{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:P4YDXXDK5AMUTZFIAHGOKZN5EB","short_pith_number":"pith:P4YDXXDK","canonical_record":{"source":{"id":"1708.01471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-04T12:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"d43913d37b3328681eae97606be2c2c23a201bd4c20e0c4228bde69e0208b301","abstract_canon_sha256":"bce5852d1f3b806726d0cd1d56934b8e18b5a21ee334eeeee6447944b610ce39"},"schema_version":"1.0"},"canonical_sha256":"7f303bdc6ae81949e4a801cce565bd2053e9e86a1bcdb567f734f39f6c2a6363","source":{"kind":"arxiv","id":"1708.01471","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01471","created_at":"2026-05-18T00:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01471v1","created_at":"2026-05-18T00:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01471","created_at":"2026-05-18T00:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"P4YDXXDK5AMU","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"P4YDXXDK5AMUTZFI","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"P4YDXXDK","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:P4YDXXDK5AMUTZFIAHGOKZN5EB","target":"record","payload":{"canonical_record":{"source":{"id":"1708.01471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-04T12:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"d43913d37b3328681eae97606be2c2c23a201bd4c20e0c4228bde69e0208b301","abstract_canon_sha256":"bce5852d1f3b806726d0cd1d56934b8e18b5a21ee334eeeee6447944b610ce39"},"schema_version":"1.0"},"canonical_sha256":"7f303bdc6ae81949e4a801cce565bd2053e9e86a1bcdb567f734f39f6c2a6363","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:37.275519Z","signature_b64":"vR3CcoIsoqCuhpzO2d0TpR/nCLZGkXP0XtP9+moNrwVgs5ylkK4J/4oxwp09U/IYhCT11WMZ5WupfmpuxdmVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f303bdc6ae81949e4a801cce565bd2053e9e86a1bcdb567f734f39f6c2a6363","last_reissued_at":"2026-05-18T00:38:37.274822Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:37.274822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.01471","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":"2026-05-18T00:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c1tH1OfojvoGHZ1Q933HkhW0UliNbt186RmtABMVbQyeo3hnnsot6MFeYT6RT+u8qnSAQNqnsp4ZceTiE8nBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:57:38.027384Z"},"content_sha256":"cb72ff5e81f64e51ea8fa3fba742959289f1c157324303832129425e56ac4db3","schema_version":"1.0","event_id":"sha256:cb72ff5e81f64e51ea8fa3fba742959289f1c157324303832129425e56ac4db3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:P4YDXXDK5AMUTZFIAHGOKZN5EB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jianping Fan, Jun Yu, Zhou Yu","submitted_at":"2017-08-04T12:17:49Z","abstract_excerpt":"Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a fine-grained manner and questions and to fuse these multi-modal features play key roles in performance. Bilinear pooling based models have been shown to outperform traditional linear models for VQA, but their high-dimensional representations and high computational complexity may seriously limit their applicability in practice. For multi-modal feature fusion, here "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01471","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":"2026-05-18T00:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FgFl3MTMhPUHaKCermQk5tzbmvnCqzZdtyfRX9+Fdh2zeXXiP7uFCnRTKUlaoVqm3yp9ighqAXMWEZTXNf4cAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:57:38.028062Z"},"content_sha256":"e6ed2cd14b19a3c068a73a3601af725be4b82847a078cd72b1832e8b4a1df319","schema_version":"1.0","event_id":"sha256:e6ed2cd14b19a3c068a73a3601af725be4b82847a078cd72b1832e8b4a1df319"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4YDXXDK5AMUTZFIAHGOKZN5EB/bundle.json","state_url":"https://pith.science/pith/P4YDXXDK5AMUTZFIAHGOKZN5EB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4YDXXDK5AMUTZFIAHGOKZN5EB/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":"2026-05-26T13:57:38Z","links":{"resolver":"https://pith.science/pith/P4YDXXDK5AMUTZFIAHGOKZN5EB","bundle":"https://pith.science/pith/P4YDXXDK5AMUTZFIAHGOKZN5EB/bundle.json","state":"https://pith.science/pith/P4YDXXDK5AMUTZFIAHGOKZN5EB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4YDXXDK5AMUTZFIAHGOKZN5EB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:P4YDXXDK5AMUTZFIAHGOKZN5EB","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":"bce5852d1f3b806726d0cd1d56934b8e18b5a21ee334eeeee6447944b610ce39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-04T12:17:49Z","title_canon_sha256":"d43913d37b3328681eae97606be2c2c23a201bd4c20e0c4228bde69e0208b301"},"schema_version":"1.0","source":{"id":"1708.01471","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01471","created_at":"2026-05-18T00:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01471v1","created_at":"2026-05-18T00:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01471","created_at":"2026-05-18T00:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"P4YDXXDK5AMU","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"P4YDXXDK5AMUTZFI","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"P4YDXXDK","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:e6ed2cd14b19a3c068a73a3601af725be4b82847a078cd72b1832e8b4a1df319","target":"graph","created_at":"2026-05-18T00:38:37Z","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) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a fine-grained manner and questions and to fuse these multi-modal features play key roles in performance. Bilinear pooling based models have been shown to outperform traditional linear models for VQA, but their high-dimensional representations and high computational complexity may seriously limit their applicability in practice. For multi-modal feature fusion, here ","authors_text":"Dacheng Tao, Jianping Fan, Jun Yu, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-04T12:17:49Z","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01471","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:cb72ff5e81f64e51ea8fa3fba742959289f1c157324303832129425e56ac4db3","target":"record","created_at":"2026-05-18T00:38:37Z","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":"bce5852d1f3b806726d0cd1d56934b8e18b5a21ee334eeeee6447944b610ce39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-04T12:17:49Z","title_canon_sha256":"d43913d37b3328681eae97606be2c2c23a201bd4c20e0c4228bde69e0208b301"},"schema_version":"1.0","source":{"id":"1708.01471","kind":"arxiv","version":1}},"canonical_sha256":"7f303bdc6ae81949e4a801cce565bd2053e9e86a1bcdb567f734f39f6c2a6363","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f303bdc6ae81949e4a801cce565bd2053e9e86a1bcdb567f734f39f6c2a6363","first_computed_at":"2026-05-18T00:38:37.274822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:37.274822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vR3CcoIsoqCuhpzO2d0TpR/nCLZGkXP0XtP9+moNrwVgs5ylkK4J/4oxwp09U/IYhCT11WMZ5WupfmpuxdmVBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:37.275519Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.01471","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb72ff5e81f64e51ea8fa3fba742959289f1c157324303832129425e56ac4db3","sha256:e6ed2cd14b19a3c068a73a3601af725be4b82847a078cd72b1832e8b4a1df319"],"state_sha256":"46a51ab36c7b2bd42bb62f8b4e7ffabc5ab2939d9c7766974cb5745bf2343a7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3SkV1bjoCkR2RLt66VvfGAwQ/J9IxpYKJfv2fZHR4wyIOMMWgPulwlroWICSpPdaVfbIoULFDdyevgpMLWKzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:57:38.031679Z","bundle_sha256":"a5aca0a2800d2932072020fd6fed6b079581114e54fbe3fb74202c1d848ea030"}}