{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HJIPGJ3TSCUAH2ZOQC5P2M3AFN","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":"8cf64aaf447840e796dbf4b8ae9eebd061f993fc23ff5f1feeb0cca850e68789","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-25T18:52:26Z","title_canon_sha256":"c507f8be23bf6a9b433fdb91a05ae7b11538598284df982655b46044996e9781"},"schema_version":"1.0","source":{"id":"2110.13214","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.13214","created_at":"2026-07-05T04:42:56Z"},{"alias_kind":"arxiv_version","alias_value":"2110.13214v4","created_at":"2026-07-05T04:42:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13214","created_at":"2026-07-05T04:42:56Z"},{"alias_kind":"pith_short_12","alias_value":"HJIPGJ3TSCUA","created_at":"2026-07-05T04:42:56Z"},{"alias_kind":"pith_short_16","alias_value":"HJIPGJ3TSCUAH2ZO","created_at":"2026-07-05T04:42:56Z"},{"alias_kind":"pith_short_8","alias_value":"HJIPGJ3T","created_at":"2026-07-05T04:42:56Z"}],"graph_snapshots":[{"event_id":"sha256:17dfdfafee89ad5d50582ced3a4565fa159d1f2377d7cb1545aa8159bc9fdab5","target":"graph","created_at":"2026-07-05T04:42:56Z","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/2110.13214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images. However, aside from natural images, abstract diagrams with semantic richness are still understudied in visual understanding and reasoning research. In this work, we introduce a new challenge of Icon Question Answering (IconQA) with the goal of answering a question in an icon image context. We release IconQA, a large-scale dataset that consists of 107,439 questions and three sub-tasks: multi-image-choice, multi-text-choice, and filling-in-the-blank. The IconQA dataset is inspire","authors_text":"Jiaqi Chen, Liang Qiu, Pan Lu, Song-Chun Zhu, Tony Xia, Wei Zhang, Xiaodan Liang, Yizhou Zhao, Zhou Yu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-25T18:52:26Z","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13214","kind":"arxiv","version":4},"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:b511e2dc2234e3ba708df9b94c4cbd00f2cab25c574df55b0f72c5a22f2377bc","target":"record","created_at":"2026-07-05T04:42:56Z","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":"8cf64aaf447840e796dbf4b8ae9eebd061f993fc23ff5f1feeb0cca850e68789","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-25T18:52:26Z","title_canon_sha256":"c507f8be23bf6a9b433fdb91a05ae7b11538598284df982655b46044996e9781"},"schema_version":"1.0","source":{"id":"2110.13214","kind":"arxiv","version":4}},"canonical_sha256":"3a50f3277390a803eb2e80bafd33602b51bef24b13326923f9f05f259537acfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a50f3277390a803eb2e80bafd33602b51bef24b13326923f9f05f259537acfa","first_computed_at":"2026-07-05T04:42:56.858550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:56.858550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e1XATMcxOY3JfyPsBfIfc81dmjxLxg6IiVAdpp+4pbqgVE1eo1MCvtsaSdJFJaw5P05QsBh9kZEkvfEKcJQRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:56.858901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.13214","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b511e2dc2234e3ba708df9b94c4cbd00f2cab25c574df55b0f72c5a22f2377bc","sha256:17dfdfafee89ad5d50582ced3a4565fa159d1f2377d7cb1545aa8159bc9fdab5"],"state_sha256":"8b04d6de128827df8e4ad817072956fb777fb63aa3b561b11af58b110d57b045"}