{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ILV4MY6J2KH4TEBQC6WQDRNJAO","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":"82201c90154dd71f1278f04b358a38071852551b9239defbad8bbf381a3f813e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-01T07:07:36Z","title_canon_sha256":"d6e62d0e1f2a98fafc3d7c64f3cf3c130a8b2f0a713709dccb183e2d1ca7a1d1"},"schema_version":"1.0","source":{"id":"2006.00753","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00753","created_at":"2026-07-05T03:35:06Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00753v2","created_at":"2026-07-05T03:35:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00753","created_at":"2026-07-05T03:35:06Z"},{"alias_kind":"pith_short_12","alias_value":"ILV4MY6J2KH4","created_at":"2026-07-05T03:35:06Z"},{"alias_kind":"pith_short_16","alias_value":"ILV4MY6J2KH4TEBQ","created_at":"2026-07-05T03:35:06Z"},{"alias_kind":"pith_short_8","alias_value":"ILV4MY6J","created_at":"2026-07-05T03:35:06Z"}],"graph_snapshots":[{"event_id":"sha256:15f6ac8d05bd551a6e6526c2affc4cd56174e1f34dd0662c5ab98b6c5eff15f4","target":"graph","created_at":"2026-07-05T03:35:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.00753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text relationships appearing in the image, and then designs a multimodal graph attention network to reason over it. Finally, the outputs from the above modules are processed by a global-local attentional answering module to produce an answer splicing together tokens from both OCR and general vocabulary iteratively by following M4C. Our proposed model outperforms","authors_text":"Anton van den Hengel, Chenyu Gao, Hui Li, Peng Wang, Qi Wu, Qi Zhu, Yuliang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-01T07:07:36Z","title":"Structured Multimodal Attentions for TextVQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00753","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:e70046f278d7eae62ced5eeb9dca48313412be04aecc077079a842e73470da4f","target":"record","created_at":"2026-07-05T03:35:06Z","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":"82201c90154dd71f1278f04b358a38071852551b9239defbad8bbf381a3f813e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-01T07:07:36Z","title_canon_sha256":"d6e62d0e1f2a98fafc3d7c64f3cf3c130a8b2f0a713709dccb183e2d1ca7a1d1"},"schema_version":"1.0","source":{"id":"2006.00753","kind":"arxiv","version":2}},"canonical_sha256":"42ebc663c9d28fc9903017ad01c5a903884905ba776a72799660e2f128da3d4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42ebc663c9d28fc9903017ad01c5a903884905ba776a72799660e2f128da3d4e","first_computed_at":"2026-07-05T03:35:06.112820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:06.112820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"94mfcMnTy4v2MeMgOWi5LuNF9kwVeA5uBNvLX5wVzT9e4UX0oVNleKcboaX4FpvtYBelyGAuAjZwHZcb4p3HCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:06.113326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.00753","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e70046f278d7eae62ced5eeb9dca48313412be04aecc077079a842e73470da4f","sha256:15f6ac8d05bd551a6e6526c2affc4cd56174e1f34dd0662c5ab98b6c5eff15f4"],"state_sha256":"bb07eaf07d19b648e8c87fa7e1f36210acae76eb95949c43888e1aee499cdb0d"}