{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7NR5HXTOASH3QG7SH6GNJ6PNCZ","short_pith_number":"pith:7NR5HXTO","canonical_record":{"source":{"id":"2506.19225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T01:19:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7af28e868da5e279922bc7f5a733bb4ff13c4d40c7f76c3187434f83aa2f14f2","abstract_canon_sha256":"dba06b9e24ac8aeba39e4961242fd4e9ca3deb65976f0643849e223a7ec85920"},"schema_version":"1.0"},"canonical_sha256":"fb63d3de6e048fb81bf23f8cd4f9ed16595e386aa68623c260a4f872e29df273","source":{"kind":"arxiv","id":"2506.19225","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19225","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19225v1","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19225","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"pith_short_12","alias_value":"7NR5HXTOASH3","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"pith_short_16","alias_value":"7NR5HXTOASH3QG7S","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"pith_short_8","alias_value":"7NR5HXTO","created_at":"2026-07-05T11:26:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7NR5HXTOASH3QG7SH6GNJ6PNCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.19225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T01:19:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7af28e868da5e279922bc7f5a733bb4ff13c4d40c7f76c3187434f83aa2f14f2","abstract_canon_sha256":"dba06b9e24ac8aeba39e4961242fd4e9ca3deb65976f0643849e223a7ec85920"},"schema_version":"1.0"},"canonical_sha256":"fb63d3de6e048fb81bf23f8cd4f9ed16595e386aa68623c260a4f872e29df273","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:11.672701Z","signature_b64":"OtTAQT8CcR1OaJH0W0HDg6R8bB/Wb3IERiQZXlY4LShAwlX5Q7sPyGb2Aiz3qe45SurMPn5V7Qcr/0KhPDWADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb63d3de6e048fb81bf23f8cd4f9ed16595e386aa68623c260a4f872e29df273","last_reissued_at":"2026-07-05T11:26:11.672135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:11.672135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.19225","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:26:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R26SYas7zC0EYa9A5Xt48XMWUWclDkR1VKx+vHZhti/39iCda9Wh/2Di4/LQLT39bjzW71lhvsOHNbmauZDvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:47:55.845956Z"},"content_sha256":"99371d43539eb6ac58a886028142e25e01844361cf3bf64ecc9c4d43c07b1a9e","schema_version":"1.0","event_id":"sha256:99371d43539eb6ac58a886028142e25e01844361cf3bf64ecc9c4d43c07b1a9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7NR5HXTOASH3QG7SH6GNJ6PNCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Huaying Yuan, Juenjie Zhou, Minghao Qin, Shitao Xiao, Xiangrui Liu, Yan Shu, Zheng Liu, Zhengyang Liang","submitted_at":"2025-06-24T01:19:56Z","abstract_excerpt":"Multi-modal large language models (MLLMs) models have made significant progress in video understanding over the past few years. However, processing long video inputs remains a major challenge due to high memory and computational costs. This makes it difficult for current models to achieve both strong performance and high efficiency in long video understanding. To address this challenge, we propose Video-XL-2, a novel MLLM that delivers superior cost-effectiveness for long-video understanding based on task-aware KV sparsification. The proposed framework operates with two key steps: chunk-based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19225","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/2506.19225/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:26:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lq91Ja2Y7t1fa/QHcw40qo9Gn9xTiR4UaqpET94UirppKiiITgmyuKt3BCHtbiutmYSlG4kX4JkeyKWSfoKADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:47:55.846479Z"},"content_sha256":"373c0ad3efad365a2ff778ad6b9204edfbd83d10f8993ced76feef8535de1044","schema_version":"1.0","event_id":"sha256:373c0ad3efad365a2ff778ad6b9204edfbd83d10f8993ced76feef8535de1044"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NR5HXTOASH3QG7SH6GNJ6PNCZ/bundle.json","state_url":"https://pith.science/pith/7NR5HXTOASH3QG7SH6GNJ6PNCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NR5HXTOASH3QG7SH6GNJ6PNCZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T15:47:55Z","links":{"resolver":"https://pith.science/pith/7NR5HXTOASH3QG7SH6GNJ6PNCZ","bundle":"https://pith.science/pith/7NR5HXTOASH3QG7SH6GNJ6PNCZ/bundle.json","state":"https://pith.science/pith/7NR5HXTOASH3QG7SH6GNJ6PNCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NR5HXTOASH3QG7SH6GNJ6PNCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7NR5HXTOASH3QG7SH6GNJ6PNCZ","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":"dba06b9e24ac8aeba39e4961242fd4e9ca3deb65976f0643849e223a7ec85920","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T01:19:56Z","title_canon_sha256":"7af28e868da5e279922bc7f5a733bb4ff13c4d40c7f76c3187434f83aa2f14f2"},"schema_version":"1.0","source":{"id":"2506.19225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19225","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19225v1","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19225","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"pith_short_12","alias_value":"7NR5HXTOASH3","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"pith_short_16","alias_value":"7NR5HXTOASH3QG7S","created_at":"2026-07-05T11:26:11Z"},{"alias_kind":"pith_short_8","alias_value":"7NR5HXTO","created_at":"2026-07-05T11:26:11Z"}],"graph_snapshots":[{"event_id":"sha256:373c0ad3efad365a2ff778ad6b9204edfbd83d10f8993ced76feef8535de1044","target":"graph","created_at":"2026-07-05T11:26:11Z","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/2506.19225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) models have made significant progress in video understanding over the past few years. However, processing long video inputs remains a major challenge due to high memory and computational costs. This makes it difficult for current models to achieve both strong performance and high efficiency in long video understanding. To address this challenge, we propose Video-XL-2, a novel MLLM that delivers superior cost-effectiveness for long-video understanding based on task-aware KV sparsification. The proposed framework operates with two key steps: chunk-based ","authors_text":"Bo Zhao, Huaying Yuan, Juenjie Zhou, Minghao Qin, Shitao Xiao, Xiangrui Liu, Yan Shu, Zheng Liu, Zhengyang Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T01:19:56Z","title":"Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19225","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":"sha256:99371d43539eb6ac58a886028142e25e01844361cf3bf64ecc9c4d43c07b1a9e","target":"record","created_at":"2026-07-05T11:26:11Z","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":"dba06b9e24ac8aeba39e4961242fd4e9ca3deb65976f0643849e223a7ec85920","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T01:19:56Z","title_canon_sha256":"7af28e868da5e279922bc7f5a733bb4ff13c4d40c7f76c3187434f83aa2f14f2"},"schema_version":"1.0","source":{"id":"2506.19225","kind":"arxiv","version":1}},"canonical_sha256":"fb63d3de6e048fb81bf23f8cd4f9ed16595e386aa68623c260a4f872e29df273","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb63d3de6e048fb81bf23f8cd4f9ed16595e386aa68623c260a4f872e29df273","first_computed_at":"2026-07-05T11:26:11.672135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:11.672135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OtTAQT8CcR1OaJH0W0HDg6R8bB/Wb3IERiQZXlY4LShAwlX5Q7sPyGb2Aiz3qe45SurMPn5V7Qcr/0KhPDWADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:11.672701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99371d43539eb6ac58a886028142e25e01844361cf3bf64ecc9c4d43c07b1a9e","sha256:373c0ad3efad365a2ff778ad6b9204edfbd83d10f8993ced76feef8535de1044"],"state_sha256":"579d3bf6153cf8908a315766860d97b0c480933ba819d177aef108231a8bba6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RVHeeMPKxVJ2XhnoX2+/edDxdurwaGqtlTdOmqtDlJCQEXFvTKZ09U2v2e6+0OMcOKqTz4I/ZaB0r5ZJyLBjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:47:55.862270Z","bundle_sha256":"2d710b39d7f37a883215841a3703bd0d3f1b13344934f1468df728d58066071f"}}