{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2LETVDU53HL6ZUYWD55JRVZIJ4","short_pith_number":"pith:2LETVDU5","schema_version":"1.0","canonical_sha256":"d2c93a8e9dd9d7ecd3161f7a98d7284f04735ca4125bd88dadf899212f727b0b","source":{"kind":"arxiv","id":"2412.07030","version":5},"attestation_state":"computed","paper":{"title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amirhossein Abaskohi, Giuseppe Carenini, Issam H. Laradji, Spandana Gella","submitted_at":"2024-12-09T22:35:44Z","abstract_excerpt":"Multimodal multihop question answering (MMQA) requires reasoning over images and text from multiple sources. Despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets. Existing methods focus on single-hop, single-modality, or short texts, limiting real-world applications like interpreting educational documents with long, multimodal content. To fill this gap, we introduce FM2DS, the first framework for creating a high-quality dataset for MMQA. Our approach consists of a 5-stage pipeline that involves acquiring relevant multimoda"},"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":"2412.07030","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T22:35:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"title_canon_sha256":"ee9690e7dc904f63c2bd208a2ecde3dccb95d8740f75cb23dcf94a496e8fcc2a","abstract_canon_sha256":"4e3dee7bfff1f3e1c69b6942f4021e89e8eef35e4e2746509ac143bf47ada165"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:14.563541Z","signature_b64":"K9wAGrJ7OcH9P7RaMyyIpBohP9Gzy5r24gH7va53wzHsYbNzvJAZck/8HAUY1BAypdfW4GcpUqgdkfpr+j77Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2c93a8e9dd9d7ecd3161f7a98d7284f04735ca4125bd88dadf899212f727b0b","last_reissued_at":"2026-07-05T12:11:14.563003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:14.563003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amirhossein Abaskohi, Giuseppe Carenini, Issam H. Laradji, Spandana Gella","submitted_at":"2024-12-09T22:35:44Z","abstract_excerpt":"Multimodal multihop question answering (MMQA) requires reasoning over images and text from multiple sources. Despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets. Existing methods focus on single-hop, single-modality, or short texts, limiting real-world applications like interpreting educational documents with long, multimodal content. To fill this gap, we introduce FM2DS, the first framework for creating a high-quality dataset for MMQA. Our approach consists of a 5-stage pipeline that involves acquiring relevant multimoda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07030","kind":"arxiv","version":5},"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/2412.07030/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":"2412.07030","created_at":"2026-07-05T12:11:14.563070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07030v5","created_at":"2026-07-05T12:11:14.563070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07030","created_at":"2026-07-05T12:11:14.563070+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LETVDU53HL6","created_at":"2026-07-05T12:11:14.563070+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LETVDU53HL6ZUYW","created_at":"2026-07-05T12:11:14.563070+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LETVDU5","created_at":"2026-07-05T12:11:14.563070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25343","citing_title":"Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25343","citing_title":"Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02794","citing_title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4","json":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4.json","graph_json":"https://pith.science/api/pith-number/2LETVDU53HL6ZUYWD55JRVZIJ4/graph.json","events_json":"https://pith.science/api/pith-number/2LETVDU53HL6ZUYWD55JRVZIJ4/events.json","paper":"https://pith.science/paper/2LETVDU5"},"agent_actions":{"view_html":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4","download_json":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4.json","view_paper":"https://pith.science/paper/2LETVDU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07030&json=true","fetch_graph":"https://pith.science/api/pith-number/2LETVDU53HL6ZUYWD55JRVZIJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/2LETVDU53HL6ZUYWD55JRVZIJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4/action/storage_attestation","attest_author":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4/action/author_attestation","sign_citation":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4/action/citation_signature","submit_replication":"https://pith.science/pith/2LETVDU53HL6ZUYWD55JRVZIJ4/action/replication_record"}},"created_at":"2026-07-05T12:11:14.563070+00:00","updated_at":"2026-07-05T12:11:14.563070+00:00"}