{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P5CB4QIDPQOP32S4626HPZMA6Q","short_pith_number":"pith:P5CB4QID","schema_version":"1.0","canonical_sha256":"7f441e41037c1cfdea5cf6bc77e580f437a1e03bc841a499d420adc03b520472","source":{"kind":"arxiv","id":"2412.04026","version":2},"attestation_state":"computed","paper":{"title":"M$^{3}$D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bobo Li, Donghong Ji, Fei Li, Hao Fei, Jiang Liu, Mingyao Zhang, Na Yang, Xinran Yang","submitted_at":"2024-12-05T10:00:58Z","abstract_excerpt":"Multimodal information extraction (IE) tasks have attracted increasing attention because many studies have shown that multimodal information benefits text information extraction. However, existing multimodal IE datasets mainly focus on sentence-level image-facilitated IE in English text, and pay little attention to video-based multimodal IE and fine-grained visual grounding. Therefore, in order to promote the development of multimodal IE, we constructed a multimodal multilingual multitask dataset, named M$^{3}$D, which has the following features: (1) It contains paired document-level text and "},"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":"2412.04026","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T10:00:58Z","cross_cats_sorted":[],"title_canon_sha256":"61bb4372c75e6a1db33c81c93ca7eb484223a2cf2d775cca37d820eff6f86a80","abstract_canon_sha256":"b2a710750412ad6b06bbdb78c6169aba0fcaec13bd0e667b8a6df652090e7695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:13.340258Z","signature_b64":"Zndv5mRWqmYxhmdr1mLqrlA3RVomQ5AZ6DzFCvl3PmLK6/fInIonG/L9AbYBjd3z6YKuBKdTtMT6FyinnMg0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f441e41037c1cfdea5cf6bc77e580f437a1e03bc841a499d420adc03b520472","last_reissued_at":"2026-07-05T09:49:13.339693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:13.339693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^{3}$D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bobo Li, Donghong Ji, Fei Li, Hao Fei, Jiang Liu, Mingyao Zhang, Na Yang, Xinran Yang","submitted_at":"2024-12-05T10:00:58Z","abstract_excerpt":"Multimodal information extraction (IE) tasks have attracted increasing attention because many studies have shown that multimodal information benefits text information extraction. However, existing multimodal IE datasets mainly focus on sentence-level image-facilitated IE in English text, and pay little attention to video-based multimodal IE and fine-grained visual grounding. Therefore, in order to promote the development of multimodal IE, we constructed a multimodal multilingual multitask dataset, named M$^{3}$D, which has the following features: (1) It contains paired document-level text and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04026","kind":"arxiv","version":2},"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/2412.04026/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":"2412.04026","created_at":"2026-07-05T09:49:13.339754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04026v2","created_at":"2026-07-05T09:49:13.339754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04026","created_at":"2026-07-05T09:49:13.339754+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5CB4QIDPQOP","created_at":"2026-07-05T09:49:13.339754+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5CB4QIDPQOP32S4","created_at":"2026-07-05T09:49:13.339754+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5CB4QID","created_at":"2026-07-05T09:49:13.339754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q","json":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q.json","graph_json":"https://pith.science/api/pith-number/P5CB4QIDPQOP32S4626HPZMA6Q/graph.json","events_json":"https://pith.science/api/pith-number/P5CB4QIDPQOP32S4626HPZMA6Q/events.json","paper":"https://pith.science/paper/P5CB4QID"},"agent_actions":{"view_html":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q","download_json":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q.json","view_paper":"https://pith.science/paper/P5CB4QID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04026&json=true","fetch_graph":"https://pith.science/api/pith-number/P5CB4QIDPQOP32S4626HPZMA6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/P5CB4QIDPQOP32S4626HPZMA6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q/action/storage_attestation","attest_author":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q/action/author_attestation","sign_citation":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q/action/citation_signature","submit_replication":"https://pith.science/pith/P5CB4QIDPQOP32S4626HPZMA6Q/action/replication_record"}},"created_at":"2026-07-05T09:49:13.339754+00:00","updated_at":"2026-07-05T09:49:13.339754+00:00"}