{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I5OBOOBFIDUBUKY7QVPJCRZEAN","short_pith_number":"pith:I5OBOOBF","schema_version":"1.0","canonical_sha256":"475c17382540e81a2b1f855e914724035301effba3be551cb3bad7292137156b","source":{"kind":"arxiv","id":"2411.17558","version":1},"attestation_state":"computed","paper":{"title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haohao Luo, Jiayi Kuang, Jingyou Xie, Ronghao Li, Xianfeng Cheng, Xika Lin, Yinghui Li, Ying Shen, Zhe Xu","submitted_at":"2024-11-26T16:21:03Z","abstract_excerpt":"Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is to provide an overview of the development of VQA and a detailed description of the latest models with high timeliness. This survey gives an up-to-date synthesis of natural language understanding of images and text, as well as the knowledge reasoning module based on image-question information on the core VQA tasks. In addition, we elaborate on recent advances"},"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":"2411.17558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T16:21:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"492ad469afbad66762f9a7c43667696024566e3eef44b8ffab96c54a4531d2a9","abstract_canon_sha256":"28b679baa4da05ed4625f7584b1b697caa5317f4235020762afa2e9781ace9e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:48.944746Z","signature_b64":"Svyb9dt8hU5grUh404AWRRv/686IaeazifHipALAdCpnaJ3CnQB97mxkOoLguX4Aj/P/7WU7Fd9R6+EjpulaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"475c17382540e81a2b1f855e914724035301effba3be551cb3bad7292137156b","last_reissued_at":"2026-07-05T09:40:48.944275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:48.944275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haohao Luo, Jiayi Kuang, Jingyou Xie, Ronghao Li, Xianfeng Cheng, Xika Lin, Yinghui Li, Ying Shen, Zhe Xu","submitted_at":"2024-11-26T16:21:03Z","abstract_excerpt":"Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is to provide an overview of the development of VQA and a detailed description of the latest models with high timeliness. This survey gives an up-to-date synthesis of natural language understanding of images and text, as well as the knowledge reasoning module based on image-question information on the core VQA tasks. In addition, we elaborate on recent advances"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17558","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/2411.17558/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":"2411.17558","created_at":"2026-07-05T09:40:48.944341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17558v1","created_at":"2026-07-05T09:40:48.944341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17558","created_at":"2026-07-05T09:40:48.944341+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5OBOOBFIDUB","created_at":"2026-07-05T09:40:48.944341+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5OBOOBFIDUBUKY7","created_at":"2026-07-05T09:40:48.944341+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5OBOOBF","created_at":"2026-07-05T09:40:48.944341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07184","citing_title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN","json":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN.json","graph_json":"https://pith.science/api/pith-number/I5OBOOBFIDUBUKY7QVPJCRZEAN/graph.json","events_json":"https://pith.science/api/pith-number/I5OBOOBFIDUBUKY7QVPJCRZEAN/events.json","paper":"https://pith.science/paper/I5OBOOBF"},"agent_actions":{"view_html":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN","download_json":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN.json","view_paper":"https://pith.science/paper/I5OBOOBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17558&json=true","fetch_graph":"https://pith.science/api/pith-number/I5OBOOBFIDUBUKY7QVPJCRZEAN/graph.json","fetch_events":"https://pith.science/api/pith-number/I5OBOOBFIDUBUKY7QVPJCRZEAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/action/storage_attestation","attest_author":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/action/author_attestation","sign_citation":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/action/citation_signature","submit_replication":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/action/replication_record"}},"created_at":"2026-07-05T09:40:48.944341+00:00","updated_at":"2026-07-05T09:40:48.944341+00:00"}