{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5HD3IPHBCC2MYKYW66BRWH24HD","short_pith_number":"pith:5HD3IPHB","schema_version":"1.0","canonical_sha256":"e9c7b43ce110b4cc2b16f7831b1f5c38deb9f775c207fe47ea818eba6081f139","source":{"kind":"arxiv","id":"2412.18351","version":2},"attestation_state":"computed","paper":{"title":"Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Li, Peng Yang, Zhenqi Wang, Zhongjian Hu","submitted_at":"2024-12-24T11:24:56Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive results in knowledge-based Visual Question Answering (VQA). However existing methods still have challenges: the inability to use external tools autonomously, and the inability to work in teams. Humans tend to know whether they need to use external tools when they encounter a new question, e.g., they tend to be able to give a direct answer to a familiar question, whereas they tend to use tools such as search engines when they encounter an unfamiliar question. In addition, humans also tend to collaborate and discuss with others to get better "},"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":"2412.18351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T11:24:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"36620f05a3ede7e75594a985fc10b9b8033121c50ae0370be4682f4f64634e98","abstract_canon_sha256":"ad944c475b147cba107aa48dba9719cbb18873dd41d8fdf9e68955ba6c8c9219"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:49.385761Z","signature_b64":"Ztr2E5M5GEpn8kx4Uv54J8/BcnHXyTkYIN4iuxBY/6RVsijOKMPoBzcMJdnYAJJyQTz7mxstBDhxAIwm7VIbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9c7b43ce110b4cc2b16f7831b1f5c38deb9f775c207fe47ea818eba6081f139","last_reissued_at":"2026-07-05T11:49:49.385198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:49.385198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Li, Peng Yang, Zhenqi Wang, Zhongjian Hu","submitted_at":"2024-12-24T11:24:56Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive results in knowledge-based Visual Question Answering (VQA). However existing methods still have challenges: the inability to use external tools autonomously, and the inability to work in teams. Humans tend to know whether they need to use external tools when they encounter a new question, e.g., they tend to be able to give a direct answer to a familiar question, whereas they tend to use tools such as search engines when they encounter an unfamiliar question. In addition, humans also tend to collaborate and discuss with others to get better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18351","kind":"arxiv","version":2},"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/2412.18351/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":"2412.18351","created_at":"2026-07-05T11:49:49.385269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18351v2","created_at":"2026-07-05T11:49:49.385269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18351","created_at":"2026-07-05T11:49:49.385269+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HD3IPHBCC2M","created_at":"2026-07-05T11:49:49.385269+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HD3IPHBCC2MYKYW","created_at":"2026-07-05T11:49:49.385269+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HD3IPHB","created_at":"2026-07-05T11:49:49.385269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16674","citing_title":"Zero-Shot Anomaly Detection in Battery Thermal Images Using Visual Question Answering with Prior Knowledge","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD","json":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD.json","graph_json":"https://pith.science/api/pith-number/5HD3IPHBCC2MYKYW66BRWH24HD/graph.json","events_json":"https://pith.science/api/pith-number/5HD3IPHBCC2MYKYW66BRWH24HD/events.json","paper":"https://pith.science/paper/5HD3IPHB"},"agent_actions":{"view_html":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD","download_json":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD.json","view_paper":"https://pith.science/paper/5HD3IPHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18351&json=true","fetch_graph":"https://pith.science/api/pith-number/5HD3IPHBCC2MYKYW66BRWH24HD/graph.json","fetch_events":"https://pith.science/api/pith-number/5HD3IPHBCC2MYKYW66BRWH24HD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD/action/storage_attestation","attest_author":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD/action/author_attestation","sign_citation":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD/action/citation_signature","submit_replication":"https://pith.science/pith/5HD3IPHBCC2MYKYW66BRWH24HD/action/replication_record"}},"created_at":"2026-07-05T11:49:49.385269+00:00","updated_at":"2026-07-05T11:49:49.385269+00:00"}