{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TYCFIVET47UNVHONDOAMJ4APVJ","short_pith_number":"pith:TYCFIVET","schema_version":"1.0","canonical_sha256":"9e04545493e7e8da9dcd1b80c4f00faa607d10ed1ff4f8a130f91416d6bce36c","source":{"kind":"arxiv","id":"2506.01689","version":1},"attestation_state":"computed","paper":{"title":"Respond Beyond Language: A Benchmark for Video Generation in Response to Realistic User Intents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chenyan Xiong, Ning Hu, Shuting Wang, Yunqi Liu, Zhicheng Dou, Zixin Yang","submitted_at":"2025-06-02T13:52:21Z","abstract_excerpt":"Querying generative AI models, e.g., large language models (LLMs), has become a prevalent method for information acquisition. However, existing query-answer datasets primarily focus on textual responses, making it challenging to address complex user queries that require visual demonstrations or explanations for better understanding. To bridge this gap, we construct a benchmark, RealVideoQuest, designed to evaluate the abilities of text-to-video (T2V) models in answering real-world, visually grounded queries. It identifies 7.5K real user queries with video response intents from Chatbot-Arena an"},"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":"2506.01689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T13:52:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"049d4f120e2534ed6b77510aa7b943375a40e702557b9cf1d564142457047d6e","abstract_canon_sha256":"9d2d31360f282354abd2353599d93750fb905bb84b36ac4fa26cf16a865b1159"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:17.920779Z","signature_b64":"fgE5HwwYbU1+WPT+KSFqpEnkvhEx8Qij6KSV+gxoxWcby8x6bRFRXKu6ieabvlAXoKHECPOLtCyamS/L8UmhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e04545493e7e8da9dcd1b80c4f00faa607d10ed1ff4f8a130f91416d6bce36c","last_reissued_at":"2026-07-05T11:14:17.920279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:17.920279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Respond Beyond Language: A Benchmark for Video Generation in Response to Realistic User Intents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chenyan Xiong, Ning Hu, Shuting Wang, Yunqi Liu, Zhicheng Dou, Zixin Yang","submitted_at":"2025-06-02T13:52:21Z","abstract_excerpt":"Querying generative AI models, e.g., large language models (LLMs), has become a prevalent method for information acquisition. However, existing query-answer datasets primarily focus on textual responses, making it challenging to address complex user queries that require visual demonstrations or explanations for better understanding. To bridge this gap, we construct a benchmark, RealVideoQuest, designed to evaluate the abilities of text-to-video (T2V) models in answering real-world, visually grounded queries. It identifies 7.5K real user queries with video response intents from Chatbot-Arena an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01689","kind":"arxiv","version":1},"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/2506.01689/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":"2506.01689","created_at":"2026-07-05T11:14:17.920349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01689v1","created_at":"2026-07-05T11:14:17.920349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01689","created_at":"2026-07-05T11:14:17.920349+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYCFIVET47UN","created_at":"2026-07-05T11:14:17.920349+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYCFIVET47UNVHON","created_at":"2026-07-05T11:14:17.920349+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYCFIVET","created_at":"2026-07-05T11:14:17.920349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18107","citing_title":"T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ","json":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ.json","graph_json":"https://pith.science/api/pith-number/TYCFIVET47UNVHONDOAMJ4APVJ/graph.json","events_json":"https://pith.science/api/pith-number/TYCFIVET47UNVHONDOAMJ4APVJ/events.json","paper":"https://pith.science/paper/TYCFIVET"},"agent_actions":{"view_html":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ","download_json":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ.json","view_paper":"https://pith.science/paper/TYCFIVET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01689&json=true","fetch_graph":"https://pith.science/api/pith-number/TYCFIVET47UNVHONDOAMJ4APVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TYCFIVET47UNVHONDOAMJ4APVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ/action/storage_attestation","attest_author":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ/action/author_attestation","sign_citation":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ/action/citation_signature","submit_replication":"https://pith.science/pith/TYCFIVET47UNVHONDOAMJ4APVJ/action/replication_record"}},"created_at":"2026-07-05T11:14:17.920349+00:00","updated_at":"2026-07-05T11:14:17.920349+00:00"}