{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UXFXZH2DU5QVLZ4AEWRRDPVGLS","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":"629c10222f7057a5c4bbf7695f0a9a0878937ba4038c592fa98d66030d5d36de","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T17:46:29Z","title_canon_sha256":"94e3e54a97fd884676bb0432345322bc994305fb7a0ff2cd2bb6cb1825f32e74"},"schema_version":"1.0","source":{"id":"2502.21271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.21271","created_at":"2026-07-05T10:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.21271v1","created_at":"2026-07-05T10:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.21271","created_at":"2026-07-05T10:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"UXFXZH2DU5QV","created_at":"2026-07-05T10:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"UXFXZH2DU5QVLZ4A","created_at":"2026-07-05T10:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"UXFXZH2D","created_at":"2026-07-05T10:21:47Z"}],"graph_snapshots":[{"event_id":"sha256:a930b9cc5a3c74056a956726772881bfc3ce8122a048651451c11baa3547428e","target":"graph","created_at":"2026-07-05T10:21:47Z","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/2502.21271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when the visual input changes from a single image to a long video, the above paradigm encounters difficulty because the vast amount of video tokens has significantly exceeded the maximal capacity of MLLMs. Therefore, existing video-based MLLMs are mostly established upon sampling a small portion of tokens from input data, which can cause key information to be lost and thus produce incorrect answers. This paper pr","authors_text":"Jianbin Jiao, Jihao Qiu, Lingxi Xie, Qixiang Ye, Xi Tang, Yunjie Tian","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T17:46:29Z","title":"Adaptive Keyframe Sampling for Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.21271","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":"sha256:5aa9ca92c8eb90d4d78d9bc05b9d8a93a8e8fb5db3ce41bb7cd6ebb6884e89f6","target":"record","created_at":"2026-07-05T10:21:47Z","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":"629c10222f7057a5c4bbf7695f0a9a0878937ba4038c592fa98d66030d5d36de","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T17:46:29Z","title_canon_sha256":"94e3e54a97fd884676bb0432345322bc994305fb7a0ff2cd2bb6cb1825f32e74"},"schema_version":"1.0","source":{"id":"2502.21271","kind":"arxiv","version":1}},"canonical_sha256":"a5cb7c9f43a76155e78025a311bea65cbb05285501c8a6ca3eacf9a8ab3056f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5cb7c9f43a76155e78025a311bea65cbb05285501c8a6ca3eacf9a8ab3056f5","first_computed_at":"2026-07-05T10:21:47.405221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:47.405221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HJ3jYsegr/q9iSXy3bfaBEezh7pO3b2Hr+QSsmYqe0j8zqxTA57q9Ep0aOESvZhkUbC/TTXQs0YrN2JTgagkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:47.405741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.21271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aa9ca92c8eb90d4d78d9bc05b9d8a93a8e8fb5db3ce41bb7cd6ebb6884e89f6","sha256:a930b9cc5a3c74056a956726772881bfc3ce8122a048651451c11baa3547428e"],"state_sha256":"0bc7d74bff0f55ac2c8e2a6f78e58481867682a9f241f4f6ba3822f4ad4630e9"}