{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E3VQXWGNPTCNQVWB43MXBZWDZS","short_pith_number":"pith:E3VQXWGN","schema_version":"1.0","canonical_sha256":"26eb0bd8cd7cc4d856c1e6d970e6c3ccb548475f42fba484cf9176aeaf1bc636","source":{"kind":"arxiv","id":"2405.19186","version":2},"attestation_state":"computed","paper":{"title":"MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanno Gottschalk, Jakob Spiegelberg, Laura Fieback","submitted_at":"2024-05-29T15:28:42Z","abstract_excerpt":"Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon referred to as hallucinations, remain an unsolved problem with regard to the trustworthiness of LVLMs. To address this problem, recent works proposed to incorporate computationally costly Large (Vision) Language Models in order to detect hallucinations on a sentence- or subsentence-level. In this work, we introduce MetaToken, a lightweight binary classifier to "},"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":"2405.19186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T15:28:42Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a32f88d05f1d7ac6fad217819443728ac9ffe84d1a21198ba980aa3fb7045f3d","abstract_canon_sha256":"cd7e99893de5a0ba131f494807d40149160ea7d2075c9480a27d26ba59122d20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:33.624344Z","signature_b64":"Oo9YCUnESWhKZNisN2akBMc6qo7YN6VGZ2nzAVbrcx6oH+wCiur0a2KYqQHLJVrgCkCwO9nzoqYG7KunbFjDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26eb0bd8cd7cc4d856c1e6d970e6c3ccb548475f42fba484cf9176aeaf1bc636","last_reissued_at":"2026-07-05T10:38:33.623865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:33.623865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanno Gottschalk, Jakob Spiegelberg, Laura Fieback","submitted_at":"2024-05-29T15:28:42Z","abstract_excerpt":"Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon referred to as hallucinations, remain an unsolved problem with regard to the trustworthiness of LVLMs. To address this problem, recent works proposed to incorporate computationally costly Large (Vision) Language Models in order to detect hallucinations on a sentence- or subsentence-level. In this work, we introduce MetaToken, a lightweight binary classifier to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19186","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/2405.19186/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":"2405.19186","created_at":"2026-07-05T10:38:33.623914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19186v2","created_at":"2026-07-05T10:38:33.623914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19186","created_at":"2026-07-05T10:38:33.623914+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3VQXWGNPTCN","created_at":"2026-07-05T10:38:33.623914+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3VQXWGNPTCNQVWB","created_at":"2026-07-05T10:38:33.623914+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3VQXWGN","created_at":"2026-07-05T10:38:33.623914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS","json":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS.json","graph_json":"https://pith.science/api/pith-number/E3VQXWGNPTCNQVWB43MXBZWDZS/graph.json","events_json":"https://pith.science/api/pith-number/E3VQXWGNPTCNQVWB43MXBZWDZS/events.json","paper":"https://pith.science/paper/E3VQXWGN"},"agent_actions":{"view_html":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS","download_json":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS.json","view_paper":"https://pith.science/paper/E3VQXWGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19186&json=true","fetch_graph":"https://pith.science/api/pith-number/E3VQXWGNPTCNQVWB43MXBZWDZS/graph.json","fetch_events":"https://pith.science/api/pith-number/E3VQXWGNPTCNQVWB43MXBZWDZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS/action/storage_attestation","attest_author":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS/action/author_attestation","sign_citation":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS/action/citation_signature","submit_replication":"https://pith.science/pith/E3VQXWGNPTCNQVWB43MXBZWDZS/action/replication_record"}},"created_at":"2026-07-05T10:38:33.623914+00:00","updated_at":"2026-07-05T10:38:33.623914+00:00"}