{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZTL6YZHYCPKYWDRYX2R2S43XT4","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":"a58088ef57353d25d24e8da2f7c0c9b78503f4fa9aefa3c581152a507ebc395b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:22:39Z","title_canon_sha256":"00f6fd53e9a774df15a8cef37aef6e642c79d83d92b83e20921d8dbd2c8d05f6"},"schema_version":"1.0","source":{"id":"2211.11701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11701","created_at":"2026-07-05T05:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11701v1","created_at":"2026-07-05T05:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11701","created_at":"2026-07-05T05:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZTL6YZHYCPKY","created_at":"2026-07-05T05:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZTL6YZHYCPKYWDRY","created_at":"2026-07-05T05:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZTL6YZHY","created_at":"2026-07-05T05:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:1c6a9a5f0c08674b3b9a023f74a512a4965664494e4e726b229f436dc280ce71","target":"graph","created_at":"2026-07-05T05:17:57Z","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/2211.11701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with linear complexity, in contrast to the quadratic complexity of self-attention used in many state-of-the-art transformer-based models. To further improve the efficiency of our framework, we also study applying LayerDrop on cross-attention layers and introduce a mixed-stream architecture for cross-modal retrieval. We evaluate Perceiver-VL on diverse video-text and i","authors_text":"Jaemin Cho, Jie Lei, Mohit Bansal, Zineng Tang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:22:39Z","title":"Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11701","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":"sha256:429192d22077f188e1640c37272497ad7db988c1a470b83c98d4c1b12e9471cf","target":"record","created_at":"2026-07-05T05:17:57Z","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":"a58088ef57353d25d24e8da2f7c0c9b78503f4fa9aefa3c581152a507ebc395b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:22:39Z","title_canon_sha256":"00f6fd53e9a774df15a8cef37aef6e642c79d83d92b83e20921d8dbd2c8d05f6"},"schema_version":"1.0","source":{"id":"2211.11701","kind":"arxiv","version":1}},"canonical_sha256":"ccd7ec64f813d58b0e38bea3a973779f1a24c835cb2f444f5290ff17c284ff7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccd7ec64f813d58b0e38bea3a973779f1a24c835cb2f444f5290ff17c284ff7e","first_computed_at":"2026-07-05T05:17:57.012714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:57.012714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aIiMxR01g8xn3H1KGCr1VNX0UuUwBWpP/np2FjLkwj014QR5CCcqRMb5kaUqj8ajdCdFbkT9V9XNy3DnoOttCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:57.013148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:429192d22077f188e1640c37272497ad7db988c1a470b83c98d4c1b12e9471cf","sha256:1c6a9a5f0c08674b3b9a023f74a512a4965664494e4e726b229f436dc280ce71"],"state_sha256":"4b51f9a3b3bd340f53a25738b6c909642673a2fd9f28ea9b96c64bfe3a5c67a6"}