{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B6QOIM6VMXEWI6JKXFQLALRSHE","short_pith_number":"pith:B6QOIM6V","schema_version":"1.0","canonical_sha256":"0fa0e433d565c964792ab960b02e323907a32621ffed6ea6f28b84d95e01f73c","source":{"kind":"arxiv","id":"2309.04041","version":2},"attestation_state":"computed","paper":{"title":"Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baochen Sun, Carl Yang, Jiaying Lu, Jie Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang","submitted_at":"2023-09-07T22:59:56Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is their constrained semantic grounding ability, which pertains to connecting language to the physical-world entities or concepts referenced in images. Therefore, a crucial need arises for a comprehensive study to assess the semantic grounding ability of widely used LVLMs. Despite the significance, sufficient investigation in this direction is currently lacking"},"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":"2309.04041","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-07T22:59:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0c0344880b7b1c78bb5ec1cb34691043a46375b719ef983c43e61f3df598361d","abstract_canon_sha256":"70fa50c236999af8d20071ca534662ed7d703f99fc3c66e105aa17edb353b8db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:19.580694Z","signature_b64":"2dMaNx1LMZKlL6Z7hKwsJ0GGC6l+3FPm+6jiKNXRo5/mQK9w4F+qCEoiDCDx6Nl/TlJvekryRqYuKNRAYSiOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fa0e433d565c964792ab960b02e323907a32621ffed6ea6f28b84d95e01f73c","last_reissued_at":"2026-07-05T07:33:19.580153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:19.580153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baochen Sun, Carl Yang, Jiaying Lu, Jie Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang","submitted_at":"2023-09-07T22:59:56Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is their constrained semantic grounding ability, which pertains to connecting language to the physical-world entities or concepts referenced in images. Therefore, a crucial need arises for a comprehensive study to assess the semantic grounding ability of widely used LVLMs. Despite the significance, sufficient investigation in this direction is currently lacking"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04041","kind":"arxiv","version":2},"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/2309.04041/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":"2309.04041","created_at":"2026-07-05T07:33:19.580211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04041v2","created_at":"2026-07-05T07:33:19.580211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04041","created_at":"2026-07-05T07:33:19.580211+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6QOIM6VMXEW","created_at":"2026-07-05T07:33:19.580211+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6QOIM6VMXEWI6JK","created_at":"2026-07-05T07:33:19.580211+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6QOIM6V","created_at":"2026-07-05T07:33:19.580211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":204,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE","json":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE.json","graph_json":"https://pith.science/api/pith-number/B6QOIM6VMXEWI6JKXFQLALRSHE/graph.json","events_json":"https://pith.science/api/pith-number/B6QOIM6VMXEWI6JKXFQLALRSHE/events.json","paper":"https://pith.science/paper/B6QOIM6V"},"agent_actions":{"view_html":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE","download_json":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE.json","view_paper":"https://pith.science/paper/B6QOIM6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04041&json=true","fetch_graph":"https://pith.science/api/pith-number/B6QOIM6VMXEWI6JKXFQLALRSHE/graph.json","fetch_events":"https://pith.science/api/pith-number/B6QOIM6VMXEWI6JKXFQLALRSHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE/action/storage_attestation","attest_author":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE/action/author_attestation","sign_citation":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE/action/citation_signature","submit_replication":"https://pith.science/pith/B6QOIM6VMXEWI6JKXFQLALRSHE/action/replication_record"}},"created_at":"2026-07-05T07:33:19.580211+00:00","updated_at":"2026-07-05T07:33:19.580211+00:00"}