{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:72C365E4TUCISX4ZORP2XB5FV3","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":"80eed22087a5e688c38c03f60cedd581bae9e6faa2bde6e7c7bfb6cb5d74532b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T06:49:49Z","title_canon_sha256":"d9cc73b5d49589537d376e04d65a1eaec08582e52328d6fc4003a47f4052ff9b"},"schema_version":"1.0","source":{"id":"2401.06400","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06400","created_at":"2026-07-05T08:57:54Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06400v3","created_at":"2026-07-05T08:57:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06400","created_at":"2026-07-05T08:57:54Z"},{"alias_kind":"pith_short_12","alias_value":"72C365E4TUCI","created_at":"2026-07-05T08:57:54Z"},{"alias_kind":"pith_short_16","alias_value":"72C365E4TUCISX4Z","created_at":"2026-07-05T08:57:54Z"},{"alias_kind":"pith_short_8","alias_value":"72C365E4","created_at":"2026-07-05T08:57:54Z"}],"graph_snapshots":[{"event_id":"sha256:92e6ed5a9c58a95dd59391a52a59cf81fc48a156de75680cda4bf79506d21cbd","target":"graph","created_at":"2026-07-05T08:57:54Z","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/2401.06400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering (VQA) is a task where an image is given, and a series of questions are asked about the image. To build an efficient VQA algorithm, a large amount of QA data is required which is very expensive. Generating synthetic QA pairs based on templates is a practical way to obtain data. However, VQA models trained on those data do not perform well on complex, human-written questions. To address this issue, we propose a new method called {\\it chain of QA for human-written questions} (CoQAH). CoQAH utilizes a sequence of QA interactions between a large language model and a VQA mo","authors_text":"Dongmyung Shin, Heejun Shin, Taehee Kim, Yeongjae Cho, Yohan Jo","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T06:49:49Z","title":"Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06400","kind":"arxiv","version":3},"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:bec1da3b8c1646611a7ecf14763a88e0e5fc5ef50db60728f4cbc75cc6fea062","target":"record","created_at":"2026-07-05T08:57:54Z","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":"80eed22087a5e688c38c03f60cedd581bae9e6faa2bde6e7c7bfb6cb5d74532b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T06:49:49Z","title_canon_sha256":"d9cc73b5d49589537d376e04d65a1eaec08582e52328d6fc4003a47f4052ff9b"},"schema_version":"1.0","source":{"id":"2401.06400","kind":"arxiv","version":3}},"canonical_sha256":"fe85bf749c9d04895f99745fab87a5aee790f9ef15b03242e817c93ec630cdce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe85bf749c9d04895f99745fab87a5aee790f9ef15b03242e817c93ec630cdce","first_computed_at":"2026-07-05T08:57:54.193220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:54.193220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nnkO+Xo4lEGCBltjBIt/mwsHODgdp5W767N5LLu1WYgQoswqA8Rqxw+eXhn41xX2aW2jG1t6+dKC+KfXJ0ltDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:54.193625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06400","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bec1da3b8c1646611a7ecf14763a88e0e5fc5ef50db60728f4cbc75cc6fea062","sha256:92e6ed5a9c58a95dd59391a52a59cf81fc48a156de75680cda4bf79506d21cbd"],"state_sha256":"7d38edd6eaace21f0a87662658f9677bd894050a19fc4cfbb41f8a071a4cec31"}