{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FHATJRU6AJAWH3CRVTNAW4ZJQV","short_pith_number":"pith:FHATJRU6","schema_version":"1.0","canonical_sha256":"29c134c69e024163ec51acda0b7329857a848fa7787e95e1376575931493e87d","source":{"kind":"arxiv","id":"2402.09717","version":1},"attestation_state":"computed","paper":{"title":"Visually Dehallucinative Instruction Generation: Know What You Don't Know","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheoljong Yang, Jusung Lee, Sungguk Cha, Younghyun Lee","submitted_at":"2024-02-15T05:22:04Z","abstract_excerpt":"\"When did the emperor Napoleon invented iPhone?\" Such hallucination-inducing question is well known challenge in generative language modeling. In this study, we present an innovative concept of visual hallucination, referred to as \"I Know (IK)\" hallucination, to address scenarios where \"I Don't Know\" is the desired response. To effectively tackle this issue, we propose the VQAv2-IDK benchmark, the subset of VQAv2 comprising unanswerable image-question pairs as determined by human annotators. Stepping further, we present the visually dehallucinative instruction generation method for IK hallucin"},"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":"2402.09717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-15T05:22:04Z","cross_cats_sorted":[],"title_canon_sha256":"b227b5d331535d65e3d51dd31b103f4bf99981573346bdf9d862b09a440f57ab","abstract_canon_sha256":"555a6b04be7eabde0fbfda2d51ad5d7fa1193f53ecd95113709669dc44422f72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:35.550387Z","signature_b64":"9/+awOkcgZEBqiq7nQEH7ChdEb7vVCNMOYmVeUM+isgKiZ5+Ij6I9HQa01wSBPzuexQIb80JAd+vDHerftXlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29c134c69e024163ec51acda0b7329857a848fa7787e95e1376575931493e87d","last_reissued_at":"2026-07-05T07:45:35.549907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:35.549907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visually Dehallucinative Instruction Generation: Know What You Don't Know","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheoljong Yang, Jusung Lee, Sungguk Cha, Younghyun Lee","submitted_at":"2024-02-15T05:22:04Z","abstract_excerpt":"\"When did the emperor Napoleon invented iPhone?\" Such hallucination-inducing question is well known challenge in generative language modeling. In this study, we present an innovative concept of visual hallucination, referred to as \"I Know (IK)\" hallucination, to address scenarios where \"I Don't Know\" is the desired response. To effectively tackle this issue, we propose the VQAv2-IDK benchmark, the subset of VQAv2 comprising unanswerable image-question pairs as determined by human annotators. Stepping further, we present the visually dehallucinative instruction generation method for IK hallucin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09717","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/2402.09717/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":"2402.09717","created_at":"2026-07-05T07:45:35.549965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09717v1","created_at":"2026-07-05T07:45:35.549965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09717","created_at":"2026-07-05T07:45:35.549965+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHATJRU6AJAW","created_at":"2026-07-05T07:45:35.549965+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHATJRU6AJAWH3CR","created_at":"2026-07-05T07:45:35.549965+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHATJRU6","created_at":"2026-07-05T07:45:35.549965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV","json":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV.json","graph_json":"https://pith.science/api/pith-number/FHATJRU6AJAWH3CRVTNAW4ZJQV/graph.json","events_json":"https://pith.science/api/pith-number/FHATJRU6AJAWH3CRVTNAW4ZJQV/events.json","paper":"https://pith.science/paper/FHATJRU6"},"agent_actions":{"view_html":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV","download_json":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV.json","view_paper":"https://pith.science/paper/FHATJRU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09717&json=true","fetch_graph":"https://pith.science/api/pith-number/FHATJRU6AJAWH3CRVTNAW4ZJQV/graph.json","fetch_events":"https://pith.science/api/pith-number/FHATJRU6AJAWH3CRVTNAW4ZJQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV/action/storage_attestation","attest_author":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV/action/author_attestation","sign_citation":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV/action/citation_signature","submit_replication":"https://pith.science/pith/FHATJRU6AJAWH3CRVTNAW4ZJQV/action/replication_record"}},"created_at":"2026-07-05T07:45:35.549965+00:00","updated_at":"2026-07-05T07:45:35.549965+00:00"}