{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DIQG5CLEMSLR3ZUW6HK3CND5S7","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":"8d8e17727a8fee5ecd5baeebaa5d16c339f55ef9be8b7a136736051cd63f049d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-06T02:50:30Z","title_canon_sha256":"f5c7fa5c9bbdcd9191864ffc46532cd44960d2c531b45cd310138d8c568718cc"},"schema_version":"1.0","source":{"id":"2411.03628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03628","created_at":"2026-07-05T09:31:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03628v1","created_at":"2026-07-05T09:31:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03628","created_at":"2026-07-05T09:31:53Z"},{"alias_kind":"pith_short_12","alias_value":"DIQG5CLEMSLR","created_at":"2026-07-05T09:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"DIQG5CLEMSLR3ZUW","created_at":"2026-07-05T09:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"DIQG5CLE","created_at":"2026-07-05T09:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:6b7c0dd63634d0993fdcdb3085db55534c62cd54c30945b009ddf3befaf040a2","target":"graph","created_at":"2026-07-05T09:31:53Z","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/2411.03628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehension, necessitating extensive processing of all video frames before any queries can be made. This presents a significant gap compared to the human ability to watch, listen, think, and respond to streaming inputs in real time, highlighting the limitations of current MLLMs. In this paper, we introduce StreamingBench, the first comprehensive benchmark designed to evaluate the stream","authors_text":"Chi Chen, Fuwen Luo, Junming Lin, Maosong Sun, Peng Li, Yang Liu, Zheng Fang, Zihao Wan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-06T02:50:30Z","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03628","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:fcae191cb8ce136034209f4bdd331fcaa7527e8a3acdec55b9ec91b4218dd546","target":"record","created_at":"2026-07-05T09:31:53Z","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":"8d8e17727a8fee5ecd5baeebaa5d16c339f55ef9be8b7a136736051cd63f049d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-06T02:50:30Z","title_canon_sha256":"f5c7fa5c9bbdcd9191864ffc46532cd44960d2c531b45cd310138d8c568718cc"},"schema_version":"1.0","source":{"id":"2411.03628","kind":"arxiv","version":1}},"canonical_sha256":"1a206e896464971de696f1d5b1347d97df01976fb1036c6b8321f3cf4b14002a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a206e896464971de696f1d5b1347d97df01976fb1036c6b8321f3cf4b14002a","first_computed_at":"2026-07-05T09:31:53.322725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:53.322725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ESLMn3TwxPZriKK0RvfCQDvb8RugXGB1Go35saInNa37lOWvCtn74Gj3SnrvEeI+x7/Dil1tUihS90NZJrsPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:53.323231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcae191cb8ce136034209f4bdd331fcaa7527e8a3acdec55b9ec91b4218dd546","sha256:6b7c0dd63634d0993fdcdb3085db55534c62cd54c30945b009ddf3befaf040a2"],"state_sha256":"4fb30432a5762f64dc69be7eead6c40466bab1216be13e30012b438f54dc0625"}