{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YDTCMNRYIA5LKZ5KJG7HJ3R5VY","short_pith_number":"pith:YDTCMNRY","schema_version":"1.0","canonical_sha256":"c0e6263638403ab567aa49be74ee3dae378c7e76f05cfabd1332f85a15260bed","source":{"kind":"arxiv","id":"1902.05715","version":1},"attestation_state":"computed","paper":{"title":"Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arijit Ray, Avi Ziskind, Giedrius Burachas, Shalini Ghosh","submitted_at":"2019-02-15T07:59:11Z","abstract_excerpt":"In this paper, we present a novel approach for the task of eXplainable Question Answering (XQA), i.e., generating natural language (NL) explanations for the Visual Question Answering (VQA) problem. We generate NL explanations comprising of the evidence to support the answer to a question asked to an image using two sources of information: (a) annotations of entities in an image (e.g., object labels, region descriptions, relation phrases) generated from the scene graph of the image, and (b) the attention map generated by a VQA model when answering the question. We show how combining the visual "},"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":"1902.05715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-15T07:59:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94d06d766b8aa5a1e0f7e0dfec28c2c4dd1c24f0628cb65c867a4f44f14075fd","abstract_canon_sha256":"f03739fb9ad8151c4714e98ea62e5aa54d3c23915661ec4d1da5781a6262fae8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:56.390656Z","signature_b64":"DQuqlKP2c5oXHfm3ZIYahnDSbb2dbbUKcKUEWTA6T/YpX804vDeCWgGFDgS2+be7vWy5jyWdn09MM8ujtu2LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0e6263638403ab567aa49be74ee3dae378c7e76f05cfabd1332f85a15260bed","last_reissued_at":"2026-05-17T23:53:56.389968Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:56.389968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arijit Ray, Avi Ziskind, Giedrius Burachas, Shalini Ghosh","submitted_at":"2019-02-15T07:59:11Z","abstract_excerpt":"In this paper, we present a novel approach for the task of eXplainable Question Answering (XQA), i.e., generating natural language (NL) explanations for the Visual Question Answering (VQA) problem. We generate NL explanations comprising of the evidence to support the answer to a question asked to an image using two sources of information: (a) annotations of entities in an image (e.g., object labels, region descriptions, relation phrases) generated from the scene graph of the image, and (b) the attention map generated by a VQA model when answering the question. We show how combining the visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05715","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":""},"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":"1902.05715","created_at":"2026-05-17T23:53:56.390065+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05715v1","created_at":"2026-05-17T23:53:56.390065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05715","created_at":"2026-05-17T23:53:56.390065+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDTCMNRYIA5L","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDTCMNRYIA5LKZ5K","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDTCMNRY","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY","json":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY.json","graph_json":"https://pith.science/api/pith-number/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/graph.json","events_json":"https://pith.science/api/pith-number/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/events.json","paper":"https://pith.science/paper/YDTCMNRY"},"agent_actions":{"view_html":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY","download_json":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY.json","view_paper":"https://pith.science/paper/YDTCMNRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05715&json=true","fetch_graph":"https://pith.science/api/pith-number/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/graph.json","fetch_events":"https://pith.science/api/pith-number/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/action/storage_attestation","attest_author":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/action/author_attestation","sign_citation":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/action/citation_signature","submit_replication":"https://pith.science/pith/YDTCMNRYIA5LKZ5KJG7HJ3R5VY/action/replication_record"}},"created_at":"2026-05-17T23:53:56.390065+00:00","updated_at":"2026-05-17T23:53:56.390065+00:00"}