{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EGAC2JA3KZJRCXHRVQD6NYYKWE","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":"20550617386eac1419eb9e4c60bf0d164b3f354709a11d9fb8ab338e403be347","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:46:07Z","title_canon_sha256":"feacc48b08e1a6d1d89781496986655d63e8cdc9ade8e72f91c8a313a942ea06"},"schema_version":"1.0","source":{"id":"2606.13289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13289","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13289v1","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13289","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"EGAC2JA3KZJR","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"EGAC2JA3KZJRCXHR","created_at":"2026-06-12T01:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"EGAC2JA3","created_at":"2026-06-12T01:09:50Z"}],"graph_snapshots":[{"event_id":"sha256:c97f3c4e0b82c043d3f6f503fd9cd6b514bbcc8b8684268a1add0cfe34f20c8c","target":"graph","created_at":"2026-06-12T01:09:50Z","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/2606.13289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space. In this paper, we present HYDRA-X, the first UMM that unifies image and video tokenization within a single Vision Transformer (ViT). Our design is driven by two core challenges: efficiently injecting spatiotemporal reconstruction capability into a native ViT, and embedding image- and video-level semantic awareness into the latent space. To address the first, comprehensive ablations reveal two key findings: (1) frame-level causal temporal attentio","authors_text":"Changlin Li, Guozhen Zhang, Jianbing Wu, Junzhe Li, Liefeng Bo, Limin Wang, Miles Yang, Tao Huang, Tianhui Song, Xiao Zhang, Xuerui Qiu, Yang Li, Yutao Cui, Zhao Zhong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:46:07Z","title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13289","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":"sha256:83f981c191c60caa63a8e9de13fcfd8f82420d45fdc8d05ab41b73651b233788","target":"record","created_at":"2026-06-12T01:09:50Z","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":"20550617386eac1419eb9e4c60bf0d164b3f354709a11d9fb8ab338e403be347","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:46:07Z","title_canon_sha256":"feacc48b08e1a6d1d89781496986655d63e8cdc9ade8e72f91c8a313a942ea06"},"schema_version":"1.0","source":{"id":"2606.13289","kind":"arxiv","version":1}},"canonical_sha256":"21802d241b5653115cf1ac07e6e30ab116412dd7335c112222779d37371db74a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21802d241b5653115cf1ac07e6e30ab116412dd7335c112222779d37371db74a","first_computed_at":"2026-06-12T01:09:50.855468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:50.855468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lc8rUhx4iTuDk1uGy9tQNhJZF2MMGP7HmnyjIjQe5/oHANX+8s7M5CjGeut8Z6WNFJqtSyNiCuWtJjT+2t8CAg==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:50.856126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83f981c191c60caa63a8e9de13fcfd8f82420d45fdc8d05ab41b73651b233788","sha256:c97f3c4e0b82c043d3f6f503fd9cd6b514bbcc8b8684268a1add0cfe34f20c8c"],"state_sha256":"c1c08ea9bce44ef9eb4d1425afedee081064906747515b858e9acbb7df082308"}