{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XDV6GMJFSZJKQFRMXMY3FZHWJU","short_pith_number":"pith:XDV6GMJF","canonical_record":{"source":{"id":"2403.14783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:57:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MA"],"title_canon_sha256":"f0beef889443b76ce1ee7e7d8cbeabb3e02ead3db466c9e0f16beccaac06eee5","abstract_canon_sha256":"6eba34c917793cb0aadee6b4cd7c4d2fac5cfe3d56a942e9a9e984b7f190b1a6"},"schema_version":"1.0"},"canonical_sha256":"b8ebe331259652a8162cbb31b2e4f64d35e831a21e5077ae8a0345d9214bbc16","source":{"kind":"arxiv","id":"2403.14783","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14783","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14783v1","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14783","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"XDV6GMJFSZJK","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"XDV6GMJFSZJKQFRM","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"XDV6GMJF","created_at":"2026-07-05T07:59:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XDV6GMJFSZJKQFRMXMY3FZHWJU","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:57:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MA"],"title_canon_sha256":"f0beef889443b76ce1ee7e7d8cbeabb3e02ead3db466c9e0f16beccaac06eee5","abstract_canon_sha256":"6eba34c917793cb0aadee6b4cd7c4d2fac5cfe3d56a942e9a9e984b7f190b1a6"},"schema_version":"1.0"},"canonical_sha256":"b8ebe331259652a8162cbb31b2e4f64d35e831a21e5077ae8a0345d9214bbc16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:25.833591Z","signature_b64":"AkTZIMO+btXyWX4Aw24duaPkKh1Y5FqOwaipofzVad4yCmd8MgbwrK6zwp/TIZ04ii+zxxNk8FgyqgRA36SIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8ebe331259652a8162cbb31b2e4f64d35e831a21e5077ae8a0345d9214bbc16","last_reissued_at":"2026-07-05T07:59:25.833069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:25.833069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14783","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8v+/F2IHwxFnO9czUXFn3E+5vQkW782yQnKYVQ0ySpyPGMz7rEAfKO52ilSteZBWm0eemzA5ulVY7Kr0HHIcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:40:14.488606Z"},"content_sha256":"d93fdc5d1aaeb3890452e65bd8b80ffccb236e226adeec5ddec89adadfade420","schema_version":"1.0","event_id":"sha256:d93fdc5d1aaeb3890452e65bd8b80ffccb236e226adeec5ddec89adadfade420"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XDV6GMJFSZJKQFRMXMY3FZHWJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MA"],"primary_cat":"cs.CV","authors_text":"Bowen Jiang, Camillo J. Taylor, Dan Roth, Shreyas S. Shivakumar, Zhijun Zhuang","submitted_at":"2024-03-21T18:57:25Z","abstract_excerpt":"This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks. We propose an adaptive multi-agent system, named Multi-Agent VQA, to overcome the limitations of foundation models in object detection and counting by using specialized agents as tools. Unlike existing approaches, our study focuses on the system's performance without fine-tuning it on specific VQA datasets, making it more practical and robust in the open world. We present preliminary experimental results under zero-shot scenarios and highlight some failure cases, offering new directions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14783","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/2403.14783/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xcNRlwRAgMEjrXxinYZUoIPw59RFTqMEhU0IB1qN+7rRVNqNfdNNrzA+is6fPLloJAUFyfyzyG+cGouIFbphDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:40:14.489174Z"},"content_sha256":"9136cebed846c3745ff85da6e5efb9768249b074a7fc40b237e4e128b47bf420","schema_version":"1.0","event_id":"sha256:9136cebed846c3745ff85da6e5efb9768249b074a7fc40b237e4e128b47bf420"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XDV6GMJFSZJKQFRMXMY3FZHWJU/bundle.json","state_url":"https://pith.science/pith/XDV6GMJFSZJKQFRMXMY3FZHWJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XDV6GMJFSZJKQFRMXMY3FZHWJU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T08:40:14Z","links":{"resolver":"https://pith.science/pith/XDV6GMJFSZJKQFRMXMY3FZHWJU","bundle":"https://pith.science/pith/XDV6GMJFSZJKQFRMXMY3FZHWJU/bundle.json","state":"https://pith.science/pith/XDV6GMJFSZJKQFRMXMY3FZHWJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XDV6GMJFSZJKQFRMXMY3FZHWJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XDV6GMJFSZJKQFRMXMY3FZHWJU","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":"6eba34c917793cb0aadee6b4cd7c4d2fac5cfe3d56a942e9a9e984b7f190b1a6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:57:25Z","title_canon_sha256":"f0beef889443b76ce1ee7e7d8cbeabb3e02ead3db466c9e0f16beccaac06eee5"},"schema_version":"1.0","source":{"id":"2403.14783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14783","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14783v1","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14783","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"XDV6GMJFSZJK","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"XDV6GMJFSZJKQFRM","created_at":"2026-07-05T07:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"XDV6GMJF","created_at":"2026-07-05T07:59:25Z"}],"graph_snapshots":[{"event_id":"sha256:9136cebed846c3745ff85da6e5efb9768249b074a7fc40b237e4e128b47bf420","target":"graph","created_at":"2026-07-05T07:59:25Z","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/2403.14783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks. We propose an adaptive multi-agent system, named Multi-Agent VQA, to overcome the limitations of foundation models in object detection and counting by using specialized agents as tools. Unlike existing approaches, our study focuses on the system's performance without fine-tuning it on specific VQA datasets, making it more practical and robust in the open world. We present preliminary experimental results under zero-shot scenarios and highlight some failure cases, offering new directions","authors_text":"Bowen Jiang, Camillo J. Taylor, Dan Roth, Shreyas S. Shivakumar, Zhijun Zhuang","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:57:25Z","title":"Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14783","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:d93fdc5d1aaeb3890452e65bd8b80ffccb236e226adeec5ddec89adadfade420","target":"record","created_at":"2026-07-05T07:59:25Z","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":"6eba34c917793cb0aadee6b4cd7c4d2fac5cfe3d56a942e9a9e984b7f190b1a6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:57:25Z","title_canon_sha256":"f0beef889443b76ce1ee7e7d8cbeabb3e02ead3db466c9e0f16beccaac06eee5"},"schema_version":"1.0","source":{"id":"2403.14783","kind":"arxiv","version":1}},"canonical_sha256":"b8ebe331259652a8162cbb31b2e4f64d35e831a21e5077ae8a0345d9214bbc16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8ebe331259652a8162cbb31b2e4f64d35e831a21e5077ae8a0345d9214bbc16","first_computed_at":"2026-07-05T07:59:25.833069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:25.833069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AkTZIMO+btXyWX4Aw24duaPkKh1Y5FqOwaipofzVad4yCmd8MgbwrK6zwp/TIZ04ii+zxxNk8FgyqgRA36SIDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:25.833591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d93fdc5d1aaeb3890452e65bd8b80ffccb236e226adeec5ddec89adadfade420","sha256:9136cebed846c3745ff85da6e5efb9768249b074a7fc40b237e4e128b47bf420"],"state_sha256":"8589f9d43b4ccdbb24194482b92a1f0251f099e157020d91a151e388584d8396"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcLnA69SdZmJQkbbl0wx0xutfytliwQylXjmRFXeKpJRj0lI0f30dzKdnzt73zlBbIimBA6O5ZfGM+77dJDMDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:40:14.495189Z","bundle_sha256":"4daf806b3ce2bb09bd5cd5b81e91c60fad9bf3ffbc571c4a5becb3170f6587a1"}}