{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:26BD2GQ7XGKEAE3PTWPAIAUFFK","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":"458f656b4adec89e068e6784a30b293787346692747f6f228eb15d2e00d46d07","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T12:13:00Z","title_canon_sha256":"86ece70a8827d223f3934ed6bcb40f6d825541a7a96add7759a8027eb0c1d2d3"},"schema_version":"1.0","source":{"id":"2307.14142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14142","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14142v1","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14142","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"26BD2GQ7XGKE","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_16","alias_value":"26BD2GQ7XGKEAE3P","created_at":"2026-07-05T06:34:58Z"},{"alias_kind":"pith_short_8","alias_value":"26BD2GQ7","created_at":"2026-07-05T06:34:58Z"}],"graph_snapshots":[{"event_id":"sha256:4f4519c5ec4de8e1955c809fdad1590a1a73b94b7d391c11f4cddd1390f7fc35","target":"graph","created_at":"2026-07-05T06:34:58Z","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/2307.14142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering (VQA) has been intensively studied as a multimodal task that requires effort in bridging vision and language to infer answers correctly. Recent attempts have developed various attention-based modules for solving VQA tasks. However, the performance of model inference is largely bottlenecked by visual processing for semantics understanding. Most existing detection methods rely on bounding boxes, remaining a serious challenge for VQA models to understand the causal nexus of object semantics in images and correctly infer contextual information. To this end, we propose a f","authors_text":"Fang Wang, Haibo Shi, Haoran Wang, Siyu Zhang, Yaoru Sun, Yeming Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T12:13:00Z","title":"LOIS: Looking Out of Instance Semantics for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14142","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":"sha256:9258fab24f4874663a89ba0616fc53f7bd0f97438b8dfea0f6980a03eebfbbbe","target":"record","created_at":"2026-07-05T06:34:58Z","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":"458f656b4adec89e068e6784a30b293787346692747f6f228eb15d2e00d46d07","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T12:13:00Z","title_canon_sha256":"86ece70a8827d223f3934ed6bcb40f6d825541a7a96add7759a8027eb0c1d2d3"},"schema_version":"1.0","source":{"id":"2307.14142","kind":"arxiv","version":1}},"canonical_sha256":"d7823d1a1fb99440136f9d9e0402852a882cd742962f2eaae895c37474b36794","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7823d1a1fb99440136f9d9e0402852a882cd742962f2eaae895c37474b36794","first_computed_at":"2026-07-05T06:34:58.224964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:58.224964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ImQb03E5rQaHDevDvWDMeQGf43iWOZxnbqT7acikggEyfWlRNWvrnZuHdjhzc9urqOaVmLr2lkR1eirdcqopCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:58.225349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9258fab24f4874663a89ba0616fc53f7bd0f97438b8dfea0f6980a03eebfbbbe","sha256:4f4519c5ec4de8e1955c809fdad1590a1a73b94b7d391c11f4cddd1390f7fc35"],"state_sha256":"6439eaf4997b7b0b00bc1da513f082644a8a046921126320bef91ae4c1eebf65"}