{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H7EBNUX5LNJW5GKXURLK3DN2FL","short_pith_number":"pith:H7EBNUX5","schema_version":"1.0","canonical_sha256":"3fc816d2fd5b536e9957a456ad8dba2ae6e1f533debae7150630cfa07c6e4055","source":{"kind":"arxiv","id":"2210.02390","version":3},"attestation_state":"computed","paper":{"title":"Bayesian Prompt Learning for Image-Language Model Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Bulat, Brais Martinez, Cees G. M. Snoek, Enrique Sanchez, Georgios Tzimiropoulos, Mohammad Mahdi Derakhshani, Victor Guilherme Turrisi da Costa","submitted_at":"2022-10-05T17:05:56Z","abstract_excerpt":"Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest, and optimizes an Empirical Risk Minimization objective. However, Empirical Risk Minimization is known to suffer from distributional shifts which hurt generalizability to prompts unseen during training. By leveraging the regularization ability of Bayesian methods, we frame prompt learning from the Bayesian perspective and formulate it as a variational inferen"},"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":"2210.02390","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T17:05:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c4436fdea5afab2f00112b8ede17a7f848e6927af02194c7abbce962eb09244a","abstract_canon_sha256":"3f6a105a7362a68efa1aeb3c052a9bd3688901f2d92a74b6b656e3af7833adda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:57.183962Z","signature_b64":"YgRL9fEitVCVZWU6m0j5PtgFWPsXU7HfFnKWhoFj/bWmL+PrG6rZXe8RKkN4Dh1WXsqe1NIsuPl4vT+cgG9wCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fc816d2fd5b536e9957a456ad8dba2ae6e1f533debae7150630cfa07c6e4055","last_reissued_at":"2026-07-05T06:42:57.183452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:57.183452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Prompt Learning for Image-Language Model Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Bulat, Brais Martinez, Cees G. M. Snoek, Enrique Sanchez, Georgios Tzimiropoulos, Mohammad Mahdi Derakhshani, Victor Guilherme Turrisi da Costa","submitted_at":"2022-10-05T17:05:56Z","abstract_excerpt":"Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest, and optimizes an Empirical Risk Minimization objective. However, Empirical Risk Minimization is known to suffer from distributional shifts which hurt generalizability to prompts unseen during training. By leveraging the regularization ability of Bayesian methods, we frame prompt learning from the Bayesian perspective and formulate it as a variational inferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02390","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/2210.02390/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":"2210.02390","created_at":"2026-07-05T06:42:57.183519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02390v3","created_at":"2026-07-05T06:42:57.183519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02390","created_at":"2026-07-05T06:42:57.183519+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7EBNUX5LNJW","created_at":"2026-07-05T06:42:57.183519+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7EBNUX5LNJW5GKX","created_at":"2026-07-05T06:42:57.183519+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7EBNUX5","created_at":"2026-07-05T06:42:57.183519+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10575","citing_title":"Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL","json":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL.json","graph_json":"https://pith.science/api/pith-number/H7EBNUX5LNJW5GKXURLK3DN2FL/graph.json","events_json":"https://pith.science/api/pith-number/H7EBNUX5LNJW5GKXURLK3DN2FL/events.json","paper":"https://pith.science/paper/H7EBNUX5"},"agent_actions":{"view_html":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL","download_json":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL.json","view_paper":"https://pith.science/paper/H7EBNUX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02390&json=true","fetch_graph":"https://pith.science/api/pith-number/H7EBNUX5LNJW5GKXURLK3DN2FL/graph.json","fetch_events":"https://pith.science/api/pith-number/H7EBNUX5LNJW5GKXURLK3DN2FL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL/action/storage_attestation","attest_author":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL/action/author_attestation","sign_citation":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL/action/citation_signature","submit_replication":"https://pith.science/pith/H7EBNUX5LNJW5GKXURLK3DN2FL/action/replication_record"}},"created_at":"2026-07-05T06:42:57.183519+00:00","updated_at":"2026-07-05T06:42:57.183519+00:00"}