{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LLBSM7UJ25N26XPP5R3AVG67MG","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":"ee894bf878847eb829cc59840262435e3eece21507aa2bfc7931bea0c3dbcf40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T04:09:36Z","title_canon_sha256":"2205dd8ed2d2f983311ef7869a3966180093e7efdd21bcb6ace78bcfe079572d"},"schema_version":"1.0","source":{"id":"2310.13265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13265","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13265v1","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13265","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_12","alias_value":"LLBSM7UJ25N2","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_16","alias_value":"LLBSM7UJ25N26XPP","created_at":"2026-07-05T07:03:00Z"},{"alias_kind":"pith_short_8","alias_value":"LLBSM7UJ","created_at":"2026-07-05T07:03:00Z"}],"graph_snapshots":[{"event_id":"sha256:9caa4743ec0ecd63ac9eb74446db84625f7028d89c445b73e6126d9b9307b29b","target":"graph","created_at":"2026-07-05T07:03:00Z","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/2310.13265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aishwarya Agrawal, Fengran Mo, Jian-Yun Nie, Le Zhang, Yihong Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T04:09:36Z","title":"MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13265","kind":"arxiv","version":1},"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":"sha256:6ae2ea16bb09c1b0a875c4a23b9d680ce614b845f5903525cadc16eff1aa2940","target":"record","created_at":"2026-07-05T07:03:00Z","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":"ee894bf878847eb829cc59840262435e3eece21507aa2bfc7931bea0c3dbcf40","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T04:09:36Z","title_canon_sha256":"2205dd8ed2d2f983311ef7869a3966180093e7efdd21bcb6ace78bcfe079572d"},"schema_version":"1.0","source":{"id":"2310.13265","kind":"arxiv","version":1}},"canonical_sha256":"5ac3267e89d75baf5defec760a9bdf61837868de98bb39db6a83847755b8f726","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ac3267e89d75baf5defec760a9bdf61837868de98bb39db6a83847755b8f726","first_computed_at":"2026-07-05T07:03:00.276875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:00.276875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6uezZlXEoqV0WwCGPF/gLBl3O+Zvrj62pZ45SEUm1Nvm7M6NGDeigf8Q51fdGHvOFcnXcYF0yPbyI7Sk0N2aAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:00.277381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ae2ea16bb09c1b0a875c4a23b9d680ce614b845f5903525cadc16eff1aa2940","sha256:9caa4743ec0ecd63ac9eb74446db84625f7028d89c445b73e6126d9b9307b29b"],"state_sha256":"e3d398b08a4a0e30c4474c45ca3ba5864789c875245471e9bab99da2c1ae2825"}