{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WNY54GOO4UWGVJTPSIDGV5FGKI","short_pith_number":"pith:WNY54GOO","schema_version":"1.0","canonical_sha256":"b371de19cee52c6aa66f92066af4a652021385f0ad01646561e2da7ad2166a1d","source":{"kind":"arxiv","id":"2305.16556","version":3},"attestation_state":"computed","paper":{"title":"LANISTR: Multimodal Learning from Structured and Unstructured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sayna Ebrahimi, Sercan O. Arik, Tomas Pfister, Yihe Dong","submitted_at":"2023-05-26T00:50:09Z","abstract_excerpt":"Multimodal large-scale pretraining has shown impressive performance for unstructured data such as language and image. However, a prevalent real-world scenario involves structured data types, tabular and time-series, along with unstructured data. Such scenarios have been understudied. To bridge this gap, we propose LANISTR, an attention-based framework to learn from LANguage, Image, and STRuctured data. The core of LANISTR's methodology is rooted in \\textit{masking-based} training applied across both unimodal and multimodal levels. In particular, we introduce a new similarity-based multimodal m"},"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":"2305.16556","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T00:50:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0103d26a6471ce1d2fe102cbe1428ec68a2d7d1a82a76116e666497cf1555a90","abstract_canon_sha256":"738db6a3414e22e55b92f3c7a733e592a3ff5f65f98092fde11035eaff3fdd64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:38.830975Z","signature_b64":"HpNg/lvfNSXsjqxaOBab6b2HkUVdTsiAKz1w0M9UFCPxcqZitmgXWsUN5HKJC4PhflMB4edNXgXp5KdqGDtoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b371de19cee52c6aa66f92066af4a652021385f0ad01646561e2da7ad2166a1d","last_reissued_at":"2026-07-05T08:11:38.830474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:38.830474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LANISTR: Multimodal Learning from Structured and Unstructured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sayna Ebrahimi, Sercan O. Arik, Tomas Pfister, Yihe Dong","submitted_at":"2023-05-26T00:50:09Z","abstract_excerpt":"Multimodal large-scale pretraining has shown impressive performance for unstructured data such as language and image. However, a prevalent real-world scenario involves structured data types, tabular and time-series, along with unstructured data. Such scenarios have been understudied. To bridge this gap, we propose LANISTR, an attention-based framework to learn from LANguage, Image, and STRuctured data. The core of LANISTR's methodology is rooted in \\textit{masking-based} training applied across both unimodal and multimodal levels. In particular, we introduce a new similarity-based multimodal m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16556","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/2305.16556/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":"2305.16556","created_at":"2026-07-05T08:11:38.830539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16556v3","created_at":"2026-07-05T08:11:38.830539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16556","created_at":"2026-07-05T08:11:38.830539+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNY54GOO4UWG","created_at":"2026-07-05T08:11:38.830539+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNY54GOO4UWGVJTP","created_at":"2026-07-05T08:11:38.830539+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNY54GOO","created_at":"2026-07-05T08:11:38.830539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06867","citing_title":"Multi-FRuGaL: Multimodal Flexible Redundancy-aware Decomposed Gated Learning for Cancer Diagnosis and Prognosis","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20223","citing_title":"MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14406","citing_title":"GeoViSTA: Geospatial Vision-Tabular Transformer for Multimodal Environment Representation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10616","citing_title":"MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI","json":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI.json","graph_json":"https://pith.science/api/pith-number/WNY54GOO4UWGVJTPSIDGV5FGKI/graph.json","events_json":"https://pith.science/api/pith-number/WNY54GOO4UWGVJTPSIDGV5FGKI/events.json","paper":"https://pith.science/paper/WNY54GOO"},"agent_actions":{"view_html":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI","download_json":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI.json","view_paper":"https://pith.science/paper/WNY54GOO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16556&json=true","fetch_graph":"https://pith.science/api/pith-number/WNY54GOO4UWGVJTPSIDGV5FGKI/graph.json","fetch_events":"https://pith.science/api/pith-number/WNY54GOO4UWGVJTPSIDGV5FGKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/action/storage_attestation","attest_author":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/action/author_attestation","sign_citation":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/action/citation_signature","submit_replication":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/action/replication_record"}},"created_at":"2026-07-05T08:11:38.830539+00:00","updated_at":"2026-07-05T08:11:38.830539+00:00"}