{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VFWMLKMKHKPWSR6OQUTYBUQZTR","short_pith_number":"pith:VFWMLKMK","schema_version":"1.0","canonical_sha256":"a96cc5a98a3a9f6947ce852780d2199c4cbf044cb3f974b401e206186334a1ef","source":{"kind":"arxiv","id":"2503.00528","version":1},"attestation_state":"computed","paper":{"title":"Efficient Prompting for Continual Adaptation to Missing Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Shulei Wang, Tao Jin, Wang Lin, Weicai Yan, Yangyang Wu, Zirun Guo","submitted_at":"2025-03-01T15:09:37Z","abstract_excerpt":"Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade significantly. Current methods often aggregate various missing cases to train recovery modules or align multimodal features, resulting in suboptimal performance, high computational costs, and the risk of catastrophic forgetting in continual environments where data arrives sequentially. In this paper, we formulate the dynamic missing modality problem as a co"},"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":"2503.00528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-01T15:09:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c57ea2a58c56047d57109f1aa5555e69ddfe92c12bf975b3c91e43c565392cf2","abstract_canon_sha256":"8c6ef87e5393e5765f41eaa86a627a48a55418c0f1474491e9731ecbe5e1d39d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:24.607377Z","signature_b64":"ZQexN+LJLfjvI651GCk/eP+UOYMBK/zMDIw9NjI60mvsQihL81x5a2ACN3UVDpura1vUwzhQMEqMxh8tuW99Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a96cc5a98a3a9f6947ce852780d2199c4cbf044cb3f974b401e206186334a1ef","last_reissued_at":"2026-07-05T10:22:24.606825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:24.606825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Prompting for Continual Adaptation to Missing Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Shulei Wang, Tao Jin, Wang Lin, Weicai Yan, Yangyang Wu, Zirun Guo","submitted_at":"2025-03-01T15:09:37Z","abstract_excerpt":"Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade significantly. Current methods often aggregate various missing cases to train recovery modules or align multimodal features, resulting in suboptimal performance, high computational costs, and the risk of catastrophic forgetting in continual environments where data arrives sequentially. In this paper, we formulate the dynamic missing modality problem as a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00528","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/2503.00528/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":"2503.00528","created_at":"2026-07-05T10:22:24.606889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00528v1","created_at":"2026-07-05T10:22:24.606889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00528","created_at":"2026-07-05T10:22:24.606889+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFWMLKMKHKPW","created_at":"2026-07-05T10:22:24.606889+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFWMLKMKHKPWSR6O","created_at":"2026-07-05T10:22:24.606889+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFWMLKMK","created_at":"2026-07-05T10:22:24.606889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR","json":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR.json","graph_json":"https://pith.science/api/pith-number/VFWMLKMKHKPWSR6OQUTYBUQZTR/graph.json","events_json":"https://pith.science/api/pith-number/VFWMLKMKHKPWSR6OQUTYBUQZTR/events.json","paper":"https://pith.science/paper/VFWMLKMK"},"agent_actions":{"view_html":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR","download_json":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR.json","view_paper":"https://pith.science/paper/VFWMLKMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00528&json=true","fetch_graph":"https://pith.science/api/pith-number/VFWMLKMKHKPWSR6OQUTYBUQZTR/graph.json","fetch_events":"https://pith.science/api/pith-number/VFWMLKMKHKPWSR6OQUTYBUQZTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR/action/storage_attestation","attest_author":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR/action/author_attestation","sign_citation":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR/action/citation_signature","submit_replication":"https://pith.science/pith/VFWMLKMKHKPWSR6OQUTYBUQZTR/action/replication_record"}},"created_at":"2026-07-05T10:22:24.606889+00:00","updated_at":"2026-07-05T10:22:24.606889+00:00"}