{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZTL6YZHYCPKYWDRYX2R2S43XT4","short_pith_number":"pith:ZTL6YZHY","canonical_record":{"source":{"id":"2211.11701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:22:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"00f6fd53e9a774df15a8cef37aef6e642c79d83d92b83e20921d8dbd2c8d05f6","abstract_canon_sha256":"a58088ef57353d25d24e8da2f7c0c9b78503f4fa9aefa3c581152a507ebc395b"},"schema_version":"1.0"},"canonical_sha256":"ccd7ec64f813d58b0e38bea3a973779f1a24c835cb2f444f5290ff17c284ff7e","source":{"kind":"arxiv","id":"2211.11701","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZTL6YZHYCPKYWDRYX2R2S43XT4","target":"record","payload":{"canonical_record":{"source":{"id":"2211.11701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T18:22:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"00f6fd53e9a774df15a8cef37aef6e642c79d83d92b83e20921d8dbd2c8d05f6","abstract_canon_sha256":"a58088ef57353d25d24e8da2f7c0c9b78503f4fa9aefa3c581152a507ebc395b"},"schema_version":"1.0"},"canonical_sha256":"ccd7ec64f813d58b0e38bea3a973779f1a24c835cb2f444f5290ff17c284ff7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:57.013148Z","signature_b64":"aIiMxR01g8xn3H1KGCr1VNX0UuUwBWpP/np2FjLkwj014QR5CCcqRMb5kaUqj8ajdCdFbkT9V9XNy3DnoOttCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccd7ec64f813d58b0e38bea3a973779f1a24c835cb2f444f5290ff17c284ff7e","last_reissued_at":"2026-07-05T05:17:57.012714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:57.012714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.11701","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkZxK9iVEbjrEb63Box9RsyFqreteCaP2MP3MyOxm41ntsD+q25/QEtcm31itBXNzbAFjvF/CK1pH3+KJoMqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:18:32.160439Z"},"content_sha256":"429192d22077f188e1640c37272497ad7db988c1a470b83c98d4c1b12e9471cf","schema_version":"1.0","event_id":"sha256:429192d22077f188e1640c37272497ad7db988c1a470b83c98d4c1b12e9471cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZTL6YZHYCPKYWDRYX2R2S43XT4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jaemin Cho, Jie Lei, Mohit Bansal, Zineng Tang","submitted_at":"2022-11-21T18:22:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11701","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.11701/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdhvSmQ46jhDvCJ5zTXP+WkHaEcZ0Z/0ciGd9ucNZ5gL06a7N09z0fou0GEoYlAVWCQk8lcyreaH1Tub27doCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:18:32.160964Z"},"content_sha256":"1c6a9a5f0c08674b3b9a023f74a512a4965664494e4e726b229f436dc280ce71","schema_version":"1.0","event_id":"sha256:1c6a9a5f0c08674b3b9a023f74a512a4965664494e4e726b229f436dc280ce71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTL6YZHYCPKYWDRYX2R2S43XT4/bundle.json","state_url":"https://pith.science/pith/ZTL6YZHYCPKYWDRYX2R2S43XT4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTL6YZHYCPKYWDRYX2R2S43XT4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T13:18:32Z","links":{"resolver":"https://pith.science/pith/ZTL6YZHYCPKYWDRYX2R2S43XT4","bundle":"https://pith.science/pith/ZTL6YZHYCPKYWDRYX2R2S43XT4/bundle.json","state":"https://pith.science/pith/ZTL6YZHYCPKYWDRYX2R2S43XT4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTL6YZHYCPKYWDRYX2R2S43XT4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TqAFHqVhgjLsV91uQOOG4aaX3qlKhcNJsGHebOhuHGZTiqj5WSLOE3c+r76PTbdEtjBT8W/7Bqf9Wc2tjcTzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T13:18:32.165579Z","bundle_sha256":"f88cd4200943ac068c6b4ec06d9e0b81b3ef818c6dd5ed311811994e48d3879f"}}