{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LLBSM7UJ25N26XPP5R3AVG67MG","short_pith_number":"pith:LLBSM7UJ","schema_version":"1.0","canonical_sha256":"5ac3267e89d75baf5defec760a9bdf61837868de98bb39db6a83847755b8f726","source":{"kind":"arxiv","id":"2310.13265","version":1},"attestation_state":"computed","paper":{"title":"MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aishwarya Agrawal, Fengran Mo, Jian-Yun Nie, Le Zhang, Yihong Wu","submitted_at":"2023-10-20T04:09:36Z","abstract_excerpt":"Multi-modal open-domain question answering typically requires evidence retrieval from databases across diverse modalities, such as images, tables, passages, etc. Even Large Language Models (LLMs) like GPT-4 fall short in this task. To enable LLMs to tackle the task in a zero-shot manner, we introduce MoqaGPT, a straightforward and flexible framework. Using a divide-and-conquer strategy that bypasses intricate multi-modality ranking, our framework can accommodate new modalities and seamlessly transition to new models for the task. Built upon LLMs, MoqaGPT retrieves and extracts answers from eac"},"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":"2310.13265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T04:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"2205dd8ed2d2f983311ef7869a3966180093e7efdd21bcb6ace78bcfe079572d","abstract_canon_sha256":"ee894bf878847eb829cc59840262435e3eece21507aa2bfc7931bea0c3dbcf40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:00.277381Z","signature_b64":"6uezZlXEoqV0WwCGPF/gLBl3O+Zvrj62pZ45SEUm1Nvm7M6NGDeigf8Q51fdGHvOFcnXcYF0yPbyI7Sk0N2aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ac3267e89d75baf5defec760a9bdf61837868de98bb39db6a83847755b8f726","last_reissued_at":"2026-07-05T07:03:00.276875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:00.276875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aishwarya Agrawal, Fengran Mo, Jian-Yun Nie, Le Zhang, Yihong Wu","submitted_at":"2023-10-20T04:09:36Z","abstract_excerpt":"Multi-modal open-domain question answering typically requires evidence retrieval from databases across diverse modalities, such as images, tables, passages, etc. Even Large Language Models (LLMs) like GPT-4 fall short in this task. To enable LLMs to tackle the task in a zero-shot manner, we introduce MoqaGPT, a straightforward and flexible framework. Using a divide-and-conquer strategy that bypasses intricate multi-modality ranking, our framework can accommodate new modalities and seamlessly transition to new models for the task. Built upon LLMs, MoqaGPT retrieves and extracts answers from eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13265","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/2310.13265/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":"2310.13265","created_at":"2026-07-05T07:03:00.276942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13265v1","created_at":"2026-07-05T07:03:00.276942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13265","created_at":"2026-07-05T07:03:00.276942+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLBSM7UJ25N2","created_at":"2026-07-05T07:03:00.276942+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLBSM7UJ25N26XPP","created_at":"2026-07-05T07:03:00.276942+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLBSM7UJ","created_at":"2026-07-05T07:03:00.276942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04641","citing_title":"Bridge the Last-Mile Gap to Semantic Analytics: Compiling Natural-Language Queries into Semantic Operator Pipelines","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG","json":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG.json","graph_json":"https://pith.science/api/pith-number/LLBSM7UJ25N26XPP5R3AVG67MG/graph.json","events_json":"https://pith.science/api/pith-number/LLBSM7UJ25N26XPP5R3AVG67MG/events.json","paper":"https://pith.science/paper/LLBSM7UJ"},"agent_actions":{"view_html":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG","download_json":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG.json","view_paper":"https://pith.science/paper/LLBSM7UJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13265&json=true","fetch_graph":"https://pith.science/api/pith-number/LLBSM7UJ25N26XPP5R3AVG67MG/graph.json","fetch_events":"https://pith.science/api/pith-number/LLBSM7UJ25N26XPP5R3AVG67MG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG/action/storage_attestation","attest_author":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG/action/author_attestation","sign_citation":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG/action/citation_signature","submit_replication":"https://pith.science/pith/LLBSM7UJ25N26XPP5R3AVG67MG/action/replication_record"}},"created_at":"2026-07-05T07:03:00.276942+00:00","updated_at":"2026-07-05T07:03:00.276942+00:00"}