{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CV32CTOF74CIYVOBDYKRPRPJOR","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":"f9b0332db1adbde385b435b12fc9716b2a1663756198f4e0cd0994d180710649","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T12:46:56Z","title_canon_sha256":"7319a40d33d68cff63a5057232bc7c93f8ef13b2ba22212a6f07b4f8b52e8f7a"},"schema_version":"1.0","source":{"id":"2608.08676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08676","created_at":"2026-08-11T01:23:26Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08676v1","created_at":"2026-08-11T01:23:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08676","created_at":"2026-08-11T01:23:26Z"},{"alias_kind":"pith_short_12","alias_value":"CV32CTOF74CI","created_at":"2026-08-11T01:23:26Z"},{"alias_kind":"pith_short_16","alias_value":"CV32CTOF74CIYVOB","created_at":"2026-08-11T01:23:26Z"},{"alias_kind":"pith_short_8","alias_value":"CV32CTOF","created_at":"2026-08-11T01:23:26Z"}],"graph_snapshots":[{"event_id":"sha256:f1f28cabaeadb78cc01acee637ce52d99d77d0d2340e10663e7066baad3f5d99","target":"graph","created_at":"2026-08-11T01:23:26Z","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/2608.08676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic vision encoders have become a central visual interface for multimodal understanding and semantic conditioning in image generation. However, their final tokens discard fine-grained visual details, leading to poor pixel reconstruction and limiting their use in reconstruction-sensitive tasks such as image generation and editing. In this work, we ask whether understanding, generation, and editing can be modeled in a single visual representation space built from a pretrained semantic ViT. We show that the frozen Transformer blocks of a semantic ViT are not intrinsically unable to preserve ","authors_text":"Feize Wu, Guanglu Wan, Jie Qin, Jinbo Yan, Junyan He, Limeng Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T12:46:56Z","title":"UniSpace: Unified Visual Representation and Scalable Multimodal Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08676","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:d103634a06e5dbdc9cbe1963a56e3d7f50d561d8efdbf1eb86276a8f0b142470","target":"record","created_at":"2026-08-11T01:23:26Z","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":"f9b0332db1adbde385b435b12fc9716b2a1663756198f4e0cd0994d180710649","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T12:46:56Z","title_canon_sha256":"7319a40d33d68cff63a5057232bc7c93f8ef13b2ba22212a6f07b4f8b52e8f7a"},"schema_version":"1.0","source":{"id":"2608.08676","kind":"arxiv","version":1}},"canonical_sha256":"1577a14dc5ff048c55c11e1517c5e9746e15c25c5ca57c239434f534c19592ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1577a14dc5ff048c55c11e1517c5e9746e15c25c5ca57c239434f534c19592ce","first_computed_at":"2026-08-11T01:23:26.885204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:23:26.885204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wG7wGFS+9IpQCaPnP6VaVRuR7eBoMNR6WYZObTqUxfisvAAXMjAIImj1fiqJ8CbPG7b59HI1Vb2CHnbn7DHuBg==","signature_status":"signed_v1","signed_at":"2026-08-11T01:23:26.887552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d103634a06e5dbdc9cbe1963a56e3d7f50d561d8efdbf1eb86276a8f0b142470","sha256:f1f28cabaeadb78cc01acee637ce52d99d77d0d2340e10663e7066baad3f5d99"],"state_sha256":"08aa528b91d9ed607d56e0a2e8632a0716cdf5f67fc491d8c39c61dc5ee3739f"}