{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ULYSJE2WWDU2NOVRPNLH7VFXNG","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":"94faaaff27329f4496059d9f80f9ca991f7a78f13fc8e2de723fa4cf407cb157","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-25T22:26:09Z","title_canon_sha256":"b27e93e98c7f552aed7f20c36f2296282ac26e84d5f5acdf5ac062087520e90f"},"schema_version":"1.0","source":{"id":"2201.10654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10654","created_at":"2026-07-05T03:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10654v1","created_at":"2026-07-05T03:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10654","created_at":"2026-07-05T03:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"ULYSJE2WWDU2","created_at":"2026-07-05T03:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"ULYSJE2WWDU2NOVR","created_at":"2026-07-05T03:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"ULYSJE2W","created_at":"2026-07-05T03:51:48Z"}],"graph_snapshots":[{"event_id":"sha256:9b7d52c526893187f7dd94640f82281422964f75b8c8df5bcbdd2f72ef8d403c","target":"graph","created_at":"2026-07-05T03:51:48Z","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/2201.10654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations. Previous approaches extensively employ entity-level alignments, such as the correlations between the visual regions and their semantic labels, or the interactions across question words and object features. These attempts aim to improve the cross-modality representations, while ignoring their internal relations. Instead, we propose to apply st","authors_text":"Peixi Xiong, Pei Yu, Quanzeng You, Ying Wu, Zicheng Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-25T22:26:09Z","title":"SA-VQA: Structured Alignment of Visual and Semantic Representations for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10654","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":"sha256:7e923c337ec9ae14ee9b817a66634ba0c5113c2661b56a3f51cb954445f1fe66","target":"record","created_at":"2026-07-05T03:51:48Z","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":"94faaaff27329f4496059d9f80f9ca991f7a78f13fc8e2de723fa4cf407cb157","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-25T22:26:09Z","title_canon_sha256":"b27e93e98c7f552aed7f20c36f2296282ac26e84d5f5acdf5ac062087520e90f"},"schema_version":"1.0","source":{"id":"2201.10654","kind":"arxiv","version":1}},"canonical_sha256":"a2f1249356b0e9a6bab17b567fd4b769a427156736988401b2b3a036e77abed8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2f1249356b0e9a6bab17b567fd4b769a427156736988401b2b3a036e77abed8","first_computed_at":"2026-07-05T03:51:48.318519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:48.318519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0jcWpNopfW3wIfJzP7vpPwPRjHZLyTKhnBhXpdogNdiBoBSCeHfaR9vGr0IIKIMQvQ889wG+WGvXmOJ+YZ5XBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:48.319072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.10654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e923c337ec9ae14ee9b817a66634ba0c5113c2661b56a3f51cb954445f1fe66","sha256:9b7d52c526893187f7dd94640f82281422964f75b8c8df5bcbdd2f72ef8d403c"],"state_sha256":"66d33c6409d0d77255c503f9ffc84684b902eb1aa16c124db7f6f52ee783980b"}