{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CEEUQU7PWKM4YBJQ7XVLOZXW4U","short_pith_number":"pith:CEEUQU7P","schema_version":"1.0","canonical_sha256":"11094853efb299cc0530fdeab766f6e53e68e36f45e604fab1b1b2a372f0552d","source":{"kind":"arxiv","id":"2003.00431","version":1},"attestation_state":"computed","paper":{"title":"A Study on Multimodal and Interactive Explanations for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Avi Ziskind, Giedrius Burachas, Jurgen P. Schulze, Kamran Alipour, Yi Yao","submitted_at":"2020-03-01T07:54:01Z","abstract_excerpt":"Explainability and interpretability of AI models is an essential factor affecting the safety of AI. While various explainable AI (XAI) approaches aim at mitigating the lack of transparency in deep networks, the evidence of the effectiveness of these approaches in improving usability, trust, and understanding of AI systems are still missing. We evaluate multimodal explanations in the setting of a Visual Question Answering (VQA) task, by asking users to predict the response accuracy of a VQA agent with and without explanations. We use between-subjects and within-subjects experiments to probe exp"},"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":"2003.00431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-01T07:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"db413e40d5082245b8a219bffde14ca398a2c1198579963173b54f28808a1ab9","abstract_canon_sha256":"50af6cbfa0611b2e3905453887f814894dec8811a68d412bb62a234cf0b2afec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:47.084818Z","signature_b64":"QxeHjFKu6MPUjQ1L/ZL1WgIdDlLi/1hlx12LQ2MOdqXw1xUT0Yc8tuSy758xb595WUagwmBkEu7eLjIM/3F0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11094853efb299cc0530fdeab766f6e53e68e36f45e604fab1b1b2a372f0552d","last_reissued_at":"2026-07-05T00:44:47.084418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:47.084418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Study on Multimodal and Interactive Explanations for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Avi Ziskind, Giedrius Burachas, Jurgen P. Schulze, Kamran Alipour, Yi Yao","submitted_at":"2020-03-01T07:54:01Z","abstract_excerpt":"Explainability and interpretability of AI models is an essential factor affecting the safety of AI. While various explainable AI (XAI) approaches aim at mitigating the lack of transparency in deep networks, the evidence of the effectiveness of these approaches in improving usability, trust, and understanding of AI systems are still missing. We evaluate multimodal explanations in the setting of a Visual Question Answering (VQA) task, by asking users to predict the response accuracy of a VQA agent with and without explanations. We use between-subjects and within-subjects experiments to probe exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00431","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/2003.00431/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":"2003.00431","created_at":"2026-07-05T00:44:47.084478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.00431v1","created_at":"2026-07-05T00:44:47.084478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00431","created_at":"2026-07-05T00:44:47.084478+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEEUQU7PWKM4","created_at":"2026-07-05T00:44:47.084478+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEEUQU7PWKM4YBJQ","created_at":"2026-07-05T00:44:47.084478+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEEUQU7P","created_at":"2026-07-05T00:44:47.084478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07005","citing_title":"Explainable AI the Latest Advancements and New Trends","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U","json":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U.json","graph_json":"https://pith.science/api/pith-number/CEEUQU7PWKM4YBJQ7XVLOZXW4U/graph.json","events_json":"https://pith.science/api/pith-number/CEEUQU7PWKM4YBJQ7XVLOZXW4U/events.json","paper":"https://pith.science/paper/CEEUQU7P"},"agent_actions":{"view_html":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U","download_json":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U.json","view_paper":"https://pith.science/paper/CEEUQU7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.00431&json=true","fetch_graph":"https://pith.science/api/pith-number/CEEUQU7PWKM4YBJQ7XVLOZXW4U/graph.json","fetch_events":"https://pith.science/api/pith-number/CEEUQU7PWKM4YBJQ7XVLOZXW4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U/action/storage_attestation","attest_author":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U/action/author_attestation","sign_citation":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U/action/citation_signature","submit_replication":"https://pith.science/pith/CEEUQU7PWKM4YBJQ7XVLOZXW4U/action/replication_record"}},"created_at":"2026-07-05T00:44:47.084478+00:00","updated_at":"2026-07-05T00:44:47.084478+00:00"}