{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2NYIPDXBO7U7QOEDPYZ3P2O6UC","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":"28937be50ba225b579ee4167d3610bacbb9c9c9840d7c105f688e3b404c41ba1","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T10:07:02Z","title_canon_sha256":"5fe22536ebd3d4ccd1eb6b4187a23a12606039dc812342c9ebf58e3e81f8d075"},"schema_version":"1.0","source":{"id":"2408.09429","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09429","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09429v3","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09429","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"2NYIPDXBO7U7","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"2NYIPDXBO7U7QOED","created_at":"2026-07-05T11:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"2NYIPDXB","created_at":"2026-07-05T11:12:19Z"}],"graph_snapshots":[{"event_id":"sha256:130efb657e57c1a3795e5840880d52b5b9bb2036335394601a4c79bddf0b34bb","target":"graph","created_at":"2026-07-05T11:12:19Z","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/2408.09429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucination issues continue to affect multimodal large language models (MLLMs), with existing research mainly addressing object-level or attribute-level hallucinations, neglecting the more complex relation hallucinations that require advanced reasoning. Current benchmarks for relation hallucinations lack detailed evaluation and effective mitigation, and their datasets often suffer from biases due to systematic annotation processes. To address these challenges, we introduce Reefknot, a comprehensive benchmark targeting relation hallucinations, comprising over 20,000 real-world samples. We pro","authors_text":"Junkai Chen, Kening Zheng, Xin Zou, Xuming Hu, Yibo Yan","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T10:07:02Z","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09429","kind":"arxiv","version":3},"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":"sha256:694b2be87f47d29d37a7a08cde2ea597a663e1b3edf9409bfdec6b3b738b81b6","target":"record","created_at":"2026-07-05T11:12:19Z","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":"28937be50ba225b579ee4167d3610bacbb9c9c9840d7c105f688e3b404c41ba1","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T10:07:02Z","title_canon_sha256":"5fe22536ebd3d4ccd1eb6b4187a23a12606039dc812342c9ebf58e3e81f8d075"},"schema_version":"1.0","source":{"id":"2408.09429","kind":"arxiv","version":3}},"canonical_sha256":"d370878ee177e9f838837e33b7e9dea083ca6cb2088aa8176aa25c60834d8bbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d370878ee177e9f838837e33b7e9dea083ca6cb2088aa8176aa25c60834d8bbe","first_computed_at":"2026-07-05T11:12:19.391939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:19.391939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DVxWl44gukmRio+k4Qdj1bD9gjCJAEzfbsFsq0y2xBZakdGaXi9p8ljFSKGsW20QHl5VhZCgf6fbUqkgTIdrAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:19.392467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09429","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:694b2be87f47d29d37a7a08cde2ea597a663e1b3edf9409bfdec6b3b738b81b6","sha256:130efb657e57c1a3795e5840880d52b5b9bb2036335394601a4c79bddf0b34bb"],"state_sha256":"6bacfb4f0c76bcc3df74e3a8f8c146d8bd7c3e3ab4aa01161552c5538f095acd"}