{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HWXWQCCX4DIW67FTQ3ZK5IG5FA","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":"0d948b10c5497f944a1f8d80fc3f8cd8072eb4db85cd249f2c9c2d3bc72f6a8d","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T17:41:23Z","title_canon_sha256":"73e2f3ad62282d79451694cf3f18961c0e91d3ba760faae2c2b24b3f0d7ae3a1"},"schema_version":"1.0","source":{"id":"2412.02611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02611","created_at":"2026-07-05T09:43:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02611v1","created_at":"2026-07-05T09:43:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02611","created_at":"2026-07-05T09:43:52Z"},{"alias_kind":"pith_short_12","alias_value":"HWXWQCCX4DIW","created_at":"2026-07-05T09:43:52Z"},{"alias_kind":"pith_short_16","alias_value":"HWXWQCCX4DIW67FT","created_at":"2026-07-05T09:43:52Z"},{"alias_kind":"pith_short_8","alias_value":"HWXWQCCX","created_at":"2026-07-05T09:43:52Z"}],"graph_snapshots":[{"event_id":"sha256:dbce8c2a4c62fc42f560931c6c3b86cfc78202ae62034fa171944e51073b0a2c","target":"graph","created_at":"2026-07-05T09:43:52Z","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/2412.02611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, multimodal large language models (MLLMs), such as GPT-4o, Gemini 1.5 Pro, and Reka Core, have expanded their capabilities to include vision and audio modalities. While these models demonstrate impressive performance across a wide range of audio-visual applications, our proposed DeafTest reveals that MLLMs often struggle with simple tasks humans find trivial: 1) determining which of two sounds is louder, and 2) determining which of two sounds has a higher pitch. Motivated by these observations, we introduce AV-Odyssey Bench, a comprehensive audio-visual benchmark designed to assess wh","authors_text":"Benyou Wang, Bohao Li, Jiaming Han, Kaituo Feng, Kaixiong Gong, Mofan Cheng, Shijia Yang, Xiangyu Yue, Yibing Wang, Yutong Bai, Zhuoran Yang","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T17:41:23Z","title":"AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02611","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":"sha256:5309bac598c2c0c8574f5624f742605245784df86cfdc2fc0038a33ad9420b2a","target":"record","created_at":"2026-07-05T09:43:52Z","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":"0d948b10c5497f944a1f8d80fc3f8cd8072eb4db85cd249f2c9c2d3bc72f6a8d","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T17:41:23Z","title_canon_sha256":"73e2f3ad62282d79451694cf3f18961c0e91d3ba760faae2c2b24b3f0d7ae3a1"},"schema_version":"1.0","source":{"id":"2412.02611","kind":"arxiv","version":1}},"canonical_sha256":"3daf680857e0d16f7cb386f2aea0dd282e5ba3220167ae299688d5c4fde3694b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3daf680857e0d16f7cb386f2aea0dd282e5ba3220167ae299688d5c4fde3694b","first_computed_at":"2026-07-05T09:43:52.344397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:52.344397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wf6TgMrdn8A+QSS0eAl5niuJbx0V6u4VgW97t09CTl/XXpJYcQbLrlyIvd2Jd+bntpgAj58TpwSYrGAewKPKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:52.344870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5309bac598c2c0c8574f5624f742605245784df86cfdc2fc0038a33ad9420b2a","sha256:dbce8c2a4c62fc42f560931c6c3b86cfc78202ae62034fa171944e51073b0a2c"],"state_sha256":"7068d2e2700cc61422e5be9c390d2c7fd6be119aeeb57f29a0d1e04519305312"}