{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5QYXBWAJS5UEI2O6OLFM33G7ON","short_pith_number":"pith:5QYXBWAJ","schema_version":"1.0","canonical_sha256":"ec3170d80997684469de72cacdecdf737bed243f2391ea7a19b0a546483550ca","source":{"kind":"arxiv","id":"2311.01477","version":2},"attestation_state":"computed","paper":{"title":"FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Jing, Ruosen Li, Xinya Du, Yunmo Chen","submitted_at":"2023-11-02T01:21:45Z","abstract_excerpt":"We introduce FaithScore (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs). The FaithScore evaluation first identifies sub-sentences containing descriptive statements that need to be verified, then extracts a comprehensive list of atomic facts from these sub-sentences, and finally conducts consistency verification between fine-grained atomic facts and the input image. Meta-evaluation demonstrates that our metric highly correlates with human ju"},"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":"2311.01477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-02T01:21:45Z","cross_cats_sorted":[],"title_canon_sha256":"96a2def477176bb1d004ad253d2afcae544c6bc88e63ff41079570843985f973","abstract_canon_sha256":"7104d7b2417c5843ace70a94941050f9242ca805286dcedfdec48bb0088b2f18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:24.005911Z","signature_b64":"BuXnyI2cBOxeGDh15rKVtZNC9RQ/Nx5Do+Dt4i2sX56ehYc+CUX15bKn5d95zNzb5Bb02A04/CT91szOODguAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec3170d80997684469de72cacdecdf737bed243f2391ea7a19b0a546483550ca","last_reissued_at":"2026-07-05T09:12:24.005411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:24.005411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Jing, Ruosen Li, Xinya Du, Yunmo Chen","submitted_at":"2023-11-02T01:21:45Z","abstract_excerpt":"We introduce FaithScore (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs). The FaithScore evaluation first identifies sub-sentences containing descriptive statements that need to be verified, then extracts a comprehensive list of atomic facts from these sub-sentences, and finally conducts consistency verification between fine-grained atomic facts and the input image. Meta-evaluation demonstrates that our metric highly correlates with human ju"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01477","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/2311.01477/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":"2311.01477","created_at":"2026-07-05T09:12:24.005473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01477v2","created_at":"2026-07-05T09:12:24.005473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01477","created_at":"2026-07-05T09:12:24.005473+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QYXBWAJS5UE","created_at":"2026-07-05T09:12:24.005473+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QYXBWAJS5UEI2O6","created_at":"2026-07-05T09:12:24.005473+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QYXBWAJ","created_at":"2026-07-05T09:12:24.005473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.12455","citing_title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21300","citing_title":"Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08409","citing_title":"Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":23,"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":146,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25584","citing_title":"DualFact+: A Multimodal Fact Verification Framework for Procedural Video Understanding","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07394","citing_title":"BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON","json":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON.json","graph_json":"https://pith.science/api/pith-number/5QYXBWAJS5UEI2O6OLFM33G7ON/graph.json","events_json":"https://pith.science/api/pith-number/5QYXBWAJS5UEI2O6OLFM33G7ON/events.json","paper":"https://pith.science/paper/5QYXBWAJ"},"agent_actions":{"view_html":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON","download_json":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON.json","view_paper":"https://pith.science/paper/5QYXBWAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01477&json=true","fetch_graph":"https://pith.science/api/pith-number/5QYXBWAJS5UEI2O6OLFM33G7ON/graph.json","fetch_events":"https://pith.science/api/pith-number/5QYXBWAJS5UEI2O6OLFM33G7ON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON/action/storage_attestation","attest_author":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON/action/author_attestation","sign_citation":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON/action/citation_signature","submit_replication":"https://pith.science/pith/5QYXBWAJS5UEI2O6OLFM33G7ON/action/replication_record"}},"created_at":"2026-07-05T09:12:24.005473+00:00","updated_at":"2026-07-05T09:12:24.005473+00:00"}