{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CVJGSVBARKZK6NMJS5N7PCSZGB","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":"7292e3aa77d16089253471fd8626198da3bb20b1de2e36a06ca7e7521952d7b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T18:02:20Z","title_canon_sha256":"36e5f467d261c313369d4702f6c6d1b68bade48c79d83e4de138acfed2ca32fb"},"schema_version":"1.0","source":{"id":"2605.26232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26232","created_at":"2026-05-27T00:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26232v1","created_at":"2026-05-27T00:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26232","created_at":"2026-05-27T00:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"CVJGSVBARKZK","created_at":"2026-05-27T00:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"CVJGSVBARKZK6NMJ","created_at":"2026-05-27T00:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"CVJGSVBA","created_at":"2026-05-27T00:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:fc406ba6c0025046d0d3ba9f8efaa3025e7cc181d175aad2851921e892d67602","target":"graph","created_at":"2026-05-27T00:04:29Z","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/2605.26232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality interference, allowing irrelevant channels to distract the model. To address this issue, we present a unified multimodal video understanding framework, named UniMVU, that performs instruction-aware fusion across video, audio, depth map, or any other modality inputs via two levels of dynamic gating: inner-modality gates emphasize salient regions within each mo","authors_text":"Abdelrahman M. Shaker, Bonan Ding, Fahad Shahbaz Khan, Jiale Cao, Jin Xie, Muhammad Haris Khan, Ufaq Khan, Umair Nawaz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T18:02:20Z","title":"Not All Modalities Are Equal: Instruction-Aware Gating for Multimodal Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26232","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:e6e1e259d40559879767a50b787cfcf627603ab9c2cda81c752c641d287d3859","target":"record","created_at":"2026-05-27T00:04:29Z","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":"7292e3aa77d16089253471fd8626198da3bb20b1de2e36a06ca7e7521952d7b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T18:02:20Z","title_canon_sha256":"36e5f467d261c313369d4702f6c6d1b68bade48c79d83e4de138acfed2ca32fb"},"schema_version":"1.0","source":{"id":"2605.26232","kind":"arxiv","version":1}},"canonical_sha256":"15526954208ab2af3589975bf78a593079ccc82a6fc1e5cc5a4525aa56a87e70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15526954208ab2af3589975bf78a593079ccc82a6fc1e5cc5a4525aa56a87e70","first_computed_at":"2026-05-27T00:04:29.853471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T00:04:29.853471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VzGOzIOM1+qunjhxOpOJRhij+leHCnq7Oq72l+8fsAHXzV2K/mF7CrCFeKlIIv8W9oSOcXQZyMTLduXb1U15CQ==","signature_status":"signed_v1","signed_at":"2026-05-27T00:04:29.854169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6e1e259d40559879767a50b787cfcf627603ab9c2cda81c752c641d287d3859","sha256:fc406ba6c0025046d0d3ba9f8efaa3025e7cc181d175aad2851921e892d67602"],"state_sha256":"d38cf870373b78acbc75846a7327c7a53459c0caee55d08af2dc3fa51a129845"}