{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XHLBZ4HZRF7XFAETTB25VQLYAS","short_pith_number":"pith:XHLBZ4HZ","canonical_record":{"source":{"id":"1906.10770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-25T22:16:03Z","cross_cats_sorted":[],"title_canon_sha256":"730e91ec248ea12e6d9bb19f7e80ef9ab4411689411c691f675d96c9982458a8","abstract_canon_sha256":"04ccba8f55b7b4b7d7f9b64a9096b2e460b0ad9232394a025d5b55919b9837ff"},"schema_version":"1.0"},"canonical_sha256":"b9d61cf0f9897f7280939875dac17804a7dc0449e349c5ab842d9b1d741aa08d","source":{"kind":"arxiv","id":"1906.10770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10770","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10770v1","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10770","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"XHLBZ4HZRF7X","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XHLBZ4HZRF7XFAET","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XHLBZ4HZ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XHLBZ4HZRF7XFAETTB25VQLYAS","target":"record","payload":{"canonical_record":{"source":{"id":"1906.10770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-25T22:16:03Z","cross_cats_sorted":[],"title_canon_sha256":"730e91ec248ea12e6d9bb19f7e80ef9ab4411689411c691f675d96c9982458a8","abstract_canon_sha256":"04ccba8f55b7b4b7d7f9b64a9096b2e460b0ad9232394a025d5b55919b9837ff"},"schema_version":"1.0"},"canonical_sha256":"b9d61cf0f9897f7280939875dac17804a7dc0449e349c5ab842d9b1d741aa08d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:14.835331Z","signature_b64":"B4ArrQOOb+zD2ZZYzILfENOd1JOhHF4z/jhzDDRCYeyFqyGuyiwhUXkINAIDCuumLlWqE2Zjws9qbpDC1LiMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9d61cf0f9897f7280939875dac17804a7dc0449e349c5ab842d9b1d741aa08d","last_reissued_at":"2026-05-17T23:42:14.834675Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:14.834675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.10770","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":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mBO9Bsjycj5EnQJRvIw5eslklKzY/DCfn0DrIlPrPJ52daWWf81M3wK1wLS3ku7erKPQrNyaDqAzFrsbjwSoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:46:40.231497Z"},"content_sha256":"2478c38998af1ccd64cdd00c76287bc3ff9fdb9f00f4096c4ecfa626859c2179","schema_version":"1.0","event_id":"sha256:2478c38998af1ccd64cdd00c76287bc3ff9fdb9f00f4096c4ecfa626859c2179"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XHLBZ4HZRF7XFAETTB25VQLYAS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Modular Co-Attention Networks for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jun Yu, Qi Tian, Yuhao Cui, Zhou Yu","submitted_at":"2019-06-25T22:16:03Z","abstract_excerpt":"Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Atte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10770","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":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h38akmjmnlEeMsRtzrblOlXAA3AHCmMjE6VYXNAiBprXiGXQfF2vk7iUShZrMn5Qkht2Bc/HNmQeDcD4sqchAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:46:40.232159Z"},"content_sha256":"f4056b1c749aecdb027276e95c749ccb4539e78b5251aa15ba633125026b28a6","schema_version":"1.0","event_id":"sha256:f4056b1c749aecdb027276e95c749ccb4539e78b5251aa15ba633125026b28a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/bundle.json","state_url":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/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":"2026-05-27T04:46:40Z","links":{"resolver":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS","bundle":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/bundle.json","state":"https://pith.science/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHLBZ4HZRF7XFAETTB25VQLYAS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XHLBZ4HZRF7XFAETTB25VQLYAS","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":"04ccba8f55b7b4b7d7f9b64a9096b2e460b0ad9232394a025d5b55919b9837ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-25T22:16:03Z","title_canon_sha256":"730e91ec248ea12e6d9bb19f7e80ef9ab4411689411c691f675d96c9982458a8"},"schema_version":"1.0","source":{"id":"1906.10770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10770","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10770v1","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10770","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"XHLBZ4HZRF7X","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XHLBZ4HZRF7XFAET","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XHLBZ4HZ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:f4056b1c749aecdb027276e95c749ccb4539e78b5251aa15ba633125026b28a6","target":"graph","created_at":"2026-05-17T23:42:14Z","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 a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Therefore, designing an effective `co-attention' model to associate key words in questions with key objects in images is central to VQA performance. So far, most successful attempts at co-attention learning have been achieved by using shallow models, and deep co-attention models show little improvement over their shallow counterparts. In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Atte","authors_text":"Dacheng Tao, Jun Yu, Qi Tian, Yuhao Cui, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-25T22:16:03Z","title":"Deep Modular Co-Attention Networks for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10770","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":"sha256:2478c38998af1ccd64cdd00c76287bc3ff9fdb9f00f4096c4ecfa626859c2179","target":"record","created_at":"2026-05-17T23:42:14Z","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":"04ccba8f55b7b4b7d7f9b64a9096b2e460b0ad9232394a025d5b55919b9837ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-25T22:16:03Z","title_canon_sha256":"730e91ec248ea12e6d9bb19f7e80ef9ab4411689411c691f675d96c9982458a8"},"schema_version":"1.0","source":{"id":"1906.10770","kind":"arxiv","version":1}},"canonical_sha256":"b9d61cf0f9897f7280939875dac17804a7dc0449e349c5ab842d9b1d741aa08d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9d61cf0f9897f7280939875dac17804a7dc0449e349c5ab842d9b1d741aa08d","first_computed_at":"2026-05-17T23:42:14.834675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:14.834675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4ArrQOOb+zD2ZZYzILfENOd1JOhHF4z/jhzDDRCYeyFqyGuyiwhUXkINAIDCuumLlWqE2Zjws9qbpDC1LiMDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:14.835331Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2478c38998af1ccd64cdd00c76287bc3ff9fdb9f00f4096c4ecfa626859c2179","sha256:f4056b1c749aecdb027276e95c749ccb4539e78b5251aa15ba633125026b28a6"],"state_sha256":"9789f248e91ef9f6d5f874352173c7a0b61df274bf4d07178e09d007ee7cd6e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tR/dZEEbB+5kbDg2wKYpCbHBnTQj5mRs1tbqlLoXaXfWWcGxL7Xx35YksSWk+FdzIUNNErIdqpIC2aOeDBhdDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T04:46:40.235393Z","bundle_sha256":"c81ede9b83884c6dc2e6448a4e6b24cdb60f54b0d45c77e54c873038353290bc"}}