{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5TV6C3K4GOQOFBA2LC7YDOTTQW","short_pith_number":"pith:5TV6C3K4","schema_version":"1.0","canonical_sha256":"ecebe16d5c33a0e2841a58bf81ba73859c5ae144023e4565ef459d678a120e18","source":{"kind":"arxiv","id":"2509.25773","version":3},"attestation_state":"computed","paper":{"title":"v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Jianqun Zhou, Qinrong Cui, Songchun Zhu, Wei Bi, Yanpeng Zhao, Yuxuan Wang, Zhengpeng Shi, Zilong Zheng","submitted_at":"2025-09-30T04:33:52Z","abstract_excerpt":"AI models capable of comprehending humor hold real-world promise -- for example, enhancing engagement in human-machine interactions. To gauge and diagnose the capacity of multimodal large language models (MLLMs) for humor understanding, we introduce v-HUB, a novel video humor understanding benchmark. v-HUB comprises a curated collection of non-verbal short videos, reflecting real-world scenarios where humor can be appreciated purely through visual cues. We pair each video clip with rich annotations to support a variety of evaluation tasks and analyses, including a novel study of environmental "},"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":"2509.25773","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-30T04:33:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"32c052523aad2b97fe8ce56c062e04549b4eb56899d7b5fa5eff792cc1c68d71","abstract_canon_sha256":"0a51a1ff4e5be6608cd647e350485367095adab3e9ab9337d75a0d5b701ce737"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:48.044913Z","signature_b64":"xbzQl9iSb1qN/sezAvb08LAAoRh8GmrHRRNIXrt4/QrMps4gdv6/nv2FGsSHf9q7U7WuA2f9P7nvHRwrgeczDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecebe16d5c33a0e2841a58bf81ba73859c5ae144023e4565ef459d678a120e18","last_reissued_at":"2026-06-02T02:04:48.044419Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:48.044419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Jianqun Zhou, Qinrong Cui, Songchun Zhu, Wei Bi, Yanpeng Zhao, Yuxuan Wang, Zhengpeng Shi, Zilong Zheng","submitted_at":"2025-09-30T04:33:52Z","abstract_excerpt":"AI models capable of comprehending humor hold real-world promise -- for example, enhancing engagement in human-machine interactions. To gauge and diagnose the capacity of multimodal large language models (MLLMs) for humor understanding, we introduce v-HUB, a novel video humor understanding benchmark. v-HUB comprises a curated collection of non-verbal short videos, reflecting real-world scenarios where humor can be appreciated purely through visual cues. We pair each video clip with rich annotations to support a variety of evaluation tasks and analyses, including a novel study of environmental "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.25773","kind":"arxiv","version":3},"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/2509.25773/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":"2509.25773","created_at":"2026-06-02T02:04:48.044486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.25773v3","created_at":"2026-06-02T02:04:48.044486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.25773","created_at":"2026-06-02T02:04:48.044486+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TV6C3K4GOQO","created_at":"2026-06-02T02:04:48.044486+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TV6C3K4GOQOFBA2","created_at":"2026-06-02T02:04:48.044486+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TV6C3K4","created_at":"2026-06-02T02:04:48.044486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14607","citing_title":"ViMU: Benchmarking Video Metaphorical Understanding","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW","json":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW.json","graph_json":"https://pith.science/api/pith-number/5TV6C3K4GOQOFBA2LC7YDOTTQW/graph.json","events_json":"https://pith.science/api/pith-number/5TV6C3K4GOQOFBA2LC7YDOTTQW/events.json","paper":"https://pith.science/paper/5TV6C3K4"},"agent_actions":{"view_html":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW","download_json":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW.json","view_paper":"https://pith.science/paper/5TV6C3K4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.25773&json=true","fetch_graph":"https://pith.science/api/pith-number/5TV6C3K4GOQOFBA2LC7YDOTTQW/graph.json","fetch_events":"https://pith.science/api/pith-number/5TV6C3K4GOQOFBA2LC7YDOTTQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW/action/storage_attestation","attest_author":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW/action/author_attestation","sign_citation":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW/action/citation_signature","submit_replication":"https://pith.science/pith/5TV6C3K4GOQOFBA2LC7YDOTTQW/action/replication_record"}},"created_at":"2026-06-02T02:04:48.044486+00:00","updated_at":"2026-06-02T02:04:48.044486+00:00"}