{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B67AW5CHREYTXE5IWIWTEKXGAE","short_pith_number":"pith:B67AW5CH","canonical_record":{"source":{"id":"2502.04326","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T18:59:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ed6a53c364bbeb8baa039d1b28da43b1abbf6d28b95c5ed889d1e5a8e88afe4","abstract_canon_sha256":"e6e693f0a6a7a9ed5e057f30399701ce9984f76b3b747e47a28b490fd1a84d67"},"schema_version":"1.0"},"canonical_sha256":"0fbe0b744789313b93a8b22d322ae6012ded139e34f5e623b3294fc1413289ad","source":{"kind":"arxiv","id":"2502.04326","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04326","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04326v3","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04326","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"B67AW5CHREYT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"B67AW5CHREYTXE5I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"B67AW5CH","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B67AW5CHREYTXE5IWIWTEKXGAE","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04326","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T18:59:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ed6a53c364bbeb8baa039d1b28da43b1abbf6d28b95c5ed889d1e5a8e88afe4","abstract_canon_sha256":"e6e693f0a6a7a9ed5e057f30399701ce9984f76b3b747e47a28b490fd1a84d67"},"schema_version":"1.0"},"canonical_sha256":"0fbe0b744789313b93a8b22d322ae6012ded139e34f5e623b3294fc1413289ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.897310Z","signature_b64":"raRYUF3r/XddOKRPPWfst3VKWDgR6n0s37BF3M3zXGo6SSt/hVWCbHo2E9shuOWvZT+Zh6ux+xa/h+U/cdkEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fbe0b744789313b93a8b22d322ae6012ded139e34f5e623b3294fc1413289ad","last_reissued_at":"2026-05-17T23:38:14.896721Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.896721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04326","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYhLGAY67tCFcKlM4YUNtz0sIJH046S+AoI0Dw5iVU+7aANqWHnvVdf14S9J2CwqvLVd18fHF0B9VwEkjTcrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:07:59.800714Z"},"content_sha256":"88252017d6db17b526093dd540fd2dfd0dd5b2dd7f26baccccdee02be78d1420","schema_version":"1.0","event_id":"sha256:88252017d6db17b526093dd540fd2dfd0dd5b2dd7f26baccccdee02be78d1420"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B67AW5CHREYTXE5IWIWTEKXGAE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The WorldSense benchmark shows that current multimodal models reach at most 65.1 percent accuracy on tasks requiring tight audio-visual synergy in real-world videos.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jack Hong, Jiayin Cai, Shilin Yan, Weidi Xie, Xiaolong Jiang, Yao Hu","submitted_at":"2025-02-06T18:59:40Z","abstract_excerpt":"We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. In contrast to existing benchmarks, our WorldSense has several features: (i)collaboration of omni-modality, we design the evaluation tasks to feature a strong coupling of audio and video, requiring models to effectively utilize the synergistic perception of omni-modality; (ii)diversity of videos and tasks, WorldSense encompasses a diverse collection of 1,662 audio-visual synchronised videos, systematically categorized into 8 primary domains"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The experimental results indicate that existing models face significant challenges in understanding real-world scenarios (65.1% best accuracy).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the manually annotated QA pairs and the chosen 26 tasks accurately capture the requirements of real-world omnimodal understanding without introducing annotation bias or task selection that favors certain model architectures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The WorldSense benchmark shows that current multimodal models reach at most 65.1 percent accuracy on tasks requiring tight audio-visual synergy in real-world videos.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"50adba971c83e578b0db0f61842488817d112d8f728ff1225605f288b2be8517"},"source":{"id":"2502.04326","kind":"arxiv","version":3},"verdict":{"id":"d0ba289f-76ac-403e-85e1-c767a36b905d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T05:48:39.250838Z","strongest_claim":"The experimental results indicate that existing models face significant challenges in understanding real-world scenarios (65.1% best accuracy).","one_line_summary":"WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the manually annotated QA pairs and the chosen 26 tasks accurately capture the requirements of real-world omnimodal understanding without introducing annotation bias or task selection that favors certain model architectures.","pith_extraction_headline":"The WorldSense benchmark shows that current multimodal models reach at most 65.1 percent accuracy on tasks requiring tight audio-visual synergy in real-world videos."},"references":{"count":88,"sample":[{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736","work_id":"4710bba6-9cf4-4a0c-92c0-404f40a04621","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Introducing the next generation of Claude","work_id":"1cbb4b5a-f4fe-41dd-8d13-af2db291d5b4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Hourvideo: 1-hour video-language understanding","work_id":"8a5f3847-96f0-4e8c-aa50-0efe6ccf9dab","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Driving with llms: Fusing object-level vector modality for explainable autonomous driving","work_id":"2ee4fb29-d694-421f-9467-3ec2cf9736aa","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","work_id":"ee70bdc8-4656-4849-ada7-ce42a2278d70","ref_index":5,"cited_arxiv_id":"2412.05271","is_internal_anchor":true}],"resolved_work":88,"snapshot_sha256":"f558c84e3e56ba3ed7577460fc9ca4468d4814064c932ef23b7df9bc6bf693de","internal_anchors":33},"formal_canon":{"evidence_count":2,"snapshot_sha256":"171201a3c31ca9854d1611ed2bbf6311253676993b22fe2fbb7f8c1a8f300d3d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d0ba289f-76ac-403e-85e1-c767a36b905d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RLDQRgdAtwtsp/7Foh1drfZ2CtTzL0XwVNEAUPx3x5bQmK/1kZ+SVQVy9elG68ZtvvDYPTRpPYy8wqSXcLWiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:07:59.801371Z"},"content_sha256":"2ad3d2041a62a53282491c75c7e4c9aecd18cc60bda0cd9f43d4cd1a4a96e31e","schema_version":"1.0","event_id":"sha256:2ad3d2041a62a53282491c75c7e4c9aecd18cc60bda0cd9f43d4cd1a4a96e31e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B67AW5CHREYTXE5IWIWTEKXGAE/bundle.json","state_url":"https://pith.science/pith/B67AW5CHREYTXE5IWIWTEKXGAE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B67AW5CHREYTXE5IWIWTEKXGAE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T09:07:59Z","links":{"resolver":"https://pith.science/pith/B67AW5CHREYTXE5IWIWTEKXGAE","bundle":"https://pith.science/pith/B67AW5CHREYTXE5IWIWTEKXGAE/bundle.json","state":"https://pith.science/pith/B67AW5CHREYTXE5IWIWTEKXGAE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B67AW5CHREYTXE5IWIWTEKXGAE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B67AW5CHREYTXE5IWIWTEKXGAE","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":"e6e693f0a6a7a9ed5e057f30399701ce9984f76b3b747e47a28b490fd1a84d67","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T18:59:40Z","title_canon_sha256":"0ed6a53c364bbeb8baa039d1b28da43b1abbf6d28b95c5ed889d1e5a8e88afe4"},"schema_version":"1.0","source":{"id":"2502.04326","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04326","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04326v3","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04326","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"B67AW5CHREYT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"B67AW5CHREYTXE5I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"B67AW5CH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2ad3d2041a62a53282491c75c7e4c9aecd18cc60bda0cd9f43d4cd1a4a96e31e","target":"graph","created_at":"2026-05-17T23:38:14Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The experimental results indicate that existing models face significant challenges in understanding real-world scenarios (65.1% best accuracy)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the manually annotated QA pairs and the chosen 26 tasks accurately capture the requirements of real-world omnimodal understanding without introducing annotation bias or task selection that favors certain model architectures."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The WorldSense benchmark shows that current multimodal models reach at most 65.1 percent accuracy on tasks requiring tight audio-visual synergy in real-world videos."}],"snapshot_sha256":"50adba971c83e578b0db0f61842488817d112d8f728ff1225605f288b2be8517"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"171201a3c31ca9854d1611ed2bbf6311253676993b22fe2fbb7f8c1a8f300d3d"},"paper":{"abstract_excerpt":"We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. In contrast to existing benchmarks, our WorldSense has several features: (i)collaboration of omni-modality, we design the evaluation tasks to feature a strong coupling of audio and video, requiring models to effectively utilize the synergistic perception of omni-modality; (ii)diversity of videos and tasks, WorldSense encompasses a diverse collection of 1,662 audio-visual synchronised videos, systematically categorized into 8 primary domains","authors_text":"Jack Hong, Jiayin Cai, Shilin Yan, Weidi Xie, Xiaolong Jiang, Yao Hu","cross_cats":["cs.AI"],"headline":"The WorldSense benchmark shows that current multimodal models reach at most 65.1 percent accuracy on tasks requiring tight audio-visual synergy in real-world videos.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T18:59:40Z","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs"},"references":{"count":88,"internal_anchors":33,"resolved_work":88,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736","work_id":"4710bba6-9cf4-4a0c-92c0-404f40a04621","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Introducing the next generation of Claude","work_id":"1cbb4b5a-f4fe-41dd-8d13-af2db291d5b4","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Hourvideo: 1-hour video-language understanding","work_id":"8a5f3847-96f0-4e8c-aa50-0efe6ccf9dab","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Driving with llms: Fusing object-level vector modality for explainable autonomous driving","work_id":"2ee4fb29-d694-421f-9467-3ec2cf9736aa","year":2024},{"cited_arxiv_id":"2412.05271","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","work_id":"ee70bdc8-4656-4849-ada7-ce42a2278d70","year":2024}],"snapshot_sha256":"f558c84e3e56ba3ed7577460fc9ca4468d4814064c932ef23b7df9bc6bf693de"},"source":{"id":"2502.04326","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T05:48:39.250838Z","id":"d0ba289f-76ac-403e-85e1-c767a36b905d","model_set":{"reader":"grok-4.3"},"one_line_summary":"WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The WorldSense benchmark shows that current multimodal models reach at most 65.1 percent accuracy on tasks requiring tight audio-visual synergy in real-world videos.","strongest_claim":"The experimental results indicate that existing models face significant challenges in understanding real-world scenarios (65.1% best accuracy).","weakest_assumption":"That the manually annotated QA pairs and the chosen 26 tasks accurately capture the requirements of real-world omnimodal understanding without introducing annotation bias or task selection that favors certain model architectures."}},"verdict_id":"d0ba289f-76ac-403e-85e1-c767a36b905d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:88252017d6db17b526093dd540fd2dfd0dd5b2dd7f26baccccdee02be78d1420","target":"record","created_at":"2026-05-17T23:38:14Z","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":"e6e693f0a6a7a9ed5e057f30399701ce9984f76b3b747e47a28b490fd1a84d67","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T18:59:40Z","title_canon_sha256":"0ed6a53c364bbeb8baa039d1b28da43b1abbf6d28b95c5ed889d1e5a8e88afe4"},"schema_version":"1.0","source":{"id":"2502.04326","kind":"arxiv","version":3}},"canonical_sha256":"0fbe0b744789313b93a8b22d322ae6012ded139e34f5e623b3294fc1413289ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fbe0b744789313b93a8b22d322ae6012ded139e34f5e623b3294fc1413289ad","first_computed_at":"2026-05-17T23:38:14.896721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:14.896721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"raRYUF3r/XddOKRPPWfst3VKWDgR6n0s37BF3M3zXGo6SSt/hVWCbHo2E9shuOWvZT+Zh6ux+xa/h+U/cdkEBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:14.897310Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04326","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88252017d6db17b526093dd540fd2dfd0dd5b2dd7f26baccccdee02be78d1420","sha256:2ad3d2041a62a53282491c75c7e4c9aecd18cc60bda0cd9f43d4cd1a4a96e31e"],"state_sha256":"1d1c5176ddd68e80bbb54936e48c8c6a2befa316116e1e3ac55ffdf331aa2800"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tzOu/AlJjsm/h2Lx3FvclZyKWRtO/M7qChloU5TprGHi5srwvekryBYO02q06kwfCkub7y1BAshjo+aokQHNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:07:59.803993Z","bundle_sha256":"789b4cf57c2e05be920d3aa6f35ff665f9497f09fd9e769cd7ab55e2c4363239"}}