{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:6EONDE2OO7H5YDIID6TIS6LAWL","short_pith_number":"pith:6EONDE2O","canonical_record":{"source":{"id":"1611.00471","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-02T05:17:03Z","cross_cats_sorted":[],"title_canon_sha256":"47eebd79b89ca0a22a6b3015adb15df31fa190956c236e4b63d1ab7cca19f899","abstract_canon_sha256":"034cc6e7868af2f79805bc6b67c41a650b7b2087d110d50ccd1eb7d9bc0bb167"},"schema_version":"1.0"},"canonical_sha256":"f11cd1934e77cfdc0d081fa6897960b2f4d7d95d6a13736d2fc7a7e9e0852e88","source":{"kind":"arxiv","id":"1611.00471","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.00471","created_at":"2026-05-18T00:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"1611.00471v2","created_at":"2026-05-18T00:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00471","created_at":"2026-05-18T00:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"6EONDE2OO7H5","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6EONDE2OO7H5YDII","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6EONDE2O","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:6EONDE2OO7H5YDIID6TIS6LAWL","target":"record","payload":{"canonical_record":{"source":{"id":"1611.00471","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-02T05:17:03Z","cross_cats_sorted":[],"title_canon_sha256":"47eebd79b89ca0a22a6b3015adb15df31fa190956c236e4b63d1ab7cca19f899","abstract_canon_sha256":"034cc6e7868af2f79805bc6b67c41a650b7b2087d110d50ccd1eb7d9bc0bb167"},"schema_version":"1.0"},"canonical_sha256":"f11cd1934e77cfdc0d081fa6897960b2f4d7d95d6a13736d2fc7a7e9e0852e88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:16.463263Z","signature_b64":"yY0FKHA/x8pHx8onf/etIWiQMoELMkYxPE2RFkwv3JfvY5EOomO/3W0X18mSw1Jy0FUL7md82talsNwNdTBvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f11cd1934e77cfdc0d081fa6897960b2f4d7d95d6a13736d2fc7a7e9e0852e88","last_reissued_at":"2026-05-18T00:48:16.462639Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:16.462639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.00471","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":"2026-05-18T00:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IOuP1QjLspiNf3n/CWxqHLoOE/wlxyDPWYm5Ki6qWpGWe/qtnYDGWU5MnejXmVyyjit6vHOUX/EHOWmtHJAABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:44:24.753280Z"},"content_sha256":"1f7d237044a8e1d72cd8a7d928ff2e82ad75052cfb58b4a7870c6d0a77732842","schema_version":"1.0","event_id":"sha256:1f7d237044a8e1d72cd8a7d928ff2e82ad75052cfb58b4a7870c6d0a77732842"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:6EONDE2OO7H5YDIID6TIS6LAWL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual Attention Networks for Multimodal Reasoning and Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyeonseob Nam, Jeonghee Kim, Jung-Woo Ha","submitted_at":"2016-11-02T05:17:03Z","abstract_excerpt":"We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language. DANs attend to specific regions in images and words in text through multiple steps and gather essential information from both modalities. Based on this framework, we introduce two types of DANs for multimodal reasoning and matching, respectively. The reasoning model allows visual and textual attentions to steer each other during collaborative inference, which is useful for tasks such as Visual Question Answering (VQA). In additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00471","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":"2026-05-18T00:48:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glSv3E2K9qqxJbN5Dm+MUL9QO5GvlUm4ppu4cz+tvJGKuwSLarg0hVlBh0D6YD8G2SYtMJy139ksIckZ8JBtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:44:24.753772Z"},"content_sha256":"830315c444aa435bfda1c4420a346f9b752ba3974a89a60442aa1005dc585305","schema_version":"1.0","event_id":"sha256:830315c444aa435bfda1c4420a346f9b752ba3974a89a60442aa1005dc585305"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EONDE2OO7H5YDIID6TIS6LAWL/bundle.json","state_url":"https://pith.science/pith/6EONDE2OO7H5YDIID6TIS6LAWL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EONDE2OO7H5YDIID6TIS6LAWL/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":"2026-05-26T12:44:24Z","links":{"resolver":"https://pith.science/pith/6EONDE2OO7H5YDIID6TIS6LAWL","bundle":"https://pith.science/pith/6EONDE2OO7H5YDIID6TIS6LAWL/bundle.json","state":"https://pith.science/pith/6EONDE2OO7H5YDIID6TIS6LAWL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EONDE2OO7H5YDIID6TIS6LAWL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:6EONDE2OO7H5YDIID6TIS6LAWL","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":"034cc6e7868af2f79805bc6b67c41a650b7b2087d110d50ccd1eb7d9bc0bb167","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-02T05:17:03Z","title_canon_sha256":"47eebd79b89ca0a22a6b3015adb15df31fa190956c236e4b63d1ab7cca19f899"},"schema_version":"1.0","source":{"id":"1611.00471","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.00471","created_at":"2026-05-18T00:48:16Z"},{"alias_kind":"arxiv_version","alias_value":"1611.00471v2","created_at":"2026-05-18T00:48:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00471","created_at":"2026-05-18T00:48:16Z"},{"alias_kind":"pith_short_12","alias_value":"6EONDE2OO7H5","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6EONDE2OO7H5YDII","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6EONDE2O","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:830315c444aa435bfda1c4420a346f9b752ba3974a89a60442aa1005dc585305","target":"graph","created_at":"2026-05-18T00:48:16Z","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":"We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language. DANs attend to specific regions in images and words in text through multiple steps and gather essential information from both modalities. Based on this framework, we introduce two types of DANs for multimodal reasoning and matching, respectively. The reasoning model allows visual and textual attentions to steer each other during collaborative inference, which is useful for tasks such as Visual Question Answering (VQA). In additi","authors_text":"Hyeonseob Nam, Jeonghee Kim, Jung-Woo Ha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-02T05:17:03Z","title":"Dual Attention Networks for Multimodal Reasoning and Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00471","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":"sha256:1f7d237044a8e1d72cd8a7d928ff2e82ad75052cfb58b4a7870c6d0a77732842","target":"record","created_at":"2026-05-18T00:48:16Z","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":"034cc6e7868af2f79805bc6b67c41a650b7b2087d110d50ccd1eb7d9bc0bb167","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-02T05:17:03Z","title_canon_sha256":"47eebd79b89ca0a22a6b3015adb15df31fa190956c236e4b63d1ab7cca19f899"},"schema_version":"1.0","source":{"id":"1611.00471","kind":"arxiv","version":2}},"canonical_sha256":"f11cd1934e77cfdc0d081fa6897960b2f4d7d95d6a13736d2fc7a7e9e0852e88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f11cd1934e77cfdc0d081fa6897960b2f4d7d95d6a13736d2fc7a7e9e0852e88","first_computed_at":"2026-05-18T00:48:16.462639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:16.462639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yY0FKHA/x8pHx8onf/etIWiQMoELMkYxPE2RFkwv3JfvY5EOomO/3W0X18mSw1Jy0FUL7md82talsNwNdTBvAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:16.463263Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.00471","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f7d237044a8e1d72cd8a7d928ff2e82ad75052cfb58b4a7870c6d0a77732842","sha256:830315c444aa435bfda1c4420a346f9b752ba3974a89a60442aa1005dc585305"],"state_sha256":"7adc4d3f2439979fff165519c0bdb06b869425b23fe80258bd70c509a0a3c15b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOzq4a6BKOHPJO7lcdcaLBKllRWKvVk3SW1Brg9IbY3eIuys4M640KkuwCJNZ6A+yKdkMPibUM9H9m4/YIHwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T12:44:24.756749Z","bundle_sha256":"9f201503d8c744dec605cd311fdb3aa0dabb4f8711d9bdf7fca7993e65023d52"}}