{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2H4ONGI6QPBQNH67RI37ORBKOR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"86e52b514045fda06ef9f53ca2b70c497a6308b40546376c523995b88e9d21b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T18:38:17Z","title_canon_sha256":"ff65b5470f44b2666b0219606c237dfb7b731298ea6f0d7d01378752bf38de3a"},"schema_version":"1.0","source":{"id":"2403.04735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04735","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04735v1","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04735","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_12","alias_value":"2H4ONGI6QPBQ","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_16","alias_value":"2H4ONGI6QPBQNH67","created_at":"2026-07-05T07:53:27Z"},{"alias_kind":"pith_short_8","alias_value":"2H4ONGI6","created_at":"2026-07-05T07:53:27Z"}],"graph_snapshots":[{"event_id":"sha256:65f7f93cfefe387008e5cc076856bc47375b7778621584c90fd3a826e903415b","target":"graph","created_at":"2026-07-05T07:53:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.04735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-extended LLMs have made significant strides in Visual Question Answering (VQA). Despite these advancements, VLLMs still encounter substantial difficulties in handling queries involving long-tail entities, with a tendency to produce erroneous or hallucinated responses. In this work, we introduce a novel evaluative benchmark named \\textbf{SnapNTell}, specifically tailored for entity-centric VQA. This task aims to test the models' capabilities in identifying entities and providing detailed, entity-specific knowledge. We have developed the \\textbf{SnapNTell Dataset}, distinct from tradition","authors_text":"Andrea Madotto, Babak Damavandi, Christos Faloutsos, Jielin Qiu, Lei Li, Paul A. Crook, Seungwhan Moon, Xin Luna Dong, Yifan Ethan Xu, Zhaojiang Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T18:38:17Z","title":"SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04735","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:429e88c80c735528aa3e50c96c67aa33975f7c9d85908750e081301297c4c661","target":"record","created_at":"2026-07-05T07:53:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"86e52b514045fda06ef9f53ca2b70c497a6308b40546376c523995b88e9d21b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T18:38:17Z","title_canon_sha256":"ff65b5470f44b2666b0219606c237dfb7b731298ea6f0d7d01378752bf38de3a"},"schema_version":"1.0","source":{"id":"2403.04735","kind":"arxiv","version":1}},"canonical_sha256":"d1f8e6991e83c3069fdf8a37f7442a744b991b087dca6fb02c1e8e8987201dbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1f8e6991e83c3069fdf8a37f7442a744b991b087dca6fb02c1e8e8987201dbd","first_computed_at":"2026-07-05T07:53:27.299283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:27.299283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ruk5eh4jBixaPz2XGB3a0idbj4/ecb0L/Zr7dTSK9kPps73VAq6D70GNpY57uRX2XTDgufF76Ku4IV5dP0u8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:27.299760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:429e88c80c735528aa3e50c96c67aa33975f7c9d85908750e081301297c4c661","sha256:65f7f93cfefe387008e5cc076856bc47375b7778621584c90fd3a826e903415b"],"state_sha256":"15c3fe6d36a10d89d5d4f379f8af967d10d7ddec82d89182f3e7165bc117620c"}