{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DNJSMXLPJKLU7BGHCMCYV7LYZJ","short_pith_number":"pith:DNJSMXLP","schema_version":"1.0","canonical_sha256":"1b53265d6f4a974f84c713058afd78ca738cb38c7336c718041384abe69e5660","source":{"kind":"arxiv","id":"2407.15680","version":1},"attestation_state":"computed","paper":{"title":"HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Adams Yu, Garrett Bingham, Golnaz Ghiasi, Quoc Le, Thang Luong, Zhecan Wang","submitted_at":"2024-07-22T14:49:51Z","abstract_excerpt":"Hallucination has been a major problem for large language models and remains a critical challenge when it comes to multimodality in which vision-language models (VLMs) have to deal with not just textual but also visual inputs. Despite rapid progress in VLMs, resources for evaluating and addressing multimodal hallucination are limited and mostly focused on evaluation. This work introduces HaloQuest, a novel visual question answering dataset that captures various aspects of multimodal hallucination such as false premises, insufficient contexts, and visual challenges. A novel idea from HaloQuest "},"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":"2407.15680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T14:49:51Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"74a6e1a6b7f2f7f7970626d2f608cafa58e6232fb3c6a74b11333efb7567522f","abstract_canon_sha256":"b471b47ae941e8c69fc957f303e99f70ced844c3bcaef98de843b1ff36165486"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:59.687983Z","signature_b64":"XJu2IJuObF8NYiDXpO2RR2gJhjlhUnt74NOul2cITwt3uoNCUAejeDJ7S5cZpsuWZdpT9uqsCfv2peeBsWXNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b53265d6f4a974f84c713058afd78ca738cb38c7336c718041384abe69e5660","last_reissued_at":"2026-07-05T08:46:59.687489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:59.687489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Adams Yu, Garrett Bingham, Golnaz Ghiasi, Quoc Le, Thang Luong, Zhecan Wang","submitted_at":"2024-07-22T14:49:51Z","abstract_excerpt":"Hallucination has been a major problem for large language models and remains a critical challenge when it comes to multimodality in which vision-language models (VLMs) have to deal with not just textual but also visual inputs. Despite rapid progress in VLMs, resources for evaluating and addressing multimodal hallucination are limited and mostly focused on evaluation. This work introduces HaloQuest, a novel visual question answering dataset that captures various aspects of multimodal hallucination such as false premises, insufficient contexts, and visual challenges. A novel idea from HaloQuest "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15680","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/2407.15680/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":"2407.15680","created_at":"2026-07-05T08:46:59.687549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15680v1","created_at":"2026-07-05T08:46:59.687549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15680","created_at":"2026-07-05T08:46:59.687549+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNJSMXLPJKLU","created_at":"2026-07-05T08:46:59.687549+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNJSMXLPJKLU7BGH","created_at":"2026-07-05T08:46:59.687549+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNJSMXLP","created_at":"2026-07-05T08:46:59.687549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ","json":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ.json","graph_json":"https://pith.science/api/pith-number/DNJSMXLPJKLU7BGHCMCYV7LYZJ/graph.json","events_json":"https://pith.science/api/pith-number/DNJSMXLPJKLU7BGHCMCYV7LYZJ/events.json","paper":"https://pith.science/paper/DNJSMXLP"},"agent_actions":{"view_html":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ","download_json":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ.json","view_paper":"https://pith.science/paper/DNJSMXLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15680&json=true","fetch_graph":"https://pith.science/api/pith-number/DNJSMXLPJKLU7BGHCMCYV7LYZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DNJSMXLPJKLU7BGHCMCYV7LYZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ/action/storage_attestation","attest_author":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ/action/author_attestation","sign_citation":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ/action/citation_signature","submit_replication":"https://pith.science/pith/DNJSMXLPJKLU7BGHCMCYV7LYZJ/action/replication_record"}},"created_at":"2026-07-05T08:46:59.687549+00:00","updated_at":"2026-07-05T08:46:59.687549+00:00"}