{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NP77ZS2JJQBZKO2BOJYIN7V5DI","short_pith_number":"pith:NP77ZS2J","schema_version":"1.0","canonical_sha256":"6bfffccb494c03953b41727086febd1a3ac8ef0082827b7dc85f56ad3652439c","source":{"kind":"arxiv","id":"2407.15754","version":1},"attestation_state":"computed","paper":{"title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bei Chen, Dongxu Li, Haoning Wu, Junnan Li","submitted_at":"2024-07-22T16:00:55Z","abstract_excerpt":"Large multimodal models (LMMs) are processing increasingly longer and richer inputs. Albeit the progress, few public benchmark is available to measure such development. To mitigate this gap, we introduce LongVideoBench, a question-answering benchmark that features video-language interleaved inputs up to an hour long. Our benchmark includes 3,763 varying-length web-collected videos with their subtitles across diverse themes, designed to comprehensively evaluate LMMs on long-term multimodal understanding. To achieve this, we interpret the primary challenge as to accurately retrieve and reason ov"},"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":"2407.15754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T16:00:55Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"82b4f6728f998f3fbdf6923ee11f8786526e2cf91ebd2d8bb99f6ff4c61db186","abstract_canon_sha256":"778f5236ea363d3854726a11fbfc41023cc8ec1e079ded4f8d1d965f56f3d182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:50.148085Z","signature_b64":"EJx3QI0jtLHQxj+cETR+5rTH3JgYCQhKI95tDe6mHNFzKYzwRMnGgaJPgXfJe9Jz3FfV1BCbw3rAzW02306wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bfffccb494c03953b41727086febd1a3ac8ef0082827b7dc85f56ad3652439c","last_reissued_at":"2026-05-18T00:24:50.147406Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:50.147406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bei Chen, Dongxu Li, Haoning Wu, Junnan Li","submitted_at":"2024-07-22T16:00:55Z","abstract_excerpt":"Large multimodal models (LMMs) are processing increasingly longer and richer inputs. Albeit the progress, few public benchmark is available to measure such development. To mitigate this gap, we introduce LongVideoBench, a question-answering benchmark that features video-language interleaved inputs up to an hour long. Our benchmark includes 3,763 varying-length web-collected videos with their subtitles across diverse themes, designed to comprehensively evaluate LMMs on long-term multimodal understanding. To achieve this, we interpret the primary challenge as to accurately retrieve and reason ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15754","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":""},"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":"2407.15754","created_at":"2026-05-18T00:24:50.147493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15754v1","created_at":"2026-05-18T00:24:50.147493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15754","created_at":"2026-05-18T00:24:50.147493+00:00"},{"alias_kind":"pith_short_12","alias_value":"NP77ZS2JJQBZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NP77ZS2JJQBZKO2B","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NP77ZS2J","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2501.02955","citing_title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2502.13923","citing_title":"Qwen2.5-VL Technical Report","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15269","citing_title":"LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17921","citing_title":"An Efficient Streaming Video Understanding Framework with Agentic Control","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":253,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19559","citing_title":"EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2406.08035","citing_title":"LVBench: An Extreme Long Video Understanding Benchmark","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00574","citing_title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2408.10188","citing_title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2501.12386","citing_title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2512.08410","citing_title":"Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22911","citing_title":"ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2406.04264","citing_title":"MLVU: Benchmarking Multi-task Long Video Understanding","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2501.13826","citing_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07355","citing_title":"TTF: Temporal Token Fusion for Efficient Video-Language Model","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05225","citing_title":"MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2410.02713","citing_title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08703","citing_title":"QoS-QoE Translation with Large Language Model","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10060","citing_title":"Mosaic: Cross-Modal Clustering for Efficient Video Understanding","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2602.02276","citing_title":"Kimi K2.5: Visual Agentic Intelligence","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":130,"is_internal_anchor":true},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":263,"is_internal_anchor":true},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":150,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16893","citing_title":"EasyVideoR1: Easier RL for Video Understanding","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05225","citing_title":"MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI","json":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI.json","graph_json":"https://pith.science/api/pith-number/NP77ZS2JJQBZKO2BOJYIN7V5DI/graph.json","events_json":"https://pith.science/api/pith-number/NP77ZS2JJQBZKO2BOJYIN7V5DI/events.json","paper":"https://pith.science/paper/NP77ZS2J"},"agent_actions":{"view_html":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI","download_json":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI.json","view_paper":"https://pith.science/paper/NP77ZS2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15754&json=true","fetch_graph":"https://pith.science/api/pith-number/NP77ZS2JJQBZKO2BOJYIN7V5DI/graph.json","fetch_events":"https://pith.science/api/pith-number/NP77ZS2JJQBZKO2BOJYIN7V5DI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI/action/storage_attestation","attest_author":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI/action/author_attestation","sign_citation":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI/action/citation_signature","submit_replication":"https://pith.science/pith/NP77ZS2JJQBZKO2BOJYIN7V5DI/action/replication_record"}},"created_at":"2026-05-18T00:24:50.147493+00:00","updated_at":"2026-05-18T00:24:50.147493+00:00"}