{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OO3PRYZ4ANCE77YWHFNXT3JC6U","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":"8847bb6fbb79749909bcc4454a398a9073bb15bf2dfd51ec68fe976d6270624c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T17:47:52Z","title_canon_sha256":"4c3164b4957ea558f9f7920a98ded82c6aa5a0a07fb015fb3df54608fc11a90e"},"schema_version":"1.0","source":{"id":"2503.10742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10742","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10742v2","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10742","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"OO3PRYZ4ANCE","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"OO3PRYZ4ANCE77YW","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"OO3PRYZ4","created_at":"2026-07-05T10:53:16Z"}],"graph_snapshots":[{"event_id":"sha256:5120e61ebd990bab6b370ab1857c201cf41a5161b6889e13223e53f49cb00016","target":"graph","created_at":"2026-07-05T10:53:16Z","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/2503.10742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to redundant visual information, particularly in long-form video scenarios. Existing approaches predominantly focus on either vision token pruning, which may overlook spatio-temporal dependencies, or keyframe selection, which identifies informative frames but discards others, thus disrupting contextual continuity. In this work, we propose KVTP (Keyframe-oriented Vision Token Pruning), a novel framework that overcomes the d","authors_text":"Hai Li, Jianyi Zhang, Jingwei Sun, Jingyang Zhang, Ming Yin, Qinsi Wang, Yiran Chen, Yudong Liu, Yueqian Lin","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T17:47:52Z","title":"Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10742","kind":"arxiv","version":2},"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":"sha256:7499cbf856192817dcc2197ab3cc5e588cb5d2ae6f6682a3a7dffe5576dffc24","target":"record","created_at":"2026-07-05T10:53:16Z","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":"8847bb6fbb79749909bcc4454a398a9073bb15bf2dfd51ec68fe976d6270624c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T17:47:52Z","title_canon_sha256":"4c3164b4957ea558f9f7920a98ded82c6aa5a0a07fb015fb3df54608fc11a90e"},"schema_version":"1.0","source":{"id":"2503.10742","kind":"arxiv","version":2}},"canonical_sha256":"73b6f8e33c03444fff16395b79ed22f5370e5d35983dadde58f5fec87e28a3fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73b6f8e33c03444fff16395b79ed22f5370e5d35983dadde58f5fec87e28a3fc","first_computed_at":"2026-07-05T10:53:16.410847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:16.410847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lx+QH9U5PbX6sWCEqjaWdJd3Pgbd/P0DJDvNHS67zvoKUZ+yDkjoHzIcW3fIz99jrWab8FP4CRVh9js8jOVtBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:16.411355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7499cbf856192817dcc2197ab3cc5e588cb5d2ae6f6682a3a7dffe5576dffc24","sha256:5120e61ebd990bab6b370ab1857c201cf41a5161b6889e13223e53f49cb00016"],"state_sha256":"ce9c50629588a6a8195a9616183b8a09ed9196bf29538e82806560503f5220bd"}