{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BP4I6NPFCKBDCO3MDVIDHLTZPU","short_pith_number":"pith:BP4I6NPF","schema_version":"1.0","canonical_sha256":"0bf88f35e51282313b6c1d5033ae797d130b261907e1b0f42a2c144637a59baf","source":{"kind":"arxiv","id":"2310.06383","version":1},"attestation_state":"computed","paper":{"title":"What Makes for Robust Multi-Modal Models in the Face of Missing Modalities?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenzhuang Du, Hang Zhao, Siting Li, Yue Zhao, Yu Huang","submitted_at":"2023-10-10T07:47:57Z","abstract_excerpt":"With the growing success of multi-modal learning, research on the robustness of multi-modal models, especially when facing situations with missing modalities, is receiving increased attention. Nevertheless, previous studies in this domain exhibit certain limitations, as they often lack theoretical insights or their methodologies are tied to specific network architectures or modalities. We model the scenarios of multi-modal models encountering missing modalities from an information-theoretic perspective and illustrate that the performance ceiling in such scenarios can be approached by efficient"},"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":"2310.06383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-10T07:47:57Z","cross_cats_sorted":[],"title_canon_sha256":"761a79e5d40e71cdef93e50bc875b2959bd85966fb41032c4338bb1c10150a5c","abstract_canon_sha256":"3154d4077fb007859d3587b9000e437fe75127bd3c02a2d56d1d088341aa172b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:10.478602Z","signature_b64":"9RPnrtc2ZKnOwRdv5nFcJS4CmpPbMH4/dBb7VvkhyI9AEVhgh8PEl0kODWeIPubSMpgTM24HzjAhs6d9C4WFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf88f35e51282313b6c1d5033ae797d130b261907e1b0f42a2c144637a59baf","last_reissued_at":"2026-07-05T06:59:10.478070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:10.478070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes for Robust Multi-Modal Models in the Face of Missing Modalities?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenzhuang Du, Hang Zhao, Siting Li, Yue Zhao, Yu Huang","submitted_at":"2023-10-10T07:47:57Z","abstract_excerpt":"With the growing success of multi-modal learning, research on the robustness of multi-modal models, especially when facing situations with missing modalities, is receiving increased attention. Nevertheless, previous studies in this domain exhibit certain limitations, as they often lack theoretical insights or their methodologies are tied to specific network architectures or modalities. We model the scenarios of multi-modal models encountering missing modalities from an information-theoretic perspective and illustrate that the performance ceiling in such scenarios can be approached by efficient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06383","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/2310.06383/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":"2310.06383","created_at":"2026-07-05T06:59:10.478125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06383v1","created_at":"2026-07-05T06:59:10.478125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06383","created_at":"2026-07-05T06:59:10.478125+00:00"},{"alias_kind":"pith_short_12","alias_value":"BP4I6NPFCKBD","created_at":"2026-07-05T06:59:10.478125+00:00"},{"alias_kind":"pith_short_16","alias_value":"BP4I6NPFCKBDCO3M","created_at":"2026-07-05T06:59:10.478125+00:00"},{"alias_kind":"pith_short_8","alias_value":"BP4I6NPF","created_at":"2026-07-05T06:59:10.478125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11186","citing_title":"AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU","json":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU.json","graph_json":"https://pith.science/api/pith-number/BP4I6NPFCKBDCO3MDVIDHLTZPU/graph.json","events_json":"https://pith.science/api/pith-number/BP4I6NPFCKBDCO3MDVIDHLTZPU/events.json","paper":"https://pith.science/paper/BP4I6NPF"},"agent_actions":{"view_html":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU","download_json":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU.json","view_paper":"https://pith.science/paper/BP4I6NPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06383&json=true","fetch_graph":"https://pith.science/api/pith-number/BP4I6NPFCKBDCO3MDVIDHLTZPU/graph.json","fetch_events":"https://pith.science/api/pith-number/BP4I6NPFCKBDCO3MDVIDHLTZPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU/action/storage_attestation","attest_author":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU/action/author_attestation","sign_citation":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU/action/citation_signature","submit_replication":"https://pith.science/pith/BP4I6NPFCKBDCO3MDVIDHLTZPU/action/replication_record"}},"created_at":"2026-07-05T06:59:10.478125+00:00","updated_at":"2026-07-05T06:59:10.478125+00:00"}