{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U3FOD42Y2AP7VYVIEYBQDP4FTU","short_pith_number":"pith:U3FOD42Y","schema_version":"1.0","canonical_sha256":"a6cae1f358d01ffae2a8260301bf859d2595c09afe201f86142439c184d8d056","source":{"kind":"arxiv","id":"2501.02135","version":1},"attestation_state":"computed","paper":{"title":"AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Mohamed Elhoseiny, Ruohan Gao, Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta, Yaoting Wang","submitted_at":"2025-01-03T23:03:24Z","abstract_excerpt":"With the rapid advancement of Multi-modal Large Language Models (MLLMs), several diagnostic benchmarks have recently been developed to assess these models' multi-modal reasoning proficiency. However, these benchmarks are restricted to assessing primarily the visual aspect and do not examine the holistic audio-visual (AV) understanding. Moreover, currently, there are no benchmarks that investigate the capabilities of AVLLMs to calibrate their responses when presented with perturbed inputs. To this end, we introduce Audio-Visual Trustworthiness assessment Benchmark (AVTrustBench), comprising 600"},"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":"2501.02135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T23:03:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0de08e1270f53cee3b1fe0897907fa745c17e263b9e193f0d5c36e01106d879d","abstract_canon_sha256":"4a01de5801cd0fc5dd2b65921800c1c0dad49b766486ac0de397a27d1bfa8189"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:02.701226Z","signature_b64":"Ljwx84C+cJ9RrgAfHfmIfnmMor5OhKuUnY3ZPk7S1MEGlmcDtPXt4YsC/gp+myZNvJDekFz/goRo3+IYIOiEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6cae1f358d01ffae2a8260301bf859d2595c09afe201f86142439c184d8d056","last_reissued_at":"2026-07-05T09:57:02.700809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:02.700809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Mohamed Elhoseiny, Ruohan Gao, Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta, Yaoting Wang","submitted_at":"2025-01-03T23:03:24Z","abstract_excerpt":"With the rapid advancement of Multi-modal Large Language Models (MLLMs), several diagnostic benchmarks have recently been developed to assess these models' multi-modal reasoning proficiency. However, these benchmarks are restricted to assessing primarily the visual aspect and do not examine the holistic audio-visual (AV) understanding. Moreover, currently, there are no benchmarks that investigate the capabilities of AVLLMs to calibrate their responses when presented with perturbed inputs. To this end, we introduce Audio-Visual Trustworthiness assessment Benchmark (AVTrustBench), comprising 600"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02135","kind":"arxiv","version":1},"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/2501.02135/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":"2501.02135","created_at":"2026-07-05T09:57:02.700861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02135v1","created_at":"2026-07-05T09:57:02.700861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02135","created_at":"2026-07-05T09:57:02.700861+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3FOD42Y2AP7","created_at":"2026-07-05T09:57:02.700861+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3FOD42Y2AP7VYVI","created_at":"2026-07-05T09:57:02.700861+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3FOD42Y","created_at":"2026-07-05T09:57:02.700861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18758","citing_title":"OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02605","citing_title":"Do Audio-Visual Large Language Models Really See and Hear?","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU","json":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU.json","graph_json":"https://pith.science/api/pith-number/U3FOD42Y2AP7VYVIEYBQDP4FTU/graph.json","events_json":"https://pith.science/api/pith-number/U3FOD42Y2AP7VYVIEYBQDP4FTU/events.json","paper":"https://pith.science/paper/U3FOD42Y"},"agent_actions":{"view_html":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU","download_json":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU.json","view_paper":"https://pith.science/paper/U3FOD42Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02135&json=true","fetch_graph":"https://pith.science/api/pith-number/U3FOD42Y2AP7VYVIEYBQDP4FTU/graph.json","fetch_events":"https://pith.science/api/pith-number/U3FOD42Y2AP7VYVIEYBQDP4FTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU/action/storage_attestation","attest_author":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU/action/author_attestation","sign_citation":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU/action/citation_signature","submit_replication":"https://pith.science/pith/U3FOD42Y2AP7VYVIEYBQDP4FTU/action/replication_record"}},"created_at":"2026-07-05T09:57:02.700861+00:00","updated_at":"2026-07-05T09:57:02.700861+00:00"}