{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HZNBXM2FFQPLV2N4B5JZF6KOTG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6af416d1e0ee713952d4fde1874055ca17997ec3ca7dfd5a4d528dbfc118d0c5","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T05:34:14Z","title_canon_sha256":"90891a49760333859d65dd86dcdb8a6233426456f13d50f1c30e2ace5dcd04f1"},"schema_version":"1.0","source":{"id":"2408.15542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15542","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15542v1","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15542","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"HZNBXM2FFQPL","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"pith_short_16","alias_value":"HZNBXM2FFQPLV2N4","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"pith_short_8","alias_value":"HZNBXM2F","created_at":"2026-07-05T09:00:13Z"}],"graph_snapshots":[{"event_id":"sha256:7bc2000844e4cd16fde31413316700a52f55bac1a68d60b7990064281da02b42","target":"graph","created_at":"2026-07-05T09:00:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.15542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Enhua Wu, Hanghang Ma, Jiajun Liu, Jianbin Jiao, Jie Hu, Xiaoming Wei, Xiaoping Wu, Xiaoqi Ma, Yibing Wang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T05:34:14Z","title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15542","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f06de968bc602fea76b76a6ed8979fc85181065719b0bed89f55ca22dd89f409","target":"record","created_at":"2026-07-05T09:00:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6af416d1e0ee713952d4fde1874055ca17997ec3ca7dfd5a4d528dbfc118d0c5","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T05:34:14Z","title_canon_sha256":"90891a49760333859d65dd86dcdb8a6233426456f13d50f1c30e2ace5dcd04f1"},"schema_version":"1.0","source":{"id":"2408.15542","kind":"arxiv","version":1}},"canonical_sha256":"3e5a1bb3452c1ebae9bc0f5392f94e99968b621f798cde57b3e7d0b3ea9a561a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e5a1bb3452c1ebae9bc0f5392f94e99968b621f798cde57b3e7d0b3ea9a561a","first_computed_at":"2026-07-05T09:00:13.519951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:13.519951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0mkeuDwrdHU3cDJuuD0w2skH0z1gt8p5gkkOYlJ8xfi+FHfPhs+Li4GddO2uwl6UOzXR8TQEtNQLyDkUjmHiAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:13.520460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f06de968bc602fea76b76a6ed8979fc85181065719b0bed89f55ca22dd89f409","sha256:7bc2000844e4cd16fde31413316700a52f55bac1a68d60b7990064281da02b42"],"state_sha256":"2384f3a730eb97d72d071ac7f815afbb523fda2f3f21fea63d91ef4476cfce0a"}