{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U64TJUDLUSU3ADBVKK5NBCM6WO","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":"1fd9151593173bbf1fa725b6c566a4a9b90f9098fa23ef1f3db8cf0467fe8100","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-11T01:01:44Z","title_canon_sha256":"7c96d7c6760ddc6bff0aecef341c32514dbba61debfcd09493a5691b9a367bbc"},"schema_version":"1.0","source":{"id":"2505.06803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06803","created_at":"2026-07-05T11:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06803v1","created_at":"2026-07-05T11:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06803","created_at":"2026-07-05T11:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"U64TJUDLUSU3","created_at":"2026-07-05T11:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"U64TJUDLUSU3ADBV","created_at":"2026-07-05T11:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"U64TJUDL","created_at":"2026-07-05T11:01:15Z"}],"graph_snapshots":[{"event_id":"sha256:8f794087033bf619bbb4ddfbc3ade39fef20ec894da2d6fc3e7cb1166965f191","target":"graph","created_at":"2026-07-05T11:01:15Z","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/2505.06803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio large language models (LLMs) are considered experts at recognizing sound objects, yet their performance relative to LLMs in other sensory modalities, such as visual or audio-visual LLMs, and to humans using their ears, eyes, or both remains unexplored. To investigate this, we systematically evaluate audio, visual, and audio-visual LLMs, specifically Qwen2-Audio, Qwen2-VL, and Qwen2.5-Omni, against humans in recognizing sound objects of different classes from audio-only, silent video, or sounded video inputs. We uncover a performance gap between Qwen2-Audio and Qwen2-VL that parallels the","authors_text":"Junkai Wu, Nima Mesgarani, Vishal Choudhari, Xilin Jiang","cross_cats":["cs.CL","cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-11T01:01:44Z","title":"Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06803","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":"sha256:0606dd2ecc4a5d0b622315872165ecf7c2a2fdadf2b95916b629d267d31b690d","target":"record","created_at":"2026-07-05T11:01:15Z","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":"1fd9151593173bbf1fa725b6c566a4a9b90f9098fa23ef1f3db8cf0467fe8100","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-11T01:01:44Z","title_canon_sha256":"7c96d7c6760ddc6bff0aecef341c32514dbba61debfcd09493a5691b9a367bbc"},"schema_version":"1.0","source":{"id":"2505.06803","kind":"arxiv","version":1}},"canonical_sha256":"a7b934d06ba4a9b00c3552bad0899eb3931c7a60f2f76fc7bc085625b12633d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7b934d06ba4a9b00c3552bad0899eb3931c7a60f2f76fc7bc085625b12633d7","first_computed_at":"2026-07-05T11:01:15.990284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:15.990284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jAygtKV9lREyoVt7SBhUPdB5ZD91leYB4kDLsxIC6Z50mvApWLF2Lo33V4mtl0WmkAy8Ks+TjD7bE4HfEAyeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:15.990832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0606dd2ecc4a5d0b622315872165ecf7c2a2fdadf2b95916b629d267d31b690d","sha256:8f794087033bf619bbb4ddfbc3ade39fef20ec894da2d6fc3e7cb1166965f191"],"state_sha256":"bda0daaff07a645ed495f3fd6601c75e41ae75a9d145f7ca16519565c0b30fa7"}