{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VXZQHGZDFIL2VOZ6QAK47D6CAP","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":"708abbf7f8966d2b5287dcc843f4509ec549678be584c1c1bf55b43c5f87e3f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T15:50:19Z","title_canon_sha256":"72ecdc711537611a8bf5ada188ae6ec5a0fcecaae9edea004ddf9b542433041c"},"schema_version":"1.0","source":{"id":"2304.05930","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05930","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05930v3","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05930","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"VXZQHGZDFIL2","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"pith_short_16","alias_value":"VXZQHGZDFIL2VOZ6","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"pith_short_8","alias_value":"VXZQHGZD","created_at":"2026-07-05T09:07:43Z"}],"graph_snapshots":[{"event_id":"sha256:d8932230f0c9ab12bd8fdeaf919309fcead49bd5f5c5ad4d4414985070c54790","target":"graph","created_at":"2026-07-05T09:07:43Z","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/2304.05930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present an end-to-end trainable unified multiscale encoder-decoder transformer that is focused on dense prediction tasks in video. The presented Multiscale Encoder-Decoder Video Transformer (MED-VT) uses multiscale representation throughout and employs an optional input beyond video (e.g., audio), when available, for multimodal processing (MED-VT++). Multiscale representation at both encoder and decoder yields three key benefits: (i) implicit extraction of spatiotemporal features at different levels of abstraction for capturing dynamics without reliance on input optical flow,","authors_text":"He Zhao, Mennatullah Siam, Rezaul Karim, Richard P. Wildes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T15:50:19Z","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05930","kind":"arxiv","version":3},"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":"sha256:2e1710f5ee199803f8d46954ccc8a97a3e9d751b872f8584fd132c1dfd9a212a","target":"record","created_at":"2026-07-05T09:07:43Z","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":"708abbf7f8966d2b5287dcc843f4509ec549678be584c1c1bf55b43c5f87e3f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T15:50:19Z","title_canon_sha256":"72ecdc711537611a8bf5ada188ae6ec5a0fcecaae9edea004ddf9b542433041c"},"schema_version":"1.0","source":{"id":"2304.05930","kind":"arxiv","version":3}},"canonical_sha256":"adf3039b232a17aabb3e8015cf8fc203d3e2666e9b10c236b4fde361584defd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adf3039b232a17aabb3e8015cf8fc203d3e2666e9b10c236b4fde361584defd7","first_computed_at":"2026-07-05T09:07:43.325143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:43.325143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zDcbIDyEXnOay4Tifwo5kuueoqA7USO/IchQbpY143L4nfv7cT7DHkCN/BEllOYVj2KNbskUxs21VjJqIDFACA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:43.325609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05930","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e1710f5ee199803f8d46954ccc8a97a3e9d751b872f8584fd132c1dfd9a212a","sha256:d8932230f0c9ab12bd8fdeaf919309fcead49bd5f5c5ad4d4414985070c54790"],"state_sha256":"e10d3df51084f389b3da2c524e4a5288d818acad088858e9c80172b8f3679235"}