{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2BDI7RYEWHJNSKPJ3AZAPGH5LG","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":"b764161a519f894329ae452578aaa1674f0b6068d855bfe2dad9fdde01f1b822","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T17:59:39Z","title_canon_sha256":"d9c9e01f27b07e15ec4fd4edd0f871eb1af0d6d326e4ed6bbb17ddf1ce008e69"},"schema_version":"1.0","source":{"id":"2607.22531","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22531","created_at":"2026-07-27T01:21:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22531v1","created_at":"2026-07-27T01:21:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22531","created_at":"2026-07-27T01:21:32Z"},{"alias_kind":"pith_short_12","alias_value":"2BDI7RYEWHJN","created_at":"2026-07-27T01:21:32Z"},{"alias_kind":"pith_short_16","alias_value":"2BDI7RYEWHJNSKPJ","created_at":"2026-07-27T01:21:32Z"},{"alias_kind":"pith_short_8","alias_value":"2BDI7RYE","created_at":"2026-07-27T01:21:32Z"}],"graph_snapshots":[{"event_id":"sha256:d3803649047c3c1ae80c23c17f41187607cda26f33c6a2e47027f1e6f52c5d6c","target":"graph","created_at":"2026-07-27T01:21:32Z","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/2607.22531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified multimodal models seek a shared visual token space that supports both multimodal understanding and image generation. Discrete methods unify the interface via a shared codebook, whereas continuous pipelines often rely on two disparate representations -- semantic features (e.g., ViT) for understanding and low-level latents (e.g., VAE) for synthesis -- resulting in mismatched latent spaces. We propose Twins, a unified continuous token space formed by channel-wise concatenating ViT and VAE features on the same token grid, so the sequence length is unchanged and attention cost does not incr","authors_text":"Bin Lin, Bohao Li, Hao Wang, Jian-Wei Zhang, Kaixiong Gong, Liefeng Bo, Miles Yang, Mingzhe Zheng, Xiangyu Yue, Xin Cai, Yunlong Lin, Zhao Zhong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T17:59:39Z","title":"Twins: Learn to Predict Unified Representations with Focal Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22531","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:c154b0e0f102daa019a617151db9c5083a7f9d30172cd5270b676f2ad718c630","target":"record","created_at":"2026-07-27T01:21:32Z","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":"b764161a519f894329ae452578aaa1674f0b6068d855bfe2dad9fdde01f1b822","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T17:59:39Z","title_canon_sha256":"d9c9e01f27b07e15ec4fd4edd0f871eb1af0d6d326e4ed6bbb17ddf1ce008e69"},"schema_version":"1.0","source":{"id":"2607.22531","kind":"arxiv","version":1}},"canonical_sha256":"d0468fc704b1d2d929e9d8320798fd5992fa16a5b2a0d6ee7030045db322063f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0468fc704b1d2d929e9d8320798fd5992fa16a5b2a0d6ee7030045db322063f","first_computed_at":"2026-07-27T01:21:32.431687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:21:32.431687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kQhNdNWZR7xMRl85T/J9R+XFVvrCZVPr6D2SWdLI3HEAGgHqCJ7qCyhLBsJSOEJ9cYei0Qh5Ywml8GIHazo4CA==","signature_status":"signed_v1","signed_at":"2026-07-27T01:21:32.432513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22531","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c154b0e0f102daa019a617151db9c5083a7f9d30172cd5270b676f2ad718c630","sha256:d3803649047c3c1ae80c23c17f41187607cda26f33c6a2e47027f1e6f52c5d6c"],"state_sha256":"a82b61be1d10f6051b6fbf1fe1efb95b73797dd678632e6e20b6660d6e9ae2cb"}