{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WO7HIQTAS2EIZVNNEULCKTL7JA","short_pith_number":"pith:WO7HIQTA","canonical_record":{"source":{"id":"1811.11903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T01:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"f25fa93da60dcbf1ef690e6ef0e5b4ebab89d79d9b923b7253ef2db53a288990","abstract_canon_sha256":"f67335faece301be22202f1a7129656090236b17e745d4372af7a160b0ab3049"},"schema_version":"1.0"},"canonical_sha256":"b3be74426096888cd5ad2516254d7f4835efe5bf23d602f8cd6c330752928feb","source":{"kind":"arxiv","id":"1811.11903","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11903","created_at":"2026-05-17T23:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11903v1","created_at":"2026-05-17T23:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11903","created_at":"2026-05-17T23:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"WO7HIQTAS2EI","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WO7HIQTAS2EIZVNN","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WO7HIQTA","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WO7HIQTAS2EIZVNNEULCKTL7JA","target":"record","payload":{"canonical_record":{"source":{"id":"1811.11903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T01:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"f25fa93da60dcbf1ef690e6ef0e5b4ebab89d79d9b923b7253ef2db53a288990","abstract_canon_sha256":"f67335faece301be22202f1a7129656090236b17e745d4372af7a160b0ab3049"},"schema_version":"1.0"},"canonical_sha256":"b3be74426096888cd5ad2516254d7f4835efe5bf23d602f8cd6c330752928feb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:35.181387Z","signature_b64":"olxXTAPCNYmEXpkdU2KAyXMT1gQf7eWmQai4yz9vE8xZcMt1ro915m2G6OiApGwmgmqwkgFZdsAwAaNSLjJcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3be74426096888cd5ad2516254d7f4835efe5bf23d602f8cd6c330752928feb","last_reissued_at":"2026-05-17T23:59:35.180539Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:35.180539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.11903","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":"2026-05-17T23:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCyB0axW+VasjJjwyjruuTeQkzrJI26A5aRTHlslNO9q0kAP4XcpMpgpuLFhpO/DYfC0qjG4VsmmfTdE5fVsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:47:10.405555Z"},"content_sha256":"23cb7f7682c676589e58aa6d4f3847dc5869cc1ac7a232effb18b2493de2dfd1","schema_version":"1.0","event_id":"sha256:23cb7f7682c676589e58aa6d4f3847dc5869cc1ac7a232effb18b2493de2dfd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WO7HIQTAS2EIZVNNEULCKTL7JA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Question Answering as Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Chunhua Shen, Hui Li, Peng Wang","submitted_at":"2018-11-29T01:11:16Z","abstract_excerpt":"Visual question answering (VQA) demands simultaneous comprehension of both the image visual content and natural language questions. In some cases, the reasoning needs the help of common sense or general knowledge which usually appear in the form of text. Current methods jointly embed both the visual information and the textual feature into the same space. However, how to model the complex interactions between the two different modalities is not an easy task. In contrast to struggling on multimodal feature fusion, in this paper, we propose to unify all the input information by natural language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11903","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":"2026-05-17T23:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E59Uc/gUpsmxc1i3sJq6+6Yu6oKaMxYRJvpKQn1fWX2M9oD/S2cm24/2o88F3KSCWz1HuetOEd76JRTBGXDlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:47:10.406024Z"},"content_sha256":"da8a3731657bee1022f6e32d64251180815f915cccc3c6f0bb5fc61aeb1ce411","schema_version":"1.0","event_id":"sha256:da8a3731657bee1022f6e32d64251180815f915cccc3c6f0bb5fc61aeb1ce411"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WO7HIQTAS2EIZVNNEULCKTL7JA/bundle.json","state_url":"https://pith.science/pith/WO7HIQTAS2EIZVNNEULCKTL7JA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WO7HIQTAS2EIZVNNEULCKTL7JA/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":"2026-08-06T14:47:10Z","links":{"resolver":"https://pith.science/pith/WO7HIQTAS2EIZVNNEULCKTL7JA","bundle":"https://pith.science/pith/WO7HIQTAS2EIZVNNEULCKTL7JA/bundle.json","state":"https://pith.science/pith/WO7HIQTAS2EIZVNNEULCKTL7JA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WO7HIQTAS2EIZVNNEULCKTL7JA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WO7HIQTAS2EIZVNNEULCKTL7JA","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":"f67335faece301be22202f1a7129656090236b17e745d4372af7a160b0ab3049","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T01:11:16Z","title_canon_sha256":"f25fa93da60dcbf1ef690e6ef0e5b4ebab89d79d9b923b7253ef2db53a288990"},"schema_version":"1.0","source":{"id":"1811.11903","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11903","created_at":"2026-05-17T23:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11903v1","created_at":"2026-05-17T23:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11903","created_at":"2026-05-17T23:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"WO7HIQTAS2EI","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WO7HIQTAS2EIZVNN","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WO7HIQTA","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:da8a3731657bee1022f6e32d64251180815f915cccc3c6f0bb5fc61aeb1ce411","target":"graph","created_at":"2026-05-17T23:59:35Z","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) demands simultaneous comprehension of both the image visual content and natural language questions. In some cases, the reasoning needs the help of common sense or general knowledge which usually appear in the form of text. Current methods jointly embed both the visual information and the textual feature into the same space. However, how to model the complex interactions between the two different modalities is not an easy task. In contrast to struggling on multimodal feature fusion, in this paper, we propose to unify all the input information by natural language ","authors_text":"Anton van den Hengel, Chunhua Shen, Hui Li, Peng Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T01:11:16Z","title":"Visual Question Answering as Reading Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11903","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":"sha256:23cb7f7682c676589e58aa6d4f3847dc5869cc1ac7a232effb18b2493de2dfd1","target":"record","created_at":"2026-05-17T23:59:35Z","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":"f67335faece301be22202f1a7129656090236b17e745d4372af7a160b0ab3049","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-29T01:11:16Z","title_canon_sha256":"f25fa93da60dcbf1ef690e6ef0e5b4ebab89d79d9b923b7253ef2db53a288990"},"schema_version":"1.0","source":{"id":"1811.11903","kind":"arxiv","version":1}},"canonical_sha256":"b3be74426096888cd5ad2516254d7f4835efe5bf23d602f8cd6c330752928feb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3be74426096888cd5ad2516254d7f4835efe5bf23d602f8cd6c330752928feb","first_computed_at":"2026-05-17T23:59:35.180539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:35.180539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"olxXTAPCNYmEXpkdU2KAyXMT1gQf7eWmQai4yz9vE8xZcMt1ro915m2G6OiApGwmgmqwkgFZdsAwAaNSLjJcBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:35.181387Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.11903","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23cb7f7682c676589e58aa6d4f3847dc5869cc1ac7a232effb18b2493de2dfd1","sha256:da8a3731657bee1022f6e32d64251180815f915cccc3c6f0bb5fc61aeb1ce411"],"state_sha256":"235bc3fd95678f70461c63d4864e9ac92b87e6b0d8fc62ed666807ea48ff4118"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+pvxoajYy/w8LWFg7ybTa8zVap7XiT3JoThb3PwFzPq1pPelZFHriYMpXcFragvhwgxAcXqT6E7dmudMFXNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:47:10.410488Z","bundle_sha256":"1aea3cd04854575cefa2bd03afa7143238001ac047c379362d1e80b247a2a25c"}}