{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JOA4XUGUYFHFCIJBOZNZT7EYL4","short_pith_number":"pith:JOA4XUGU","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"},"canonical_sha256":"4b81cbd0d4c14e512121765b99fc985f32cf539f0a2d44a41cad67b7f36c6a9d","source":{"kind":"arxiv","id":"1801.09041","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09041","created_at":"2026-05-18T00:24:58Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09041v1","created_at":"2026-05-18T00:24:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09041","created_at":"2026-05-18T00:24:58Z"},{"alias_kind":"pith_short_12","alias_value":"JOA4XUGUYFHF","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JOA4XUGUYFHFCIJB","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JOA4XUGU","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JOA4XUGUYFHFCIJBOZNZT7EYL4","target":"record","payload":{"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"},"canonical_sha256":"4b81cbd0d4c14e512121765b99fc985f32cf539f0a2d44a41cad67b7f36c6a9d","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"},"source_kind":"arxiv","source_id":"1801.09041","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":"2026-05-18T00:24:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJQ5sB8IQ/2zwNen9gsL/iM99lDvAmojjddom8p2JBEduoJGiY0SOP0uW+pan+AfjOoXfLKJf1XcoAEsAurQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:01:08.220443Z"},"content_sha256":"485b880c49f22405d181c5e56989705c53e39b31767604711e5d7c2e7e0ea3d4","schema_version":"1.0","event_id":"sha256:485b880c49f22405d181c5e56989705c53e39b31767604711e5d7c2e7e0ea3d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JOA4XUGUYFHFCIJBOZNZT7EYL4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:24:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYEgFBEUFNEBVvROY3jbihabZSyz5kHT4rjnRSzPOqknx5+lBr2sjtTrfvBf0tKGgt6P4NQvP1+q0HkNy3GUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:01:08.220904Z"},"content_sha256":"ea101851e8cfa13d4cb5499d38c35c957e89dbbc88c4555287be05e8efb0fd15","schema_version":"1.0","event_id":"sha256:ea101851e8cfa13d4cb5499d38c35c957e89dbbc88c4555287be05e8efb0fd15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/bundle.json","state_url":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/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":"2026-05-25T00:01:08Z","links":{"resolver":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4","bundle":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/bundle.json","state":"https://pith.science/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOA4XUGUYFHFCIJBOZNZT7EYL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JOA4XUGUYFHFCIJBOZNZT7EYL4","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":"ede37452eb43762974417f1a616194e6b21cbf77092841708f4a205b5f823237","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-27T05:34:37Z","title_canon_sha256":"491836d5367a6bf65a2a5a66b12033303f2ec18094ef075962b65221e1346c07"},"schema_version":"1.0","source":{"id":"1801.09041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09041","created_at":"2026-05-18T00:24:58Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09041v1","created_at":"2026-05-18T00:24:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09041","created_at":"2026-05-18T00:24:58Z"},{"alias_kind":"pith_short_12","alias_value":"JOA4XUGUYFHF","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JOA4XUGUYFHFCIJB","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JOA4XUGU","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:ea101851e8cfa13d4cb5499d38c35c957e89dbbc88c4555287be05e8efb0fd15","target":"graph","created_at":"2026-05-18T00:24:58Z","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"},"paper":{"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","authors_text":"Dongfei Yu, Jianlong Fu, Jiebo Luo, Qing Li, Tao Mei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-27T05:34:37Z","title":"Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09041","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":"sha256:485b880c49f22405d181c5e56989705c53e39b31767604711e5d7c2e7e0ea3d4","target":"record","created_at":"2026-05-18T00:24:58Z","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":"ede37452eb43762974417f1a616194e6b21cbf77092841708f4a205b5f823237","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-27T05:34:37Z","title_canon_sha256":"491836d5367a6bf65a2a5a66b12033303f2ec18094ef075962b65221e1346c07"},"schema_version":"1.0","source":{"id":"1801.09041","kind":"arxiv","version":1}},"canonical_sha256":"4b81cbd0d4c14e512121765b99fc985f32cf539f0a2d44a41cad67b7f36c6a9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b81cbd0d4c14e512121765b99fc985f32cf539f0a2d44a41cad67b7f36c6a9d","first_computed_at":"2026-05-18T00:24:58.828653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:58.828653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jMNa3cV54VPcAQNyquvMgdsw3KzrFv18q5AA+E+T0VUVWIQe4t1nBUGfvA800vR6hrmD1MAxPCdGVCd2CCmSAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:58.829339Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.09041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:485b880c49f22405d181c5e56989705c53e39b31767604711e5d7c2e7e0ea3d4","sha256:ea101851e8cfa13d4cb5499d38c35c957e89dbbc88c4555287be05e8efb0fd15"],"state_sha256":"daccc539558706c015c51aad8247aa402b885f093753bb5d011f04874e72b7db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G9sqvJ4BrAtA8biyiiAamXl4eNGzDt21TkpbB1ExgU5fxThZVz8+YFqoRrqhJrnK5qfOUEUJHKxsOVztFQ4UAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T00:01:08.223833Z","bundle_sha256":"3d59aeb15d5269c03a25af75ca31f9a56f137076940719737d4ef0e3a52906d2"}}