{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L23IT4RXNTSUUV7M6WSTCXUETF","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":"5cbdf9132b4f8bc4503f0ca0b45e5f40aae44d6dd5ac0054d526aeab4c70a705","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T23:36:06Z","title_canon_sha256":"6df81713e4710d258d895a27a39d91b79f6a1393ad8594dd4b9c4d06fbaf035e"},"schema_version":"1.0","source":{"id":"2410.18325","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18325","created_at":"2026-07-05T10:32:32Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18325v2","created_at":"2026-07-05T10:32:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18325","created_at":"2026-07-05T10:32:32Z"},{"alias_kind":"pith_short_12","alias_value":"L23IT4RXNTSU","created_at":"2026-07-05T10:32:32Z"},{"alias_kind":"pith_short_16","alias_value":"L23IT4RXNTSUUV7M","created_at":"2026-07-05T10:32:32Z"},{"alias_kind":"pith_short_8","alias_value":"L23IT4RX","created_at":"2026-07-05T10:32:32Z"}],"graph_snapshots":[{"event_id":"sha256:79d42fb618b722fbeb411d880f0c4cfe07b1c423f61ed2b00e79cd3a02f163e3","target":"graph","created_at":"2026-07-05T10:32:32Z","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/2410.18325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Following the success of Large Language Models (LLMs), expanding their boundaries to new modalities represents a significant paradigm shift in multimodal understanding. Human perception is inherently multimodal, relying not only on text but also on auditory and visual cues for a complete understanding of the world. In recognition of this fact, audio-visual LLMs have recently emerged. Despite promising developments, the lack of dedicated benchmarks poses challenges for understanding and evaluating models. In this work, we show that audio-visual LLMs struggle to discern subtle relationships betw","authors_text":"Arda Senocak, Joon Son Chung, JungMok Lee, Kim Sung-Bin, Oh Hyun-Bin, Tae-Hyun Oh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T23:36:06Z","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18325","kind":"arxiv","version":2},"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:fd999a63d0190f14a6cbdd2b92f29d48b35ce56624e4b7d9043739e7f84b6a2a","target":"record","created_at":"2026-07-05T10:32:32Z","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":"5cbdf9132b4f8bc4503f0ca0b45e5f40aae44d6dd5ac0054d526aeab4c70a705","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T23:36:06Z","title_canon_sha256":"6df81713e4710d258d895a27a39d91b79f6a1393ad8594dd4b9c4d06fbaf035e"},"schema_version":"1.0","source":{"id":"2410.18325","kind":"arxiv","version":2}},"canonical_sha256":"5eb689f2376ce54a57ecf5a5315e84996f3e13ab236f6397653093b91a281f37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eb689f2376ce54a57ecf5a5315e84996f3e13ab236f6397653093b91a281f37","first_computed_at":"2026-07-05T10:32:32.557179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:32.557179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sVf29FErYshVQTP9NkDDwlN6dnQK9RqsscvaDjw26/UmziqXfQXNueNRwr7Xn0CsDc02oaJwuPjQj9TeMpvcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:32.558232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18325","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd999a63d0190f14a6cbdd2b92f29d48b35ce56624e4b7d9043739e7f84b6a2a","sha256:79d42fb618b722fbeb411d880f0c4cfe07b1c423f61ed2b00e79cd3a02f163e3"],"state_sha256":"6133858b555ee734fd2dafbf719b548db3385e3beb41d39b562831c8c1ca4575"}