{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DLOXI7VQYHR6HHMOTJ3V3QDBNX","short_pith_number":"pith:DLOXI7VQ","schema_version":"1.0","canonical_sha256":"1add747eb0c1e3e39d8e9a775dc0616df776568d30e1fd2272f9cb52f9aff968","source":{"kind":"arxiv","id":"2411.10867","version":2},"attestation_state":"computed","paper":{"title":"ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aarush Sinha, Aishwarya Naresh Reganti, Aman Bansal, Aman Chadha, Amitava Das, Amit P. Sheth, Garv Kaushik, Prathiksha Rumale Vishwanath, Samyak Rajesh Jain, Sarthak Jain, Vinija Jain, Vipula Rawte","submitted_at":"2024-11-16T19:23:12Z","abstract_excerpt":"Recent advances in Large Multimodal Models (LMMs) have expanded their capabilities to video understanding, with Text-to-Video (T2V) models excelling in generating videos from textual prompts. However, they still frequently produce hallucinated content, revealing AI-generated inconsistencies. We introduce ViBe (https://vibe-t2v-bench.github.io/): a large-scale dataset of hallucinated videos from open-source T2V models. We identify five major hallucination types: Vanishing Subject, Omission Error, Numeric Variability, Subject Dysmorphia, and Visual Incongruity. Using ten T2V models, we generated"},"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":"2411.10867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T19:23:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d59186b6e1d9ffbb518e79bb2b370f68c9e886e43a1358f2ff6c2020a032b12c","abstract_canon_sha256":"3e5e9f3cfeb9f14f53929536f0f0ff5255483659e844d77d70c12a54087c9f97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:41.231194Z","signature_b64":"kGyvp+DPQX1BHCIKNyppjDxqPTx9RJ/xLUFbGGysolCv3HZ5dLShnSsBv5MgKvo08XZK6Ajx4d2B/GVAKZZOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1add747eb0c1e3e39d8e9a775dc0616df776568d30e1fd2272f9cb52f9aff968","last_reissued_at":"2026-07-05T10:35:41.230643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:41.230643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aarush Sinha, Aishwarya Naresh Reganti, Aman Bansal, Aman Chadha, Amitava Das, Amit P. Sheth, Garv Kaushik, Prathiksha Rumale Vishwanath, Samyak Rajesh Jain, Sarthak Jain, Vinija Jain, Vipula Rawte","submitted_at":"2024-11-16T19:23:12Z","abstract_excerpt":"Recent advances in Large Multimodal Models (LMMs) have expanded their capabilities to video understanding, with Text-to-Video (T2V) models excelling in generating videos from textual prompts. However, they still frequently produce hallucinated content, revealing AI-generated inconsistencies. We introduce ViBe (https://vibe-t2v-bench.github.io/): a large-scale dataset of hallucinated videos from open-source T2V models. We identify five major hallucination types: Vanishing Subject, Omission Error, Numeric Variability, Subject Dysmorphia, and Visual Incongruity. Using ten T2V models, we generated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10867","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/2411.10867/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":"2411.10867","created_at":"2026-07-05T10:35:41.230715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10867v2","created_at":"2026-07-05T10:35:41.230715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10867","created_at":"2026-07-05T10:35:41.230715+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLOXI7VQYHR6","created_at":"2026-07-05T10:35:41.230715+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLOXI7VQYHR6HHMO","created_at":"2026-07-05T10:35:41.230715+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLOXI7VQ","created_at":"2026-07-05T10:35:41.230715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX","json":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX.json","graph_json":"https://pith.science/api/pith-number/DLOXI7VQYHR6HHMOTJ3V3QDBNX/graph.json","events_json":"https://pith.science/api/pith-number/DLOXI7VQYHR6HHMOTJ3V3QDBNX/events.json","paper":"https://pith.science/paper/DLOXI7VQ"},"agent_actions":{"view_html":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX","download_json":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX.json","view_paper":"https://pith.science/paper/DLOXI7VQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10867&json=true","fetch_graph":"https://pith.science/api/pith-number/DLOXI7VQYHR6HHMOTJ3V3QDBNX/graph.json","fetch_events":"https://pith.science/api/pith-number/DLOXI7VQYHR6HHMOTJ3V3QDBNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX/action/storage_attestation","attest_author":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX/action/author_attestation","sign_citation":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX/action/citation_signature","submit_replication":"https://pith.science/pith/DLOXI7VQYHR6HHMOTJ3V3QDBNX/action/replication_record"}},"created_at":"2026-07-05T10:35:41.230715+00:00","updated_at":"2026-07-05T10:35:41.230715+00:00"}