{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3IFOBBNHVTGAZTIK57IOG2BBJM","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":"c03d385eabcdbba08f5b340e409e5bedcaeb5ba3e5133949030db147444183f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T08:10:32Z","title_canon_sha256":"20511ff786950ff03dec01f3869b55bf473f522d3ff67c57a15b28415190054e"},"schema_version":"1.0","source":{"id":"2412.10435","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10435","created_at":"2026-07-05T11:31:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10435v2","created_at":"2026-07-05T11:31:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10435","created_at":"2026-07-05T11:31:03Z"},{"alias_kind":"pith_short_12","alias_value":"3IFOBBNHVTGA","created_at":"2026-07-05T11:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"3IFOBBNHVTGAZTIK","created_at":"2026-07-05T11:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"3IFOBBNH","created_at":"2026-07-05T11:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:da5d37bc3375bbf2e42c24c123becac7893567c09ce7501f80db24f833165903","target":"graph","created_at":"2026-07-05T11:31:03Z","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/2412.10435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, with the emergence of recent Multimodal Large Language Model (MLLM) technology, it has become possible to exploit its video understanding capability on different classification tasks. In practice, we face the difficulty of huge requirements for GPU resource if we need to deploy MLLMs online. In this paper, we propose COEF-VQ, a novel cascaded MLLM framework designed to enhance video quality understanding on the short-video platform while optimizing computational efficiency. Our approach integrates an entropy-based pre-filtering stage, where a lightweight model assesses uncertainty an","authors_text":"Bingfeng Deng, Hongyu Xiong, Ming Rui Wang, Sen Jia, Xin Dong, Yan Li, Zhenheng Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T08:10:32Z","title":"COEF-VQ: Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10435","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:bdda0ca4d1792ce28d048220f697929e95605bc519d12a98e1a46522d2472505","target":"record","created_at":"2026-07-05T11:31:03Z","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":"c03d385eabcdbba08f5b340e409e5bedcaeb5ba3e5133949030db147444183f5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T08:10:32Z","title_canon_sha256":"20511ff786950ff03dec01f3869b55bf473f522d3ff67c57a15b28415190054e"},"schema_version":"1.0","source":{"id":"2412.10435","kind":"arxiv","version":2}},"canonical_sha256":"da0ae085a7accc0ccd0aefd0e368214b30231c7775f36fea10c3cdc3999aa3e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da0ae085a7accc0ccd0aefd0e368214b30231c7775f36fea10c3cdc3999aa3e1","first_computed_at":"2026-07-05T11:31:03.648517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:03.648517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JaZOTaQ3U/dDG+G7snExfgUiXf314+IWAz2nSCf2BJa/M/2R3BQq5HTWkg7uAbRZC217X6VswRog6d+qSFRGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:03.649066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10435","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdda0ca4d1792ce28d048220f697929e95605bc519d12a98e1a46522d2472505","sha256:da5d37bc3375bbf2e42c24c123becac7893567c09ce7501f80db24f833165903"],"state_sha256":"c21f960a08b8e170b72dcfdd23bb96f5922a2f6ca2d1c52f9a6b3a2abaf51c33"}