{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JOA4XUGUYFHFCIJBOZNZT7EYL4","short_pith_number":"pith:JOA4XUGU","schema_version":"1.0","canonical_sha256":"4b81cbd0d4c14e512121765b99fc985f32cf539f0a2d44a41cad67b7f36c6a9d","source":{"kind":"arxiv","id":"1801.09041","version":1},"attestation_state":"computed","paper":{"title":"Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongfei Yu, Jianlong Fu, Jiebo Luo, Qing Li, Tao Mei","submitted_at":"2018-01-27T05:34:37Z","abstract_excerpt":"Visual Question Answering (VQA) has attracted attention from both computer vision and natural language processing communities. Most existing approaches adopt the pipeline of representing an image via pre-trained CNNs, and then using the uninterpretable CNN features in conjunction with the question to predict the answer. Although such end-to-end models might report promising performance, they rarely provide any insight, apart from the answer, into the VQA process. In this work, we propose to break up the end-to-end VQA into two steps: explaining and reasoning, in an attempt towards a more expla"},"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":"1801.09041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-27T05:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"491836d5367a6bf65a2a5a66b12033303f2ec18094ef075962b65221e1346c07","abstract_canon_sha256":"ede37452eb43762974417f1a616194e6b21cbf77092841708f4a205b5f823237"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:58.829339Z","signature_b64":"jMNa3cV54VPcAQNyquvMgdsw3KzrFv18q5AA+E+T0VUVWIQe4t1nBUGfvA800vR6hrmD1MAxPCdGVCd2CCmSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b81cbd0d4c14e512121765b99fc985f32cf539f0a2d44a41cad67b7f36c6a9d","last_reissued_at":"2026-05-18T00:24:58.828653Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:58.828653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongfei Yu, Jianlong Fu, Jiebo Luo, Qing Li, Tao Mei","submitted_at":"2018-01-27T05:34:37Z","abstract_excerpt":"Visual Question Answering (VQA) has attracted attention from both computer vision and natural language processing communities. Most existing approaches adopt the pipeline of representing an image via pre-trained CNNs, and then using the uninterpretable CNN features in conjunction with the question to predict the answer. Although such end-to-end models might report promising performance, they rarely provide any insight, apart from the answer, into the VQA process. In this work, we propose to break up the end-to-end VQA into two steps: explaining and reasoning, in an attempt towards a more expla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09041","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":"1801.09041","created_at":"2026-05-18T00:24:58.828754+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.09041v1","created_at":"2026-05-18T00:24:58.828754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09041","created_at":"2026-05-18T00:24:58.828754+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOA4XUGUYFHF","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOA4XUGUYFHFCIJB","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOA4XUGU","created_at":"2026-05-18T12:32:31.084164+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/JOA4XUGUYFHFCIJBOZNZT7EYL4","json":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4.json","graph_json":"https://pith.science/api/pith-number/JOA4XUGUYFHFCIJBOZNZT7EYL4/graph.json","events_json":"https://pith.science/api/pith-number/JOA4XUGUYFHFCIJBOZNZT7EYL4/events.json","paper":"https://pith.science/paper/JOA4XUGU"},"agent_actions":{"view_html":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4","download_json":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4.json","view_paper":"https://pith.science/paper/JOA4XUGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.09041&json=true","fetch_graph":"https://pith.science/api/pith-number/JOA4XUGUYFHFCIJBOZNZT7EYL4/graph.json","fetch_events":"https://pith.science/api/pith-number/JOA4XUGUYFHFCIJBOZNZT7EYL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/action/storage_attestation","attest_author":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/action/author_attestation","sign_citation":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/action/citation_signature","submit_replication":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/action/replication_record"}},"created_at":"2026-05-18T00:24:58.828754+00:00","updated_at":"2026-05-18T00:24:58.828754+00:00"}