schema_version":"1.0","canonical_sha256":"6f963fd44a6116bbee686849a62691c62b3bcb181ee02218c3f9491649f6dfcb","source":{"kind":"arxiv","id":"2306.01195","version":4},"attestation_state":"computed","paper":{"title":"Consistency-guided Prompt Learning for Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Etemad, Shuvendu Roy","submitted_at":"2023-06-01T23:20:47Z","abstract_excerpt":"We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting. The basic idea of CoPrompt is to enforce a consistency constraint in the prediction of the trainable and pre-trained models to prevent overfitting on the downstream task. Additionally, we introduce the following two components into our consistency constraint to further boost the performance: enforcing consistency on two perturbed inputs and combining two domin"},"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":"2306.01195","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T23:20:47Z","cross_cats_sorted":[],"title_canon_sha256":"bbea49795d07c1dc712a1acbc3f65c2d396c4f6441f49d5576c9345919796659","abstract_canon_sha256":"c448a91a4f579ee6a647cb4c02cc030c86bb4b7ee765924c64842ca45501935b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:42.048758Z","signature_b64":"T9Om4qZ6uk9jx0zxIfv0M9JaVkY9MFUuBIwSO7LhqtSW/lL0jkAWZyhPoXIW1WGM1BsfnyAfEfOPOtJ+am7hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f963fd44a6116bbee686849a62691c62b3bcb181ee02218c3f9491649f6dfcb","last_reissued_at":"2026-07-05T08:51:42.048200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:42.048200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency-guided Prompt Learning for Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Etemad, Shuvendu Roy","submitted_at":"2023-06-01T23:20:47Z","abstract_excerpt":"We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting. The basic idea of CoPrompt is to enforce a consistency constraint in the prediction of the trainable and pre-trained models to prevent overfitting on the downstream task. Additionally, we introduce the following two components into our consistency constraint to further boost the performance: enforcing consistency on two perturbed inputs and combining two domin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01195","kind":"arxiv","version":4},"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/2306.01195/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":"2306.01195","created_at":"2026-07-05T08:51:42.048260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01195v4","created_at":"2026-07-05T08:51:42.048260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01195","created_at":"2026-07-05T08:51:42.048260+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6LD7VCKMELL","created_at":"2026-07-05T08:51:42.048260+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6LD7VCKMELLX3TI","created_at":"2026-07-05T08:51:42.048260+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6LD7VCK","created_at":"2026-07-05T08:51:42.048260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10488","citing_title":"5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30968","citing_title":"Variational Adapter for Cross-modal Similarity Representation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03980","citing_title":"Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY","json":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY.json","graph_json":"https://pith.science/api/pith-number/N6LD7VCKMELLX3TINBE2MJURYY/graph.json","events_json":"https://pith.science/api/pith-number/N6LD7VCKMELLX3TINBE2MJURYY/events.json","paper":"https://pith.science/paper/N6LD7VCK"},"agent_actions":{"view_html":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY","download_json":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY.json","view_paper":"https://pith.science/paper/N6LD7VCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01195&json=true","fetch_graph":"https://pith.science/api/pith-number/N6LD7VCKMELLX3TINBE2MJURYY/graph.json","fetch_events":"https://pith.science/api/pith-number/N6LD7VCKMELLX3TINBE2MJURYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY/action/storage_attestation","attest_author":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY/action/author_attestation","sign_citation":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY/action/citation_signature","submit_replication":"https://pith.science/pith/N6LD7VCKMELLX3TINBE2MJURYY/action/replication_record"}},"created_at":"2026-07-05T08:51:42.048260+00:00","updated_at":"2026-07-05T08:51:42.048260+00:00"}