{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UU4OJDXLN47HLZKFIQUCWKMHHS","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":"452b2d0d4db283bba46424a3cefe8bea343240e1109090ef449e96a70159824b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T18:32:32Z","title_canon_sha256":"5ae9641ee7755098979fff62ce831910ff8adae00ace24d4df72cdfc35b542ad"},"schema_version":"1.0","source":{"id":"2305.06407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06407","created_at":"2026-07-05T06:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06407v1","created_at":"2026-07-05T06:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06407","created_at":"2026-07-05T06:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"UU4OJDXLN47H","created_at":"2026-07-05T06:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"UU4OJDXLN47HLZKF","created_at":"2026-07-05T06:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"UU4OJDXL","created_at":"2026-07-05T06:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:87498daa3b11a48fe67ed6e5eabd69bf19092634d8ab6c0d25cf1217424f7077","target":"graph","created_at":"2026-07-05T06:09:12Z","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/2305.06407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Outside-knowledge visual question answering is a challenging task that requires both the acquisition and the use of open-ended real-world knowledge. Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features. In this paper, we are inspired to constrain the cross-modality space into the same space of natural-language space which ","authors_text":"Huishan Ji, Qingyi Si, Weiping Wang, Yuchen Mo, Zheng Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T18:32:32Z","title":"Combo of Thinking and Observing for Outside-Knowledge VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06407","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":"sha256:22a7159ebdb8d1a175ab457fde4605d0c9580d022cf3410d5726ab1b56c0aa7e","target":"record","created_at":"2026-07-05T06:09:12Z","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":"452b2d0d4db283bba46424a3cefe8bea343240e1109090ef449e96a70159824b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T18:32:32Z","title_canon_sha256":"5ae9641ee7755098979fff62ce831910ff8adae00ace24d4df72cdfc35b542ad"},"schema_version":"1.0","source":{"id":"2305.06407","kind":"arxiv","version":1}},"canonical_sha256":"a538e48eeb6f3e75e54544282b29873ca5396bda7086915145925b44c8089733","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a538e48eeb6f3e75e54544282b29873ca5396bda7086915145925b44c8089733","first_computed_at":"2026-07-05T06:09:12.096117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:12.096117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I9adATwW5BDPO1UPbXCvk08iHFkrDFLs3wlwvSPNs0XOkA9uE+kNGk2zhTfyTXuEOQma6mj8625wm1yqTDOvBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:12.096634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22a7159ebdb8d1a175ab457fde4605d0c9580d022cf3410d5726ab1b56c0aa7e","sha256:87498daa3b11a48fe67ed6e5eabd69bf19092634d8ab6c0d25cf1217424f7077"],"state_sha256":"16da480e8c86c6bbe9b7682321858a5fcc658254cb6e66f7c01af4178772d8d2"}