{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CSB6DU6FXNLBXZDF3VY76WEMZW","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":"095bb66644e4a99af2e9207f99595117e5a5e7ae4f4298f08daf55dd9cf71e45","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T21:31:40Z","title_canon_sha256":"7e18790648d2ca2dec1e2b86f6b684a397894bea5107ee3a8abdc1856bb235e8"},"schema_version":"1.0","source":{"id":"2607.23373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23373","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23373v1","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23373","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"CSB6DU6FXNLB","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"pith_short_16","alias_value":"CSB6DU6FXNLBXZDF","created_at":"2026-07-28T01:22:49Z"},{"alias_kind":"pith_short_8","alias_value":"CSB6DU6F","created_at":"2026-07-28T01:22:49Z"}],"graph_snapshots":[{"event_id":"sha256:474f51eff59624eff786c0b02eb59a715351fcc569dbaa847ef31544d553eccf","target":"graph","created_at":"2026-07-28T01:22:49Z","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/2607.23373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deployment on resource-constrained edge devices. While efforts to compress LVLMs focus heavily on vision token reduction or smaller language models, the vision encoder is largely overlooked, typically deployed as a monolithic, computationally heavy feature extractor. Moreover, there is no previous effort that designs a vision encoder for LVLMs directly optimized for on-device latency. In this paper, we present UltraViT, a vision encoder for LVLMs, explicitly designed and optimized for","authors_text":"Adrian Bulat, Alberto Baldrati, Anestis Zaganidis, Georgios Tzimiropoulos, Hyeonuk Kim, Ioannis Maniadis Metaxas, Yassine Ouali","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T21:31:40Z","title":"UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23373","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":"sha256:673d268321aec3123a194f526622b906e205fbc1d648b187d72b46eea5a9df0d","target":"record","created_at":"2026-07-28T01:22:49Z","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":"095bb66644e4a99af2e9207f99595117e5a5e7ae4f4298f08daf55dd9cf71e45","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T21:31:40Z","title_canon_sha256":"7e18790648d2ca2dec1e2b86f6b684a397894bea5107ee3a8abdc1856bb235e8"},"schema_version":"1.0","source":{"id":"2607.23373","kind":"arxiv","version":1}},"canonical_sha256":"1483e1d3c5bb561be465dd71ff588ccd9c6ca4732998ecd8fb7229898de6027f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1483e1d3c5bb561be465dd71ff588ccd9c6ca4732998ecd8fb7229898de6027f","first_computed_at":"2026-07-28T01:22:49.643831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:49.643831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kz5EhrdYCmkzeu3NIPEpFGQJCTM/gwpdFgEuxC2qSm7XiVruzsLSQ+gD9qHtzjYorYacpBkxtd9XNIMyvwahAQ==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:49.644645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:673d268321aec3123a194f526622b906e205fbc1d648b187d72b46eea5a9df0d","sha256:474f51eff59624eff786c0b02eb59a715351fcc569dbaa847ef31544d553eccf"],"state_sha256":"af4fa31916657f20bbefbed9e88aaf56bf979ef3533d079a365a6ddab03becb1"}