{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DYWJ4JCRJTETEBQF372YAET24R","short_pith_number":"pith:DYWJ4JCR","schema_version":"1.0","canonical_sha256":"1e2c9e24514cc9320605dff580127ae458f3cab690dcc8beb4d959f07de68dc8","source":{"kind":"arxiv","id":"2306.14899","version":2},"attestation_state":"computed","paper":{"title":"FunQA: Towards Surprising Video Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Binzhu Xie, Bo Li, Jack Hessel, Jingkang Yang, Sicheng Zhang, Yuanhan Zhang, Zitang Zhou, Ziwei Liu","submitted_at":"2023-06-26T17:59:55Z","abstract_excerpt":"Surprising videos, such as funny clips, creative performances, or visual illusions, attract significant attention. Enjoyment of these videos is not simply a response to visual stimuli; rather, it hinges on the human capacity to understand (and appreciate) commonsense violations depicted in these videos. We introduce FunQA, a challenging video question-answering (QA) dataset specifically designed to evaluate and enhance the depth of video reasoning based on counter-intuitive and fun videos. Unlike most video QA benchmarks which focus on less surprising contexts, e.g., cooking or instructional v"},"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":"2306.14899","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-26T17:59:55Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"d6e2d4c8f97e532d1c6ad015376137d3716a2cd0c6db433e0ec8c01148b734b3","abstract_canon_sha256":"e43a6560383d71cb6723c96d3fc1268c87a0aaed80fa7df1d4788e33832bdcb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:15.894837Z","signature_b64":"feYUjWhObJz1hAAokz3zsSHRF6rdtbOm5/7c0f0BlrmdPscOYzlNjASGUUn39rSc+3SR3jULzK/7mwwFWGjrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e2c9e24514cc9320605dff580127ae458f3cab690dcc8beb4d959f07de68dc8","last_reissued_at":"2026-07-05T07:59:15.894338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:15.894338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FunQA: Towards Surprising Video Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Binzhu Xie, Bo Li, Jack Hessel, Jingkang Yang, Sicheng Zhang, Yuanhan Zhang, Zitang Zhou, Ziwei Liu","submitted_at":"2023-06-26T17:59:55Z","abstract_excerpt":"Surprising videos, such as funny clips, creative performances, or visual illusions, attract significant attention. Enjoyment of these videos is not simply a response to visual stimuli; rather, it hinges on the human capacity to understand (and appreciate) commonsense violations depicted in these videos. We introduce FunQA, a challenging video question-answering (QA) dataset specifically designed to evaluate and enhance the depth of video reasoning based on counter-intuitive and fun videos. Unlike most video QA benchmarks which focus on less surprising contexts, e.g., cooking or instructional v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14899","kind":"arxiv","version":2},"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/2306.14899/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":"2306.14899","created_at":"2026-07-05T07:59:15.894399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14899v2","created_at":"2026-07-05T07:59:15.894399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14899","created_at":"2026-07-05T07:59:15.894399+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYWJ4JCRJTET","created_at":"2026-07-05T07:59:15.894399+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYWJ4JCRJTETEBQF","created_at":"2026-07-05T07:59:15.894399+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYWJ4JCR","created_at":"2026-07-05T07:59:15.894399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2311.17005","citing_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2305.03726","citing_title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04264","citing_title":"MLVU: Benchmarking Multi-task Long Video Understanding","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R","json":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R.json","graph_json":"https://pith.science/api/pith-number/DYWJ4JCRJTETEBQF372YAET24R/graph.json","events_json":"https://pith.science/api/pith-number/DYWJ4JCRJTETEBQF372YAET24R/events.json","paper":"https://pith.science/paper/DYWJ4JCR"},"agent_actions":{"view_html":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R","download_json":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R.json","view_paper":"https://pith.science/paper/DYWJ4JCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14899&json=true","fetch_graph":"https://pith.science/api/pith-number/DYWJ4JCRJTETEBQF372YAET24R/graph.json","fetch_events":"https://pith.science/api/pith-number/DYWJ4JCRJTETEBQF372YAET24R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R/action/storage_attestation","attest_author":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R/action/author_attestation","sign_citation":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R/action/citation_signature","submit_replication":"https://pith.science/pith/DYWJ4JCRJTETEBQF372YAET24R/action/replication_record"}},"created_at":"2026-07-05T07:59:15.894399+00:00","updated_at":"2026-07-05T07:59:15.894399+00:00"}