{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BVCYYJSHKCYUJYKT7LFQ4RR25P","short_pith_number":"pith:BVCYYJSH","canonical_record":{"source":{"id":"1708.03619","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-10T09:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"0f7bf83a54a1f859b7aa06de2e14bb5679d483997a6da0a894641987237e5e21","abstract_canon_sha256":"dbe5d0d1b3ab2c020d1608b19adad9cf5a7498b792bb93e6a969eda817948b92"},"schema_version":"1.0"},"canonical_sha256":"0d458c264750b144e153facb0e463aebe20975d60747fec547d349f5fb45d6ef","source":{"kind":"arxiv","id":"1708.03619","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.03619","created_at":"2026-05-17T23:46:04Z"},{"alias_kind":"arxiv_version","alias_value":"1708.03619v2","created_at":"2026-05-17T23:46:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03619","created_at":"2026-05-17T23:46:04Z"},{"alias_kind":"pith_short_12","alias_value":"BVCYYJSHKCYU","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BVCYYJSHKCYUJYKT","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BVCYYJSH","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BVCYYJSHKCYUJYKT7LFQ4RR25P","target":"record","payload":{"canonical_record":{"source":{"id":"1708.03619","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-10T09:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"0f7bf83a54a1f859b7aa06de2e14bb5679d483997a6da0a894641987237e5e21","abstract_canon_sha256":"dbe5d0d1b3ab2c020d1608b19adad9cf5a7498b792bb93e6a969eda817948b92"},"schema_version":"1.0"},"canonical_sha256":"0d458c264750b144e153facb0e463aebe20975d60747fec547d349f5fb45d6ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:04.526592Z","signature_b64":"PPJhcNOrm3YWceYA64VvH/LeGQxVG/1eIjgfZ++mbcm/b9HNukaq4TCx1YQlkywOC/LMjKNf6NiBBpn0SRcGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d458c264750b144e153facb0e463aebe20975d60747fec547d349f5fb45d6ef","last_reissued_at":"2026-05-17T23:46:04.525763Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:04.525763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.03619","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":"2026-05-17T23:46:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cy4iyJkQGm8iWHI0z8D5nnM5iCCBDyrO+PPAs7UTFZWS6PA7rOt6FFkLYItZ3/nmF/sf8gKX/Fz3OaoNwvwQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:19:02.265466Z"},"content_sha256":"4a5dab6366d0764a4242c2dad17b8e2c5da8b83331fcf2a2ee5c94b8435e3932","schema_version":"1.0","event_id":"sha256:4a5dab6366d0764a4242c2dad17b8e2c5da8b83331fcf2a2ee5c94b8435e3932"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BVCYYJSHKCYUJYKT7LFQ4RR25P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenchao Xiang, Dacheng Tao, Jianping Fan, Jun Yu, Zhou Yu","submitted_at":"2017-08-10T09:09:23Z","abstract_excerpt":"Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both visual content of images and textual content of questions. To support the VQA task, we need to find good solutions for the following three issues: 1) fine-grained feature representations for both the image and the question; 2) multi-modal feature fusion that is able to capture the complex interactions between multi-modal features; 3) automatic answer prediction that is able to consider the complex correlations between multiple diverse answers for the same question. For fine-grained image and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03619","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":"2026-05-17T23:46:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fIet+CCIFkT9z2pIWrAzzxffpOsVGyOElnYUkTRlHsGL1f2h9n14H4KYo7SmPrai5f/SLO5LbaKc1G2MrQ/rAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:19:02.266125Z"},"content_sha256":"0118a457db466ea8bd33f9c8f5080d0bdef4c2f6217c2c90a6003397748a37f0","schema_version":"1.0","event_id":"sha256:0118a457db466ea8bd33f9c8f5080d0bdef4c2f6217c2c90a6003397748a37f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVCYYJSHKCYUJYKT7LFQ4RR25P/bundle.json","state_url":"https://pith.science/pith/BVCYYJSHKCYUJYKT7LFQ4RR25P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVCYYJSHKCYUJYKT7LFQ4RR25P/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":"2026-05-26T11:19:02Z","links":{"resolver":"https://pith.science/pith/BVCYYJSHKCYUJYKT7LFQ4RR25P","bundle":"https://pith.science/pith/BVCYYJSHKCYUJYKT7LFQ4RR25P/bundle.json","state":"https://pith.science/pith/BVCYYJSHKCYUJYKT7LFQ4RR25P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVCYYJSHKCYUJYKT7LFQ4RR25P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BVCYYJSHKCYUJYKT7LFQ4RR25P","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":"dbe5d0d1b3ab2c020d1608b19adad9cf5a7498b792bb93e6a969eda817948b92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-10T09:09:23Z","title_canon_sha256":"0f7bf83a54a1f859b7aa06de2e14bb5679d483997a6da0a894641987237e5e21"},"schema_version":"1.0","source":{"id":"1708.03619","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.03619","created_at":"2026-05-17T23:46:04Z"},{"alias_kind":"arxiv_version","alias_value":"1708.03619v2","created_at":"2026-05-17T23:46:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03619","created_at":"2026-05-17T23:46:04Z"},{"alias_kind":"pith_short_12","alias_value":"BVCYYJSHKCYU","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BVCYYJSHKCYUJYKT","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BVCYYJSH","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:0118a457db466ea8bd33f9c8f5080d0bdef4c2f6217c2c90a6003397748a37f0","target":"graph","created_at":"2026-05-17T23:46:04Z","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 visual content of images and textual content of questions. To support the VQA task, we need to find good solutions for the following three issues: 1) fine-grained feature representations for both the image and the question; 2) multi-modal feature fusion that is able to capture the complex interactions between multi-modal features; 3) automatic answer prediction that is able to consider the complex correlations between multiple diverse answers for the same question. For fine-grained image and","authors_text":"Chenchao Xiang, 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":"2017-08-10T09:09:23Z","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03619","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":"sha256:4a5dab6366d0764a4242c2dad17b8e2c5da8b83331fcf2a2ee5c94b8435e3932","target":"record","created_at":"2026-05-17T23:46:04Z","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":"dbe5d0d1b3ab2c020d1608b19adad9cf5a7498b792bb93e6a969eda817948b92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-10T09:09:23Z","title_canon_sha256":"0f7bf83a54a1f859b7aa06de2e14bb5679d483997a6da0a894641987237e5e21"},"schema_version":"1.0","source":{"id":"1708.03619","kind":"arxiv","version":2}},"canonical_sha256":"0d458c264750b144e153facb0e463aebe20975d60747fec547d349f5fb45d6ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d458c264750b144e153facb0e463aebe20975d60747fec547d349f5fb45d6ef","first_computed_at":"2026-05-17T23:46:04.525763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:04.525763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PPJhcNOrm3YWceYA64VvH/LeGQxVG/1eIjgfZ++mbcm/b9HNukaq4TCx1YQlkywOC/LMjKNf6NiBBpn0SRcGCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:04.526592Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.03619","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a5dab6366d0764a4242c2dad17b8e2c5da8b83331fcf2a2ee5c94b8435e3932","sha256:0118a457db466ea8bd33f9c8f5080d0bdef4c2f6217c2c90a6003397748a37f0"],"state_sha256":"fa8ecdbcc49136bc235cf31144125e2997ec30ea071624654a0a9af0f02f019f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZ7wcgKDt/+OchgJtObyY/5nmU3XtpJK9+Yrp4rKlk+r62EwIzm9N8Zro+t/GhC9Q3ItCHzjNvt6c4VHyms0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:19:02.268953Z","bundle_sha256":"7e9a2d4b3bc41d4a4df07ad489ddbf772f745c8ddc8b337143af29db6fb69e65"}}