{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DARVSEPYTCIUR2HNBTGFE6P245","short_pith_number":"pith:DARVSEPY","schema_version":"1.0","canonical_sha256":"18235911f8989148e8ed0ccc5279fae7618f977332a57652def6e822db729046","source":{"kind":"arxiv","id":"2309.04790","version":1},"attestation_state":"computed","paper":{"title":"MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangyu Lei, Jiahe Lei, Jun Zhao, Kang Liu, Shizhu He, Tongxu Luo, Weihao Liu","submitted_at":"2023-09-09T13:35:01Z","abstract_excerpt":"In the real world, knowledge often exists in a multimodal and heterogeneous form. Addressing the task of question answering with hybrid data types, including text, tables, and images, is a challenging task (MMHQA). Recently, with the rise of large language models (LLM), in-context learning (ICL) has become the most popular way to solve QA problems. We propose MMHQA-ICL framework for addressing this problems, which includes stronger heterogeneous data retriever and an image caption module. Most importantly, we propose a Type-specific In-context Learning Strategy for MMHQA, enabling LLMs to leve"},"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":"2309.04790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-09T13:35:01Z","cross_cats_sorted":[],"title_canon_sha256":"0bb03d8f6068164599fd0723ff755d0065ecbda5edc0ea29205490e360a02c08","abstract_canon_sha256":"c5708e4e67dfeb05c118d59b3be83834d9bddf4eff3b3648e24984acbf423303"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:27.157183Z","signature_b64":"zEtspije5PxMdypN1umET1nLf2GrAJZUJzqu+S8DI7PkFplXXU45HPMUKox1dDWbSZuEDrlXHfQIH026gUNSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18235911f8989148e8ed0ccc5279fae7618f977332a57652def6e822db729046","last_reissued_at":"2026-07-05T06:49:27.156703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:27.156703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangyu Lei, Jiahe Lei, Jun Zhao, Kang Liu, Shizhu He, Tongxu Luo, Weihao Liu","submitted_at":"2023-09-09T13:35:01Z","abstract_excerpt":"In the real world, knowledge often exists in a multimodal and heterogeneous form. Addressing the task of question answering with hybrid data types, including text, tables, and images, is a challenging task (MMHQA). Recently, with the rise of large language models (LLM), in-context learning (ICL) has become the most popular way to solve QA problems. We propose MMHQA-ICL framework for addressing this problems, which includes stronger heterogeneous data retriever and an image caption module. Most importantly, we propose a Type-specific In-context Learning Strategy for MMHQA, enabling LLMs to leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04790","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/2309.04790/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":"2309.04790","created_at":"2026-07-05T06:49:27.156766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04790v1","created_at":"2026-07-05T06:49:27.156766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04790","created_at":"2026-07-05T06:49:27.156766+00:00"},{"alias_kind":"pith_short_12","alias_value":"DARVSEPYTCIU","created_at":"2026-07-05T06:49:27.156766+00:00"},{"alias_kind":"pith_short_16","alias_value":"DARVSEPYTCIUR2HN","created_at":"2026-07-05T06:49:27.156766+00:00"},{"alias_kind":"pith_short_8","alias_value":"DARVSEPY","created_at":"2026-07-05T06:49:27.156766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.13415","citing_title":"Attention Grounded Enhancement for Visual Document Retrieval","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12081","citing_title":"Human-Inspired Context-Selective Multimodal Memory for Social Robots","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245","json":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245.json","graph_json":"https://pith.science/api/pith-number/DARVSEPYTCIUR2HNBTGFE6P245/graph.json","events_json":"https://pith.science/api/pith-number/DARVSEPYTCIUR2HNBTGFE6P245/events.json","paper":"https://pith.science/paper/DARVSEPY"},"agent_actions":{"view_html":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245","download_json":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245.json","view_paper":"https://pith.science/paper/DARVSEPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04790&json=true","fetch_graph":"https://pith.science/api/pith-number/DARVSEPYTCIUR2HNBTGFE6P245/graph.json","fetch_events":"https://pith.science/api/pith-number/DARVSEPYTCIUR2HNBTGFE6P245/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245/action/storage_attestation","attest_author":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245/action/author_attestation","sign_citation":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245/action/citation_signature","submit_replication":"https://pith.science/pith/DARVSEPYTCIUR2HNBTGFE6P245/action/replication_record"}},"created_at":"2026-07-05T06:49:27.156766+00:00","updated_at":"2026-07-05T06:49:27.156766+00:00"}