{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M5B4WT44TCK4D3NNNOYK7ELQ4J","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":"6cac82dec33e9cbd5888542fbd4c3e562ac3c409f8e28f43fc4707309cb329e1","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T09:00:42Z","title_canon_sha256":"b6851a6b7d124e4fe8198f9945275b4a63c23cb472ed828d15638e94fb4c7b41"},"schema_version":"1.0","source":{"id":"2301.04883","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04883","created_at":"2026-07-05T05:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04883v1","created_at":"2026-07-05T05:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04883","created_at":"2026-07-05T05:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"M5B4WT44TCK4","created_at":"2026-07-05T05:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M5B4WT44TCK4D3NN","created_at":"2026-07-05T05:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M5B4WT44","created_at":"2026-07-05T05:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:566510174a7b5b4c24338db90b7a96539ea4b60e79ce8107dd4e2b96f865dcd1","target":"graph","created_at":"2026-07-05T05:32:37Z","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/2301.04883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering on document images that contain textual, visual, and layout information, called document VQA, has received much attention recently. Although many datasets have been proposed for developing document VQA systems, most of the existing datasets focus on understanding the content relationships within a single image and not across multiple images. In this study, we propose a new multi-image document VQA dataset, SlideVQA, containing 2.6k+ slide decks composed of 52k+ slide images and 14.5k questions about a slide deck. SlideVQA requires complex reasoning, including single-h","authors_text":"Itsumi Saito, Kosuke Nishida, Kuniko Saito, Kyosuke Nishida, Ryota Tanaka, Taku Hasegawa","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T09:00:42Z","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04883","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:e8d5438ca1b1a90cbc50248578730d5cd67be6b5785af48dac5128c7674116ab","target":"record","created_at":"2026-07-05T05:32:37Z","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":"6cac82dec33e9cbd5888542fbd4c3e562ac3c409f8e28f43fc4707309cb329e1","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-12T09:00:42Z","title_canon_sha256":"b6851a6b7d124e4fe8198f9945275b4a63c23cb472ed828d15638e94fb4c7b41"},"schema_version":"1.0","source":{"id":"2301.04883","kind":"arxiv","version":1}},"canonical_sha256":"6743cb4f9c9895c1edad6bb0af9170e26be3eeab05e0193108d09def6f3611b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6743cb4f9c9895c1edad6bb0af9170e26be3eeab05e0193108d09def6f3611b8","first_computed_at":"2026-07-05T05:32:37.366797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:37.366797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bEqGqq1kQxwaf8q1jQlBe8FH0ZNVowm4MiNN19EzgebkBL7bG32mwtS89exdLlxH7vU8dY+r8qxjnnS6evDJDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:37.367276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.04883","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8d5438ca1b1a90cbc50248578730d5cd67be6b5785af48dac5128c7674116ab","sha256:566510174a7b5b4c24338db90b7a96539ea4b60e79ce8107dd4e2b96f865dcd1"],"state_sha256":"1d1393ff4639c107fee30c6618ac3e70a3846d52884d2cb19dada65f11c6b105"}