{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NY53ZN45PVOKWN3JEIP7A5UH7L","short_pith_number":"pith:NY53ZN45","schema_version":"1.0","canonical_sha256":"6e3bbcb79d7d5cab3769221ff07687fae669970b8c08ddfeed4272c61d09b723","source":{"kind":"arxiv","id":"2412.18327","version":1},"attestation_state":"computed","paper":{"title":"HAUR: Human Annotation Understanding and Recognition Through Text-Heavy Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Yan, Qingqiang Wu, Qingqi Hong, Yanhao Chen, Yuchen Yang","submitted_at":"2024-12-24T10:25:41Z","abstract_excerpt":"Vision Question Answering (VQA) tasks use images to convey critical information to answer text-based questions, which is one of the most common forms of question answering in real-world scenarios. Numerous vision-text models exist today and have performed well on certain VQA tasks. However, these models exhibit significant limitations in understanding human annotations on text-heavy images. To address this, we propose the Human Annotation Understanding and Recognition (HAUR) task. As part of this effort, we introduce the Human Annotation Understanding and Recognition-5 (HAUR-5) dataset, which "},"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":"2412.18327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T10:25:41Z","cross_cats_sorted":[],"title_canon_sha256":"ea91181ed985a9b1f11d7677086afb153629101eeae1ef210ccd42a9b6f7c2a5","abstract_canon_sha256":"77ec3e74c31f2ec48b0ac39d952a9163104948a753975a6c0a64ffdaa3dfe1d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:53.922594Z","signature_b64":"jvcslfXmn4UEUNPpM4X+VGLuat0cabmHYcPzTVCl5ITqjVhuHgQhPSQfPUGUStcSMLCt0RT9CIURhNHsLfF6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e3bbcb79d7d5cab3769221ff07687fae669970b8c08ddfeed4272c61d09b723","last_reissued_at":"2026-07-05T09:53:53.922220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:53.922220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAUR: Human Annotation Understanding and Recognition Through Text-Heavy Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Yan, Qingqiang Wu, Qingqi Hong, Yanhao Chen, Yuchen Yang","submitted_at":"2024-12-24T10:25:41Z","abstract_excerpt":"Vision Question Answering (VQA) tasks use images to convey critical information to answer text-based questions, which is one of the most common forms of question answering in real-world scenarios. Numerous vision-text models exist today and have performed well on certain VQA tasks. However, these models exhibit significant limitations in understanding human annotations on text-heavy images. To address this, we propose the Human Annotation Understanding and Recognition (HAUR) task. As part of this effort, we introduce the Human Annotation Understanding and Recognition-5 (HAUR-5) dataset, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18327","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/2412.18327/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":"2412.18327","created_at":"2026-07-05T09:53:53.922274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18327v1","created_at":"2026-07-05T09:53:53.922274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18327","created_at":"2026-07-05T09:53:53.922274+00:00"},{"alias_kind":"pith_short_12","alias_value":"NY53ZN45PVOK","created_at":"2026-07-05T09:53:53.922274+00:00"},{"alias_kind":"pith_short_16","alias_value":"NY53ZN45PVOKWN3J","created_at":"2026-07-05T09:53:53.922274+00:00"},{"alias_kind":"pith_short_8","alias_value":"NY53ZN45","created_at":"2026-07-05T09:53:53.922274+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/NY53ZN45PVOKWN3JEIP7A5UH7L","json":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L.json","graph_json":"https://pith.science/api/pith-number/NY53ZN45PVOKWN3JEIP7A5UH7L/graph.json","events_json":"https://pith.science/api/pith-number/NY53ZN45PVOKWN3JEIP7A5UH7L/events.json","paper":"https://pith.science/paper/NY53ZN45"},"agent_actions":{"view_html":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L","download_json":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L.json","view_paper":"https://pith.science/paper/NY53ZN45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18327&json=true","fetch_graph":"https://pith.science/api/pith-number/NY53ZN45PVOKWN3JEIP7A5UH7L/graph.json","fetch_events":"https://pith.science/api/pith-number/NY53ZN45PVOKWN3JEIP7A5UH7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L/action/storage_attestation","attest_author":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L/action/author_attestation","sign_citation":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L/action/citation_signature","submit_replication":"https://pith.science/pith/NY53ZN45PVOKWN3JEIP7A5UH7L/action/replication_record"}},"created_at":"2026-07-05T09:53:53.922274+00:00","updated_at":"2026-07-05T09:53:53.922274+00:00"}