{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DUXQZ73SHORY52JPYPUQEMU4F6","short_pith_number":"pith:DUXQZ73S","canonical_record":{"source":{"id":"1806.04860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-13T06:37:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f220903f3a45989877944e84ccf111635a14ce01fb15e84d89af0e1b986ddd40","abstract_canon_sha256":"4d7cbba8cc7d27e81e0cbc7f94ed67ec365f82f1ccece8a31dac134b2d9ed0af"},"schema_version":"1.0"},"canonical_sha256":"1d2f0cff723ba38ee92fc3e902329c2fb5f4bcb6b57aaaafcd12cb37723455ce","source":{"kind":"arxiv","id":"1806.04860","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04860","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04860v1","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04860","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"DUXQZ73SHORY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DUXQZ73SHORY52JP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DUXQZ73S","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DUXQZ73SHORY52JPYPUQEMU4F6","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-13T06:37:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f220903f3a45989877944e84ccf111635a14ce01fb15e84d89af0e1b986ddd40","abstract_canon_sha256":"4d7cbba8cc7d27e81e0cbc7f94ed67ec365f82f1ccece8a31dac134b2d9ed0af"},"schema_version":"1.0"},"canonical_sha256":"1d2f0cff723ba38ee92fc3e902329c2fb5f4bcb6b57aaaafcd12cb37723455ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:20.684916Z","signature_b64":"xAo8rTT61r/6b/WvbQBKHUQlB6/ulS7ICraayx5aS+mxvMOCdSNgYhuZTR99VZynWYaue3BAGArxCW7UlQWnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d2f0cff723ba38ee92fc3e902329c2fb5f4bcb6b57aaaafcd12cb37723455ce","last_reissued_at":"2026-05-18T00:13:20.684260Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:20.684260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04860","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":"2026-05-18T00:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hm9yUR97YGgQBgtW5cGQ8W5uDTc9lVWBziLPsT0uEPMFr7uvDGV0mdNR9OmfwwIWWY4+ytlhSmhHlNxRrgd3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:57:00.999432Z"},"content_sha256":"cf1e20911dce13396216bdfa7eef6af07dcf5b22ec45bfbf4b5eb720abf5bc9f","schema_version":"1.0","event_id":"sha256:cf1e20911dce13396216bdfa7eef6af07dcf5b22ec45bfbf4b5eb720abf5bc9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DUXQZ73SHORY52JPYPUQEMU4F6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Visual Knowledge Memory Networks for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chen Zhu, Dongqi Cai, Jianguo Li, Yinpeng Dong, Yurong Chen, Zhou Su","submitted_at":"2018-06-13T06:37:42Z","abstract_excerpt":"Visual question answering (VQA) requires joint comprehension of images and natural language questions, where many questions can't be directly or clearly answered from visual content but require reasoning from structured human knowledge with confirmation from visual content. This paper proposes visual knowledge memory network (VKMN) to address this issue, which seamlessly incorporates structured human knowledge and deep visual features into memory networks in an end-to-end learning framework. Comparing to existing methods for leveraging external knowledge for supporting VQA, this paper stresses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04860","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":"2026-05-18T00:13:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ApbNwpHtHD2/U1VuCb7syGYPnlXk0Fi/ga5eYbJGtylplbarnR1qZTSXgEV7QRWJY/2qsrnMb1isyqdOrNQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:57:00.999791Z"},"content_sha256":"3dfa3989d8a2b8d4716401689f3ac91c4ce864badda4a4c2cefd8efb67a5ea44","schema_version":"1.0","event_id":"sha256:3dfa3989d8a2b8d4716401689f3ac91c4ce864badda4a4c2cefd8efb67a5ea44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUXQZ73SHORY52JPYPUQEMU4F6/bundle.json","state_url":"https://pith.science/pith/DUXQZ73SHORY52JPYPUQEMU4F6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUXQZ73SHORY52JPYPUQEMU4F6/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":"2026-05-26T01:57:01Z","links":{"resolver":"https://pith.science/pith/DUXQZ73SHORY52JPYPUQEMU4F6","bundle":"https://pith.science/pith/DUXQZ73SHORY52JPYPUQEMU4F6/bundle.json","state":"https://pith.science/pith/DUXQZ73SHORY52JPYPUQEMU4F6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUXQZ73SHORY52JPYPUQEMU4F6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DUXQZ73SHORY52JPYPUQEMU4F6","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":"4d7cbba8cc7d27e81e0cbc7f94ed67ec365f82f1ccece8a31dac134b2d9ed0af","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-13T06:37:42Z","title_canon_sha256":"f220903f3a45989877944e84ccf111635a14ce01fb15e84d89af0e1b986ddd40"},"schema_version":"1.0","source":{"id":"1806.04860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04860","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04860v1","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04860","created_at":"2026-05-18T00:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"DUXQZ73SHORY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DUXQZ73SHORY52JP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DUXQZ73S","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:3dfa3989d8a2b8d4716401689f3ac91c4ce864badda4a4c2cefd8efb67a5ea44","target":"graph","created_at":"2026-05-18T00:13:20Z","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) requires joint comprehension of images and natural language questions, where many questions can't be directly or clearly answered from visual content but require reasoning from structured human knowledge with confirmation from visual content. This paper proposes visual knowledge memory network (VKMN) to address this issue, which seamlessly incorporates structured human knowledge and deep visual features into memory networks in an end-to-end learning framework. Comparing to existing methods for leveraging external knowledge for supporting VQA, this paper stresses","authors_text":"Chen Zhu, Dongqi Cai, Jianguo Li, Yinpeng Dong, Yurong Chen, Zhou Su","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-13T06:37:42Z","title":"Learning Visual Knowledge Memory Networks for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04860","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:cf1e20911dce13396216bdfa7eef6af07dcf5b22ec45bfbf4b5eb720abf5bc9f","target":"record","created_at":"2026-05-18T00:13:20Z","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":"4d7cbba8cc7d27e81e0cbc7f94ed67ec365f82f1ccece8a31dac134b2d9ed0af","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-13T06:37:42Z","title_canon_sha256":"f220903f3a45989877944e84ccf111635a14ce01fb15e84d89af0e1b986ddd40"},"schema_version":"1.0","source":{"id":"1806.04860","kind":"arxiv","version":1}},"canonical_sha256":"1d2f0cff723ba38ee92fc3e902329c2fb5f4bcb6b57aaaafcd12cb37723455ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d2f0cff723ba38ee92fc3e902329c2fb5f4bcb6b57aaaafcd12cb37723455ce","first_computed_at":"2026-05-18T00:13:20.684260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:20.684260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xAo8rTT61r/6b/WvbQBKHUQlB6/ulS7ICraayx5aS+mxvMOCdSNgYhuZTR99VZynWYaue3BAGArxCW7UlQWnAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:20.684916Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf1e20911dce13396216bdfa7eef6af07dcf5b22ec45bfbf4b5eb720abf5bc9f","sha256:3dfa3989d8a2b8d4716401689f3ac91c4ce864badda4a4c2cefd8efb67a5ea44"],"state_sha256":"8a0995ec36128b4baeb6dcf72bd4515c35ce3f3117015450ee8b3f3662f2f002"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HzJE1qSeDC9OSIgZPqd5rxnR5YH1DQiim/bXEvzc2eXq+pTBn20ljdC1JIeX77tPG+09l6ub7dDlSxughQvCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:57:01.002422Z","bundle_sha256":"03e7522d66d0d05e0f078699d37ddf0205197b0c66905195692ea71617a08f45"}}