{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WNY54GOO4UWGVJTPSIDGV5FGKI","short_pith_number":"pith:WNY54GOO","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"},"canonical_sha256":"b371de19cee52c6aa66f92066af4a652021385f0ad01646561e2da7ad2166a1d","source":{"kind":"arxiv","id":"2305.16556","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16556","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16556v3","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16556","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"WNY54GOO4UWG","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"WNY54GOO4UWGVJTP","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"WNY54GOO","created_at":"2026-07-05T08:11:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WNY54GOO4UWGVJTPSIDGV5FGKI","target":"record","payload":{"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"},"canonical_sha256":"b371de19cee52c6aa66f92066af4a652021385f0ad01646561e2da7ad2166a1d","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"},"source_kind":"arxiv","source_id":"2305.16556","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wEBAORggI6oWCUKRWDKOjPuYxXeqVTBLR3n9v0kFgptiA5WneZAkvfd0oEPRDmiXOPmmSBfoLbJXmqTWa8iZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:06:40.727388Z"},"content_sha256":"0bc4276574f9e5606d663165cef383f546b5ff439b5486766d8d40c652238b66","schema_version":"1.0","event_id":"sha256:0bc4276574f9e5606d663165cef383f546b5ff439b5486766d8d40c652238b66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WNY54GOO4UWGVJTPSIDGV5FGKI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z+JTgYE/gK5tMVvqDv9ZC2TXJJZgakCbHVfoj0iYdV6RTlVYBfGFH97MIM4LrIO5xiVTwXjVmcJwI+6Nw6CuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:06:40.727895Z"},"content_sha256":"49a2fb9a5791de7a87bc1fa97e56a908fd0a9f9f6c1876f86e2c66c71d94da81","schema_version":"1.0","event_id":"sha256:49a2fb9a5791de7a87bc1fa97e56a908fd0a9f9f6c1876f86e2c66c71d94da81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/bundle.json","state_url":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T13:06:40Z","links":{"resolver":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI","bundle":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/bundle.json","state":"https://pith.science/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WNY54GOO4UWGVJTPSIDGV5FGKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WNY54GOO4UWGVJTPSIDGV5FGKI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"738db6a3414e22e55b92f3c7a733e592a3ff5f65f98092fde11035eaff3fdd64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T00:50:09Z","title_canon_sha256":"0103d26a6471ce1d2fe102cbe1428ec68a2d7d1a82a76116e666497cf1555a90"},"schema_version":"1.0","source":{"id":"2305.16556","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16556","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16556v3","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16556","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"WNY54GOO4UWG","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"WNY54GOO4UWGVJTP","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"WNY54GOO","created_at":"2026-07-05T08:11:38Z"}],"graph_snapshots":[{"event_id":"sha256:49a2fb9a5791de7a87bc1fa97e56a908fd0a9f9f6c1876f86e2c66c71d94da81","target":"graph","created_at":"2026-07-05T08:11:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.16556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Sayna Ebrahimi, Sercan O. Arik, Tomas Pfister, Yihe Dong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T00:50:09Z","title":"LANISTR: Multimodal Learning from Structured and Unstructured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16556","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0bc4276574f9e5606d663165cef383f546b5ff439b5486766d8d40c652238b66","target":"record","created_at":"2026-07-05T08:11:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"738db6a3414e22e55b92f3c7a733e592a3ff5f65f98092fde11035eaff3fdd64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T00:50:09Z","title_canon_sha256":"0103d26a6471ce1d2fe102cbe1428ec68a2d7d1a82a76116e666497cf1555a90"},"schema_version":"1.0","source":{"id":"2305.16556","kind":"arxiv","version":3}},"canonical_sha256":"b371de19cee52c6aa66f92066af4a652021385f0ad01646561e2da7ad2166a1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b371de19cee52c6aa66f92066af4a652021385f0ad01646561e2da7ad2166a1d","first_computed_at":"2026-07-05T08:11:38.830474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:38.830474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HpNg/lvfNSXsjqxaOBab6b2HkUVdTsiAKz1w0M9UFCPxcqZitmgXWsUN5HKJC4PhflMB4edNXgXp5KdqGDtoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:38.830975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16556","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bc4276574f9e5606d663165cef383f546b5ff439b5486766d8d40c652238b66","sha256:49a2fb9a5791de7a87bc1fa97e56a908fd0a9f9f6c1876f86e2c66c71d94da81"],"state_sha256":"c9eec585eb7d479dbf553e6e3d05d913e78407cfc47cc972084dc596a4945cd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"191zpxPHBzuYZ1RX+LUCYn501lyWRqEyfhTHzmeJO6l2NQeDB2v8v4th1JbhqvosRHvD9X1mUS82VjHjQWQGAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:06:40.732936Z","bundle_sha256":"48e776fb495c0467ed0fe949250ccec554ce229ab6407b0ba51828878f6207c8"}}