{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:26BD2GQ7XGKEAE3PTWPAIAUFFK","short_pith_number":"pith:26BD2GQ7","schema_version":"1.0","canonical_sha256":"d7823d1a1fb99440136f9d9e0402852a882cd742962f2eaae895c37474b36794","source":{"kind":"arxiv","id":"2307.14142","version":1},"attestation_state":"computed","paper":{"title":"LOIS: Looking Out of Instance Semantics for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fang Wang, Haibo Shi, Haoran Wang, Siyu Zhang, Yaoru Sun, Yeming Chen","submitted_at":"2023-07-26T12:13:00Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.14142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T12:13:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"86ece70a8827d223f3934ed6bcb40f6d825541a7a96add7759a8027eb0c1d2d3","abstract_canon_sha256":"458f656b4adec89e068e6784a30b293787346692747f6f228eb15d2e00d46d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:58.225349Z","signature_b64":"ImQb03E5rQaHDevDvWDMeQGf43iWOZxnbqT7acikggEyfWlRNWvrnZuHdjhzc9urqOaVmLr2lkR1eirdcqopCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7823d1a1fb99440136f9d9e0402852a882cd742962f2eaae895c37474b36794","last_reissued_at":"2026-07-05T06:34:58.224964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:58.224964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOIS: Looking Out of Instance Semantics for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fang Wang, Haibo Shi, Haoran Wang, Siyu Zhang, Yaoru Sun, Yeming Chen","submitted_at":"2023-07-26T12:13:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14142","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.14142/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.14142","created_at":"2026-07-05T06:34:58.225031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14142v1","created_at":"2026-07-05T06:34:58.225031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14142","created_at":"2026-07-05T06:34:58.225031+00:00"},{"alias_kind":"pith_short_12","alias_value":"26BD2GQ7XGKE","created_at":"2026-07-05T06:34:58.225031+00:00"},{"alias_kind":"pith_short_16","alias_value":"26BD2GQ7XGKEAE3P","created_at":"2026-07-05T06:34:58.225031+00:00"},{"alias_kind":"pith_short_8","alias_value":"26BD2GQ7","created_at":"2026-07-05T06:34:58.225031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK","json":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK.json","graph_json":"https://pith.science/api/pith-number/26BD2GQ7XGKEAE3PTWPAIAUFFK/graph.json","events_json":"https://pith.science/api/pith-number/26BD2GQ7XGKEAE3PTWPAIAUFFK/events.json","paper":"https://pith.science/paper/26BD2GQ7"},"agent_actions":{"view_html":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK","download_json":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK.json","view_paper":"https://pith.science/paper/26BD2GQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14142&json=true","fetch_graph":"https://pith.science/api/pith-number/26BD2GQ7XGKEAE3PTWPAIAUFFK/graph.json","fetch_events":"https://pith.science/api/pith-number/26BD2GQ7XGKEAE3PTWPAIAUFFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK/action/storage_attestation","attest_author":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK/action/author_attestation","sign_citation":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK/action/citation_signature","submit_replication":"https://pith.science/pith/26BD2GQ7XGKEAE3PTWPAIAUFFK/action/replication_record"}},"created_at":"2026-07-05T06:34:58.225031+00:00","updated_at":"2026-07-05T06:34:58.225031+00:00"}