{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:PZE75PXX3GNMWU3SAFXCNTN3NW","short_pith_number":"pith:PZE75PXX","canonical_record":{"source":{"id":"1606.01455","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-05T02:38:20Z","cross_cats_sorted":[],"title_canon_sha256":"4ed48897bde15c27d0d5fe39077540209d30747cdeb65a054a9a943eae5be3f9","abstract_canon_sha256":"2fd4426a75b5bc336b1b470c97f2194115103ae7d4ea71379c0b348be81300e6"},"schema_version":"1.0"},"canonical_sha256":"7e49febef7d99acb5372016e26cdbb6da7b1d9ab87d3b92973955521df6e5a3f","source":{"kind":"arxiv","id":"1606.01455","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.01455","created_at":"2026-05-18T01:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"1606.01455v2","created_at":"2026-05-18T01:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.01455","created_at":"2026-05-18T01:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"PZE75PXX3GNM","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PZE75PXX3GNMWU3S","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PZE75PXX","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:PZE75PXX3GNMWU3SAFXCNTN3NW","target":"record","payload":{"canonical_record":{"source":{"id":"1606.01455","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-05T02:38:20Z","cross_cats_sorted":[],"title_canon_sha256":"4ed48897bde15c27d0d5fe39077540209d30747cdeb65a054a9a943eae5be3f9","abstract_canon_sha256":"2fd4426a75b5bc336b1b470c97f2194115103ae7d4ea71379c0b348be81300e6"},"schema_version":"1.0"},"canonical_sha256":"7e49febef7d99acb5372016e26cdbb6da7b1d9ab87d3b92973955521df6e5a3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:06:40.599755Z","signature_b64":"T8cUu+DYziq0wVw3w1LLO9MsXVqgwN6o3zmOgsd74CJqjRPqsUsF4Hy58G5V0p6gpq92Jcc0yJRP/HDCahtZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e49febef7d99acb5372016e26cdbb6da7b1d9ab87d3b92973955521df6e5a3f","last_reissued_at":"2026-05-18T01:06:40.599097Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:06:40.599097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.01455","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UHV+3BT+fkfwKGU5SW1JTCjLIt/BTQ4aIqjLlJdvzm9eujs11+2KLUfWzdR92T4FwvmOYrwajeMgdJnPyqBLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:20:30.253210Z"},"content_sha256":"c6c017d9f69c3fef6fdb423e6e5ffd52b2d18efd03e01f28dc5e10362921aa4e","schema_version":"1.0","event_id":"sha256:c6c017d9f69c3fef6fdb423e6e5ffd52b2d18efd03e01f28dc5e10362921aa4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:PZE75PXX3GNMWU3SAFXCNTN3NW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Residual Learning for Visual QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byoung-Tak Zhang, Dong-Hyun Kwak, Jeonghee Kim, Jin-Hwa Kim, Jung-Woo Ha, Min-Oh Heo, Sang-Woo Lee","submitted_at":"2016-06-05T02:38:20Z","abstract_excerpt":"Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning. Unlike the deep residual learning, MRN effectively learns the joint representation from vision and language information. The main idea is to use element-wise multiplication for the joint residual mappings exploiting the residual learning of the atten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.01455","kind":"arxiv","version":2},"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":"2026-05-18T01:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5p9afcNyJ3pJ8kOMANe1f8JOKy3SCFvWxOQgdP/dFzp42AHqzWNR8EgUWlpgZuu7kLYZSnCe2Hak+3cr463GDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:20:30.253578Z"},"content_sha256":"0a99fd2ab2ca108e0887fca90e8052fb24251fad28869ab669c3a0a0e1f89ac5","schema_version":"1.0","event_id":"sha256:0a99fd2ab2ca108e0887fca90e8052fb24251fad28869ab669c3a0a0e1f89ac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZE75PXX3GNMWU3SAFXCNTN3NW/bundle.json","state_url":"https://pith.science/pith/PZE75PXX3GNMWU3SAFXCNTN3NW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZE75PXX3GNMWU3SAFXCNTN3NW/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":"2026-06-01T09:20:30Z","links":{"resolver":"https://pith.science/pith/PZE75PXX3GNMWU3SAFXCNTN3NW","bundle":"https://pith.science/pith/PZE75PXX3GNMWU3SAFXCNTN3NW/bundle.json","state":"https://pith.science/pith/PZE75PXX3GNMWU3SAFXCNTN3NW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZE75PXX3GNMWU3SAFXCNTN3NW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:PZE75PXX3GNMWU3SAFXCNTN3NW","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":"2fd4426a75b5bc336b1b470c97f2194115103ae7d4ea71379c0b348be81300e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-05T02:38:20Z","title_canon_sha256":"4ed48897bde15c27d0d5fe39077540209d30747cdeb65a054a9a943eae5be3f9"},"schema_version":"1.0","source":{"id":"1606.01455","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.01455","created_at":"2026-05-18T01:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"1606.01455v2","created_at":"2026-05-18T01:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.01455","created_at":"2026-05-18T01:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"PZE75PXX3GNM","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PZE75PXX3GNMWU3S","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PZE75PXX","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:0a99fd2ab2ca108e0887fca90e8052fb24251fad28869ab669c3a0a0e1f89ac5","target":"graph","created_at":"2026-05-18T01:06:40Z","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":"Deep neural networks continue to advance the state-of-the-art of image recognition tasks with various methods. However, applications of these methods to multimodality remain limited. We present Multimodal Residual Networks (MRN) for the multimodal residual learning of visual question-answering, which extends the idea of the deep residual learning. Unlike the deep residual learning, MRN effectively learns the joint representation from vision and language information. The main idea is to use element-wise multiplication for the joint residual mappings exploiting the residual learning of the atten","authors_text":"Byoung-Tak Zhang, Dong-Hyun Kwak, Jeonghee Kim, Jin-Hwa Kim, Jung-Woo Ha, Min-Oh Heo, Sang-Woo Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-05T02:38:20Z","title":"Multimodal Residual Learning for Visual QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.01455","kind":"arxiv","version":2},"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:c6c017d9f69c3fef6fdb423e6e5ffd52b2d18efd03e01f28dc5e10362921aa4e","target":"record","created_at":"2026-05-18T01:06:40Z","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":"2fd4426a75b5bc336b1b470c97f2194115103ae7d4ea71379c0b348be81300e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-05T02:38:20Z","title_canon_sha256":"4ed48897bde15c27d0d5fe39077540209d30747cdeb65a054a9a943eae5be3f9"},"schema_version":"1.0","source":{"id":"1606.01455","kind":"arxiv","version":2}},"canonical_sha256":"7e49febef7d99acb5372016e26cdbb6da7b1d9ab87d3b92973955521df6e5a3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e49febef7d99acb5372016e26cdbb6da7b1d9ab87d3b92973955521df6e5a3f","first_computed_at":"2026-05-18T01:06:40.599097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:06:40.599097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T8cUu+DYziq0wVw3w1LLO9MsXVqgwN6o3zmOgsd74CJqjRPqsUsF4Hy58G5V0p6gpq92Jcc0yJRP/HDCahtZAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:06:40.599755Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.01455","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6c017d9f69c3fef6fdb423e6e5ffd52b2d18efd03e01f28dc5e10362921aa4e","sha256:0a99fd2ab2ca108e0887fca90e8052fb24251fad28869ab669c3a0a0e1f89ac5"],"state_sha256":"76bb8504ab63810231a791f90ea9aace703aa7d6dede4f255ec7131a19351422"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3S6Dd9UVhbE8vJxizvu21D7YDH7wJ7JCBPQjJN24xTSbSE8LaLX/lVWCPWWVbqx08dlYs56Hk5V/3zKJ05hAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T09:20:30.255524Z","bundle_sha256":"54e49a8887036c91d6ce815fc854e8b011719f38f151645ee8b033726ce82e74"}}