{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A2HBBDYPLH3QNCHMTGF7HGJH75","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":"3f08d681c28d92570d2ab53f70434f3a895cca1700f2baf5ba5746dc8c68fd79","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T17:59:56Z","title_canon_sha256":"156d04277e43021d1909b3710cf9603b0c3882a05f6eb35ba2bc0488395c6565"},"schema_version":"1.0","source":{"id":"2206.01201","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01201","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01201v2","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01201","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"A2HBBDYPLH3Q","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"A2HBBDYPLH3QNCHM","created_at":"2026-07-05T05:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"A2HBBDYP","created_at":"2026-07-05T05:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:ed33f7a30015a616d904f793582cdb0bd75ddac0f556024f4c87371852b5bd34","target":"graph","created_at":"2026-07-05T05:04:49Z","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/2206.01201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper revisits visual representation in knowledge-based visual question answering (VQA) and demonstrates that using regional information in a better way can significantly improve the performance. While visual representation is extensively studied in traditional VQA, it is under-explored in knowledge-based VQA even though these two tasks share the common spirit, i.e., rely on visual input to answer the question. Specifically, we observe that in most state-of-the-art knowledge-based VQA methods: 1) visual features are extracted either from the whole image or in a sliding window manner for r","authors_text":"Chenguang Zhu, Dongdong Chen, Lu Yuan, Yichong Xu, Yuanze Lin, Yujia Xie","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T17:59:56Z","title":"REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01201","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":"sha256:3c674a8347abf7cb33be2fb76fe5e67e70fa991e3c654076150efeb8188d1c6d","target":"record","created_at":"2026-07-05T05:04:49Z","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":"3f08d681c28d92570d2ab53f70434f3a895cca1700f2baf5ba5746dc8c68fd79","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T17:59:56Z","title_canon_sha256":"156d04277e43021d1909b3710cf9603b0c3882a05f6eb35ba2bc0488395c6565"},"schema_version":"1.0","source":{"id":"2206.01201","kind":"arxiv","version":2}},"canonical_sha256":"068e108f0f59f70688ec998bf39927ff5715767fdaa03774f2d51daf8c05c900","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"068e108f0f59f70688ec998bf39927ff5715767fdaa03774f2d51daf8c05c900","first_computed_at":"2026-07-05T05:04:49.233601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:49.233601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lSIIXVt0/JAXRz67z84Z1EbLkK+oqA1gYtROe5zkF08jaIUoH6YdWi2xY602jwz2rSn5wbmXwcwdSD6DfvOGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:49.234094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01201","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c674a8347abf7cb33be2fb76fe5e67e70fa991e3c654076150efeb8188d1c6d","sha256:ed33f7a30015a616d904f793582cdb0bd75ddac0f556024f4c87371852b5bd34"],"state_sha256":"ac53d74c3a49a1fe3dfb4d58cfa6b2d30106177457b09dacdfccc92ddcaac728"}