{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZE6GDHAENFCSJA6IIOXW5JQA3T","short_pith_number":"pith:ZE6GDHAE","schema_version":"1.0","canonical_sha256":"c93c619c0469452483c843af6ea600dce7abdab67765ea95313ec00f8193efff","source":{"kind":"arxiv","id":"2410.04107","version":1},"attestation_state":"computed","paper":{"title":"TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"A-Long Jin, Qianru Zhang, Siu-Ming Yiu, Xingwei He, Yuan Yuan","submitted_at":"2024-10-05T10:23:14Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved remarkable progress on visual perception and linguistic interpretation. Despite their impressive capabilities across various tasks, LVLMs still suffer from the issue of hallucination, which involves generating content that is incorrect or unfaithful to the visual or textual inputs. Traditional benchmarks, such as MME and POPE, evaluate hallucination in LVLMs within the scope of Visual Question Answering (VQA) using answerable questions. However, some questions are unanswerable due to insufficient information in the images, and the performance "},"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":"2410.04107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-05T10:23:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"adaa836243e842d24ca65fb450032b2a9db546f7cd70ac77f75cd5791234d60d","abstract_canon_sha256":"11c749829f4c08767db2674f9fe07e29779aaaba9472cfa5e25ae215be036870"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:29.194190Z","signature_b64":"guAzp0WXgYK3xH+5QB6DMnr6Nq5dXAQccW/Q0t+DTxDu8FRCdWh25gzpn7+u39BASUxtDCiD/V3pd2s0GqQ0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c93c619c0469452483c843af6ea600dce7abdab67765ea95313ec00f8193efff","last_reissued_at":"2026-07-05T09:16:29.193656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:29.193656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"A-Long Jin, Qianru Zhang, Siu-Ming Yiu, Xingwei He, Yuan Yuan","submitted_at":"2024-10-05T10:23:14Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved remarkable progress on visual perception and linguistic interpretation. Despite their impressive capabilities across various tasks, LVLMs still suffer from the issue of hallucination, which involves generating content that is incorrect or unfaithful to the visual or textual inputs. Traditional benchmarks, such as MME and POPE, evaluate hallucination in LVLMs within the scope of Visual Question Answering (VQA) using answerable questions. However, some questions are unanswerable due to insufficient information in the images, and the performance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04107","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/2410.04107/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":"2410.04107","created_at":"2026-07-05T09:16:29.193737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04107v1","created_at":"2026-07-05T09:16:29.193737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04107","created_at":"2026-07-05T09:16:29.193737+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZE6GDHAENFCS","created_at":"2026-07-05T09:16:29.193737+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZE6GDHAENFCSJA6I","created_at":"2026-07-05T09:16:29.193737+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZE6GDHAE","created_at":"2026-07-05T09:16:29.193737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30557","citing_title":"Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T","json":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T.json","graph_json":"https://pith.science/api/pith-number/ZE6GDHAENFCSJA6IIOXW5JQA3T/graph.json","events_json":"https://pith.science/api/pith-number/ZE6GDHAENFCSJA6IIOXW5JQA3T/events.json","paper":"https://pith.science/paper/ZE6GDHAE"},"agent_actions":{"view_html":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T","download_json":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T.json","view_paper":"https://pith.science/paper/ZE6GDHAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04107&json=true","fetch_graph":"https://pith.science/api/pith-number/ZE6GDHAENFCSJA6IIOXW5JQA3T/graph.json","fetch_events":"https://pith.science/api/pith-number/ZE6GDHAENFCSJA6IIOXW5JQA3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T/action/storage_attestation","attest_author":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T/action/author_attestation","sign_citation":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T/action/citation_signature","submit_replication":"https://pith.science/pith/ZE6GDHAENFCSJA6IIOXW5JQA3T/action/replication_record"}},"created_at":"2026-07-05T09:16:29.193737+00:00","updated_at":"2026-07-05T09:16:29.193737+00:00"}