{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RBZ2S6JG76UTZIV4OAOIT2GW7A","short_pith_number":"pith:RBZ2S6JG","schema_version":"1.0","canonical_sha256":"8873a97926ffa93ca2bc701c89e8d6f83353fb97e0b64e0a10b86dd15135f1cb","source":{"kind":"arxiv","id":"2401.06799","version":1},"attestation_state":"computed","paper":{"title":"Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Heesun Bae, Il-Chul Moon, Seungjae Shin, Weonyoung Joo, Yeo Dong Youn, Youngjae Cho","submitted_at":"2024-01-09T10:15:59Z","abstract_excerpt":"Recent Vision-Language Pretrained (VLP) models have become the backbone for many downstream tasks, but they are utilized as frozen model without learning. Prompt learning is a method to improve the pre-trained VLP model by adding a learnable context vector to the inputs of the text encoder. In a few-shot learning scenario of the downstream task, MLE training can lead the context vector to over-fit dominant image features in the training data. This overfitting can potentially harm the generalization ability, especially in the presence of a distribution shift between the training and test datase"},"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":"2401.06799","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-09T10:15:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d417315a07dcb6537ee93e84c59fee9ab17300ae13da1827abc79c9d2201b739","abstract_canon_sha256":"2d8b175bdc6e176a04abbb47577d2ee6586b4f5a00322fb75a2b890f4b29da47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:26.574154Z","signature_b64":"3nRGrmsqz5n/GsmMqyMeVgnToFOiybGgz94+he0BlPwfTZl9nLlNcn0uioUTqgSGAqmXy20vxQHwVa1XdposBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8873a97926ffa93ca2bc701c89e8d6f83353fb97e0b64e0a10b86dd15135f1cb","last_reissued_at":"2026-07-05T07:33:26.573705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:26.573705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Heesun Bae, Il-Chul Moon, Seungjae Shin, Weonyoung Joo, Yeo Dong Youn, Youngjae Cho","submitted_at":"2024-01-09T10:15:59Z","abstract_excerpt":"Recent Vision-Language Pretrained (VLP) models have become the backbone for many downstream tasks, but they are utilized as frozen model without learning. Prompt learning is a method to improve the pre-trained VLP model by adding a learnable context vector to the inputs of the text encoder. In a few-shot learning scenario of the downstream task, MLE training can lead the context vector to over-fit dominant image features in the training data. This overfitting can potentially harm the generalization ability, especially in the presence of a distribution shift between the training and test datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06799","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/2401.06799/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":"2401.06799","created_at":"2026-07-05T07:33:26.573766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06799v1","created_at":"2026-07-05T07:33:26.573766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06799","created_at":"2026-07-05T07:33:26.573766+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBZ2S6JG76UT","created_at":"2026-07-05T07:33:26.573766+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBZ2S6JG76UTZIV4","created_at":"2026-07-05T07:33:26.573766+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBZ2S6JG","created_at":"2026-07-05T07:33:26.573766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A","json":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A.json","graph_json":"https://pith.science/api/pith-number/RBZ2S6JG76UTZIV4OAOIT2GW7A/graph.json","events_json":"https://pith.science/api/pith-number/RBZ2S6JG76UTZIV4OAOIT2GW7A/events.json","paper":"https://pith.science/paper/RBZ2S6JG"},"agent_actions":{"view_html":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A","download_json":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A.json","view_paper":"https://pith.science/paper/RBZ2S6JG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06799&json=true","fetch_graph":"https://pith.science/api/pith-number/RBZ2S6JG76UTZIV4OAOIT2GW7A/graph.json","fetch_events":"https://pith.science/api/pith-number/RBZ2S6JG76UTZIV4OAOIT2GW7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A/action/storage_attestation","attest_author":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A/action/author_attestation","sign_citation":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A/action/citation_signature","submit_replication":"https://pith.science/pith/RBZ2S6JG76UTZIV4OAOIT2GW7A/action/replication_record"}},"created_at":"2026-07-05T07:33:26.573766+00:00","updated_at":"2026-07-05T07:33:26.573766+00:00"}