{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HZNBXM2FFQPLV2N4B5JZF6KOTG","short_pith_number":"pith:HZNBXM2F","schema_version":"1.0","canonical_sha256":"3e5a1bb3452c1ebae9bc0f5392f94e99968b621f798cde57b3e7d0b3ea9a561a","source":{"kind":"arxiv","id":"2408.15542","version":1},"attestation_state":"computed","paper":{"title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Hanghang Ma, Jiajun Liu, Jianbin Jiao, Jie Hu, Xiaoming Wei, Xiaoping Wu, Xiaoqi Ma, Yibing Wang","submitted_at":"2024-08-28T05:34:14Z","abstract_excerpt":"Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a challenging endeavor, especially for long videos. Due to insufficient access to large-scale high-quality video data and the excessive compression of visual features, current methods exhibit limitations in effectively processing long videos. In this paper, we introduce Kangaroo, a powerful Video LMM aimed at addressing these challenges. Confronted with issue of inadequate training data, we develop a data curation system"},"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":"2408.15542","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T05:34:14Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"90891a49760333859d65dd86dcdb8a6233426456f13d50f1c30e2ace5dcd04f1","abstract_canon_sha256":"6af416d1e0ee713952d4fde1874055ca17997ec3ca7dfd5a4d528dbfc118d0c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:13.520460Z","signature_b64":"0mkeuDwrdHU3cDJuuD0w2skH0z1gt8p5gkkOYlJ8xfi+FHfPhs+Li4GddO2uwl6UOzXR8TQEtNQLyDkUjmHiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e5a1bb3452c1ebae9bc0f5392f94e99968b621f798cde57b3e7d0b3ea9a561a","last_reissued_at":"2026-07-05T09:00:13.519951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:13.519951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Hanghang Ma, Jiajun Liu, Jianbin Jiao, Jie Hu, Xiaoming Wei, Xiaoping Wu, Xiaoqi Ma, Yibing Wang","submitted_at":"2024-08-28T05:34:14Z","abstract_excerpt":"Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a challenging endeavor, especially for long videos. Due to insufficient access to large-scale high-quality video data and the excessive compression of visual features, current methods exhibit limitations in effectively processing long videos. In this paper, we introduce Kangaroo, a powerful Video LMM aimed at addressing these challenges. Confronted with issue of inadequate training data, we develop a data curation system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15542","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/2408.15542/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":"2408.15542","created_at":"2026-07-05T09:00:13.520012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15542v1","created_at":"2026-07-05T09:00:13.520012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15542","created_at":"2026-07-05T09:00:13.520012+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZNBXM2FFQPL","created_at":"2026-07-05T09:00:13.520012+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZNBXM2FFQPLV2N4","created_at":"2026-07-05T09:00:13.520012+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZNBXM2F","created_at":"2026-07-05T09:00:13.520012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19341","citing_title":"Native Active Perception as Reasoning for Omni-Modal Understanding","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18441","citing_title":"Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":296,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25621","citing_title":"StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2501.02955","citing_title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17921","citing_title":"An Efficient Streaming Video Understanding Framework with Agentic Control","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08035","citing_title":"LVBench: An Extreme Long Video Understanding Benchmark","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00574","citing_title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01707","citing_title":"StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14724","citing_title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2504.05299","citing_title":"SmolVLM: Redefining small and efficient multimodal models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21776","citing_title":"Video-R1: Reinforcing Video Reasoning in MLLMs","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07575","citing_title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01844","citing_title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00444","citing_title":"Scaling Video Understanding via Compact Latent Multi-Agent Collaboration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07575","citing_title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08120","citing_title":"Small Vision-Language Models are Smart Compressors for Long Video Understanding","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14149","citing_title":"One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17052","citing_title":"OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG","json":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG.json","graph_json":"https://pith.science/api/pith-number/HZNBXM2FFQPLV2N4B5JZF6KOTG/graph.json","events_json":"https://pith.science/api/pith-number/HZNBXM2FFQPLV2N4B5JZF6KOTG/events.json","paper":"https://pith.science/paper/HZNBXM2F"},"agent_actions":{"view_html":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG","download_json":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG.json","view_paper":"https://pith.science/paper/HZNBXM2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15542&json=true","fetch_graph":"https://pith.science/api/pith-number/HZNBXM2FFQPLV2N4B5JZF6KOTG/graph.json","fetch_events":"https://pith.science/api/pith-number/HZNBXM2FFQPLV2N4B5JZF6KOTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG/action/storage_attestation","attest_author":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG/action/author_attestation","sign_citation":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG/action/citation_signature","submit_replication":"https://pith.science/pith/HZNBXM2FFQPLV2N4B5JZF6KOTG/action/replication_record"}},"created_at":"2026-07-05T09:00:13.520012+00:00","updated_at":"2026-07-05T09:00:13.520012+00:00"}