{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L23IT4RXNTSUUV7M6WSTCXUETF","short_pith_number":"pith:L23IT4RX","schema_version":"1.0","canonical_sha256":"5eb689f2376ce54a57ecf5a5315e84996f3e13ab236f6397653093b91a281f37","source":{"kind":"arxiv","id":"2410.18325","version":2},"attestation_state":"computed","paper":{"title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arda Senocak, Joon Son Chung, JungMok Lee, Kim Sung-Bin, Oh Hyun-Bin, Tae-Hyun Oh","submitted_at":"2024-10-23T23:36:06Z","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"},"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":"2410.18325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T23:36:06Z","cross_cats_sorted":[],"title_canon_sha256":"6df81713e4710d258d895a27a39d91b79f6a1393ad8594dd4b9c4d06fbaf035e","abstract_canon_sha256":"5cbdf9132b4f8bc4503f0ca0b45e5f40aae44d6dd5ac0054d526aeab4c70a705"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:32.558232Z","signature_b64":"sVf29FErYshVQTP9NkDDwlN6dnQK9RqsscvaDjw26/UmziqXfQXNueNRwr7Xn0CsDc02oaJwuPjQj9TeMpvcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eb689f2376ce54a57ecf5a5315e84996f3e13ab236f6397653093b91a281f37","last_reissued_at":"2026-07-05T10:32:32.557179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:32.557179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arda Senocak, Joon Son Chung, JungMok Lee, Kim Sung-Bin, Oh Hyun-Bin, Tae-Hyun Oh","submitted_at":"2024-10-23T23:36:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18325","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/2410.18325/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":"2410.18325","created_at":"2026-07-05T10:32:32.557302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18325v2","created_at":"2026-07-05T10:32:32.557302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18325","created_at":"2026-07-05T10:32:32.557302+00:00"},{"alias_kind":"pith_short_12","alias_value":"L23IT4RXNTSU","created_at":"2026-07-05T10:32:32.557302+00:00"},{"alias_kind":"pith_short_16","alias_value":"L23IT4RXNTSUUV7M","created_at":"2026-07-05T10:32:32.557302+00:00"},{"alias_kind":"pith_short_8","alias_value":"L23IT4RX","created_at":"2026-07-05T10:32:32.557302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20970","citing_title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00247","citing_title":"Adaptive Perturbation Selection for Contrastive Audio Decoding","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07643","citing_title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30059","citing_title":"From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15148","citing_title":"XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02605","citing_title":"Do Audio-Visual Large Language Models Really See and Hear?","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03995","citing_title":"A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07593","citing_title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14129","citing_title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14520","citing_title":"Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16902","citing_title":"Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF","json":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF.json","graph_json":"https://pith.science/api/pith-number/L23IT4RXNTSUUV7M6WSTCXUETF/graph.json","events_json":"https://pith.science/api/pith-number/L23IT4RXNTSUUV7M6WSTCXUETF/events.json","paper":"https://pith.science/paper/L23IT4RX"},"agent_actions":{"view_html":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF","download_json":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF.json","view_paper":"https://pith.science/paper/L23IT4RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18325&json=true","fetch_graph":"https://pith.science/api/pith-number/L23IT4RXNTSUUV7M6WSTCXUETF/graph.json","fetch_events":"https://pith.science/api/pith-number/L23IT4RXNTSUUV7M6WSTCXUETF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF/action/storage_attestation","attest_author":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF/action/author_attestation","sign_citation":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF/action/citation_signature","submit_replication":"https://pith.science/pith/L23IT4RXNTSUUV7M6WSTCXUETF/action/replication_record"}},"created_at":"2026-07-05T10:32:32.557302+00:00","updated_at":"2026-07-05T10:32:32.557302+00:00"}