{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RZGMV6RCUNRUI636EWA4QTKEHT","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":"e655960b683c77f239a51ceb76f6d89a93646d3023f988c2d18df2b0c9362f51","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T15:59:52Z","title_canon_sha256":"2ac033975c653293ebdc3a6afaac879af63a32a57d9174eb5a1345510a3862fd"},"schema_version":"1.0","source":{"id":"2410.13694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13694","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13694v1","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13694","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"RZGMV6RCUNRU","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"RZGMV6RCUNRUI636","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"RZGMV6RC","created_at":"2026-07-05T09:22:04Z"}],"graph_snapshots":[{"event_id":"sha256:db865e2c0f09974ad27208b7fa9448bb5f77196da0b5261c0d6e7efce54ceed8","target":"graph","created_at":"2026-07-05T09:22:04Z","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/2410.13694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Multimodal Large Language Models (MLLMs) have shown remarkable capability of understanding the video semantics on various downstream tasks. Despite the advancements, there is still a lack of systematic research on visual context representation, which refers to the scheme to select frames from a video and further select the tokens from a frame. In this paper, we explore the design space for visual context representation, and aim to improve the performance of video MLLMs by finding more effective representation schemes. Firstly, we formulate the task of visual context representation as a c","authors_text":"Bingning Wang, Han Huang, Haoyu Lu, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao, Weipeng Chen, Yifan Du, Yuqi Huo, Zijia Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T15:59:52Z","title":"Exploring the Design Space of Visual Context Representation in Video MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13694","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:acba34ee9d09ca2ecd733e54592984f4d1532a8bd5e2b6670164cd709e85a41c","target":"record","created_at":"2026-07-05T09:22:04Z","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":"e655960b683c77f239a51ceb76f6d89a93646d3023f988c2d18df2b0c9362f51","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T15:59:52Z","title_canon_sha256":"2ac033975c653293ebdc3a6afaac879af63a32a57d9174eb5a1345510a3862fd"},"schema_version":"1.0","source":{"id":"2410.13694","kind":"arxiv","version":1}},"canonical_sha256":"8e4ccafa22a363447b7e2581c84d443ce9fcd5c8568ff10100531231273b9e3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e4ccafa22a363447b7e2581c84d443ce9fcd5c8568ff10100531231273b9e3c","first_computed_at":"2026-07-05T09:22:04.559660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:04.559660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k8c1hL6wY7bsWH/gAdU6wjjyLz1qeGrEYkLvBEQBCNBK+H1zt5iXfCKxxw6zEW/7eDqvcq4MGVfpEZw1oGKKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:04.560163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acba34ee9d09ca2ecd733e54592984f4d1532a8bd5e2b6670164cd709e85a41c","sha256:db865e2c0f09974ad27208b7fa9448bb5f77196da0b5261c0d6e7efce54ceed8"],"state_sha256":"3b19e4a049719c05bd0bf8c9efba7f05a7a6f3382ee5677f2ac30942ac689d85"}