{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WREO76KCMVHEYODBOGGQRCR4WW","short_pith_number":"pith:WREO76KC","schema_version":"1.0","canonical_sha256":"b448eff942654e4c3861718d088a3cb596516b5ab8b4d07c99cfda087be12d3e","source":{"kind":"arxiv","id":"2103.05677","version":1},"attestation_state":"computed","paper":{"title":"SMIL: Multimodal Learning with Severely Missing Modality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cathy Wu, Jian Ren, Long Zhao, Mengmeng Ma, Sergey Tulyakov, Xi Peng","submitted_at":"2021-03-09T19:27:08Z","abstract_excerpt":"A common assumption in multimodal learning is the completeness of training data, i.e., full modalities are available in all training examples. Although there exists research endeavor in developing novel methods to tackle the incompleteness of testing data, e.g., modalities are partially missing in testing examples, few of them can handle incomplete training modalities. The problem becomes even more challenging if considering the case of severely missing, e.g., 90% training examples may have incomplete modalities. For the first time in the literature, this paper formally studies multimodal lear"},"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":"2103.05677","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-09T19:27:08Z","cross_cats_sorted":[],"title_canon_sha256":"3ac315014beb6218c79e04b29a0e51566a5169a3bb372f4bfa44314b7d5fbfc8","abstract_canon_sha256":"a1dfc389394afcc770769e66a4dc62f673ac9abbbad1e477b77ef28b1629ee5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:56.817301Z","signature_b64":"DPMTy3ljf+dTHXr+SXsgdedoRR7CpnLTYyZW355axJmdcpfGpfgbqcOBsoGkUXAX+EZqvsG7yIckJH+FmBN6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b448eff942654e4c3861718d088a3cb596516b5ab8b4d07c99cfda087be12d3e","last_reissued_at":"2026-07-05T02:21:56.816757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:56.816757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMIL: Multimodal Learning with Severely Missing Modality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cathy Wu, Jian Ren, Long Zhao, Mengmeng Ma, Sergey Tulyakov, Xi Peng","submitted_at":"2021-03-09T19:27:08Z","abstract_excerpt":"A common assumption in multimodal learning is the completeness of training data, i.e., full modalities are available in all training examples. Although there exists research endeavor in developing novel methods to tackle the incompleteness of testing data, e.g., modalities are partially missing in testing examples, few of them can handle incomplete training modalities. The problem becomes even more challenging if considering the case of severely missing, e.g., 90% training examples may have incomplete modalities. For the first time in the literature, this paper formally studies multimodal lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05677","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/2103.05677/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":"2103.05677","created_at":"2026-07-05T02:21:56.816821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05677v1","created_at":"2026-07-05T02:21:56.816821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05677","created_at":"2026-07-05T02:21:56.816821+00:00"},{"alias_kind":"pith_short_12","alias_value":"WREO76KCMVHE","created_at":"2026-07-05T02:21:56.816821+00:00"},{"alias_kind":"pith_short_16","alias_value":"WREO76KCMVHEYODB","created_at":"2026-07-05T02:21:56.816821+00:00"},{"alias_kind":"pith_short_8","alias_value":"WREO76KC","created_at":"2026-07-05T02:21:56.816821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30994","citing_title":"Dynamic Interaction-Aware and Causality-Disentangled Framework for Multimodal Sentiment Analysis","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW","json":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW.json","graph_json":"https://pith.science/api/pith-number/WREO76KCMVHEYODBOGGQRCR4WW/graph.json","events_json":"https://pith.science/api/pith-number/WREO76KCMVHEYODBOGGQRCR4WW/events.json","paper":"https://pith.science/paper/WREO76KC"},"agent_actions":{"view_html":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW","download_json":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW.json","view_paper":"https://pith.science/paper/WREO76KC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05677&json=true","fetch_graph":"https://pith.science/api/pith-number/WREO76KCMVHEYODBOGGQRCR4WW/graph.json","fetch_events":"https://pith.science/api/pith-number/WREO76KCMVHEYODBOGGQRCR4WW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW/action/storage_attestation","attest_author":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW/action/author_attestation","sign_citation":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW/action/citation_signature","submit_replication":"https://pith.science/pith/WREO76KCMVHEYODBOGGQRCR4WW/action/replication_record"}},"created_at":"2026-07-05T02:21:56.816821+00:00","updated_at":"2026-07-05T02:21:56.816821+00:00"}