{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LZ7G55V5BQRFPSOUSYX2JMAQQB","short_pith_number":"pith:LZ7G55V5","canonical_record":{"source":{"id":"2409.14485","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:13:31Z","cross_cats_sorted":[],"title_canon_sha256":"79f441616e1a6aaca7d86211f691fd3b19dcfd3482f36774f3642f33b9dd31ae","abstract_canon_sha256":"6ba1e3e75a4028f5ba6a9af7c9ed26c1a8990d0b1ab273c244e881c982f861c4"},"schema_version":"1.0"},"canonical_sha256":"5e7e6ef6bd0c2257c9d4962fa4b0108062854dc7c2743e24b3777311c915d0a8","source":{"kind":"arxiv","id":"2409.14485","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14485","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14485v4","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14485","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"LZ7G55V5BQRF","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"pith_short_16","alias_value":"LZ7G55V5BQRFPSOU","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"pith_short_8","alias_value":"LZ7G55V5","created_at":"2026-07-05T09:46:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LZ7G55V5BQRFPSOUSYX2JMAQQB","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14485","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:13:31Z","cross_cats_sorted":[],"title_canon_sha256":"79f441616e1a6aaca7d86211f691fd3b19dcfd3482f36774f3642f33b9dd31ae","abstract_canon_sha256":"6ba1e3e75a4028f5ba6a9af7c9ed26c1a8990d0b1ab273c244e881c982f861c4"},"schema_version":"1.0"},"canonical_sha256":"5e7e6ef6bd0c2257c9d4962fa4b0108062854dc7c2743e24b3777311c915d0a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:51.996908Z","signature_b64":"64CMhWUGxi2F0zEna/QqeCIN7b5CqtDsiHfDApRFWMoYOJS+pzBZvACDgnucnsOC0dpz8RZHf/3RTDnoA2snAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e7e6ef6bd0c2257c9d4962fa4b0108062854dc7c2743e24b3777311c915d0a8","last_reissued_at":"2026-07-05T09:46:51.996382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:51.996382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14485","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+Mh2EmiUEuiOsMYdcTkGqj4tzy8kNPWe+O06HNEIjgfiLp6VwME4rCVne5h46Ex8qeKiJ/ircQD2u+TTrPBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:04.166739Z"},"content_sha256":"b768256f41d79b4ddc10d7d656f639686ae1c7501af804da2761acab6ed25bff","schema_version":"1.0","event_id":"sha256:b768256f41d79b4ddc10d7d656f639686ae1c7501af804da2761acab6ed25bff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LZ7G55V5BQRFPSOUSYX2JMAQQB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Junjie Zhou, Minghao Qin, Peitian Zhang, Tiejun Huang, Yan Shu, Zheng Liu, Zhengyang Liang","submitted_at":"2024-09-22T15:13:31Z","abstract_excerpt":"Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos. Although several existing methods attempt to reduce visual tokens, their strategies encounter severe bottleneck, restricting MLLMs' ability to perceive fine-grained visual details. In this work, we propose Video-XL, a novel approach that leverages MLLMs' inherent key-value (KV) sparsification capacity to condense the visual input. Specifically, we introduce a new "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14485","kind":"arxiv","version":4},"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/2409.14485/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":"2026-07-05T09:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"klwKk4r6HKrhfXRFhQYvEueUbi7wjQUw7OGezVn8MIVoCcl/Z15GaVk+QiC0AmaoHq0Jp9dnoHIwRxEF+6kYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:04.167240Z"},"content_sha256":"0fe370c90e0f449e0b41f882a7ebabd122a7b85a1fa6c47317bd788eb0a1820f","schema_version":"1.0","event_id":"sha256:0fe370c90e0f449e0b41f882a7ebabd122a7b85a1fa6c47317bd788eb0a1820f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZ7G55V5BQRFPSOUSYX2JMAQQB/bundle.json","state_url":"https://pith.science/pith/LZ7G55V5BQRFPSOUSYX2JMAQQB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZ7G55V5BQRFPSOUSYX2JMAQQB/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":"2026-08-07T16:00:04Z","links":{"resolver":"https://pith.science/pith/LZ7G55V5BQRFPSOUSYX2JMAQQB","bundle":"https://pith.science/pith/LZ7G55V5BQRFPSOUSYX2JMAQQB/bundle.json","state":"https://pith.science/pith/LZ7G55V5BQRFPSOUSYX2JMAQQB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZ7G55V5BQRFPSOUSYX2JMAQQB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZ7G55V5BQRFPSOUSYX2JMAQQB","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":"6ba1e3e75a4028f5ba6a9af7c9ed26c1a8990d0b1ab273c244e881c982f861c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:13:31Z","title_canon_sha256":"79f441616e1a6aaca7d86211f691fd3b19dcfd3482f36774f3642f33b9dd31ae"},"schema_version":"1.0","source":{"id":"2409.14485","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14485","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14485v4","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14485","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"LZ7G55V5BQRF","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"pith_short_16","alias_value":"LZ7G55V5BQRFPSOU","created_at":"2026-07-05T09:46:51Z"},{"alias_kind":"pith_short_8","alias_value":"LZ7G55V5","created_at":"2026-07-05T09:46:51Z"}],"graph_snapshots":[{"event_id":"sha256:0fe370c90e0f449e0b41f882a7ebabd122a7b85a1fa6c47317bd788eb0a1820f","target":"graph","created_at":"2026-07-05T09:46:51Z","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/2409.14485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos. Although several existing methods attempt to reduce visual tokens, their strategies encounter severe bottleneck, restricting MLLMs' ability to perceive fine-grained visual details. In this work, we propose Video-XL, a novel approach that leverages MLLMs' inherent key-value (KV) sparsification capacity to condense the visual input. Specifically, we introduce a new ","authors_text":"Bo Zhao, Junjie Zhou, Minghao Qin, Peitian Zhang, Tiejun Huang, Yan Shu, Zheng Liu, Zhengyang Liang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:13:31Z","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14485","kind":"arxiv","version":4},"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:b768256f41d79b4ddc10d7d656f639686ae1c7501af804da2761acab6ed25bff","target":"record","created_at":"2026-07-05T09:46:51Z","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":"6ba1e3e75a4028f5ba6a9af7c9ed26c1a8990d0b1ab273c244e881c982f861c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T15:13:31Z","title_canon_sha256":"79f441616e1a6aaca7d86211f691fd3b19dcfd3482f36774f3642f33b9dd31ae"},"schema_version":"1.0","source":{"id":"2409.14485","kind":"arxiv","version":4}},"canonical_sha256":"5e7e6ef6bd0c2257c9d4962fa4b0108062854dc7c2743e24b3777311c915d0a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e7e6ef6bd0c2257c9d4962fa4b0108062854dc7c2743e24b3777311c915d0a8","first_computed_at":"2026-07-05T09:46:51.996382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:51.996382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"64CMhWUGxi2F0zEna/QqeCIN7b5CqtDsiHfDApRFWMoYOJS+pzBZvACDgnucnsOC0dpz8RZHf/3RTDnoA2snAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:51.996908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14485","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b768256f41d79b4ddc10d7d656f639686ae1c7501af804da2761acab6ed25bff","sha256:0fe370c90e0f449e0b41f882a7ebabd122a7b85a1fa6c47317bd788eb0a1820f"],"state_sha256":"19b4feea1684f191414235d525fb4ff67da33b52aebdeb157e8332b02e297cf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z94BYbfbJu8VyrwOlurY5eERQknDL7dmsbizlaEfv5jPF+58hCh8yoh3QO28AOhk6CJdYkXztTgGF+9exTffBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:00:04.198170Z","bundle_sha256":"cd8776ca603b7668a4c5b2712b9a8b3488645cd47336446a36d79086fb70c9d9"}}