{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NO74TOPD4LR3VX6LIB5XRFRWV2","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":"0d05214e092c0e2895054b28b3910ac89c71b9d3c9d76b80b6a86323bc7cb48c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T15:37:22Z","title_canon_sha256":"3a22edde2aeffb38fd6bb8d57e00af2c92a00fe5b1e71c18ea91ec9b3b94b80f"},"schema_version":"1.0","source":{"id":"2508.08098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08098","created_at":"2026-07-05T11:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08098v2","created_at":"2026-07-05T11:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08098","created_at":"2026-07-05T11:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"NO74TOPD4LR3","created_at":"2026-07-05T11:53:50Z"},{"alias_kind":"pith_short_16","alias_value":"NO74TOPD4LR3VX6L","created_at":"2026-07-05T11:53:50Z"},{"alias_kind":"pith_short_8","alias_value":"NO74TOPD","created_at":"2026-07-05T11:53:50Z"}],"graph_snapshots":[{"event_id":"sha256:362c11bfc95813759235b0d4e9b82ed75a32b8a1b0478b552d7ebcf9e7829502","target":"graph","created_at":"2026-07-05T11:53:50Z","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/2508.08098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces TBAC-UniImage, a novel unified model for multimodal understanding and generation. We achieve this by deeply integrating a pre-trained Diffusion Model, acting as a generative ladder, with a Multimodal Large Language Model (MLLM). Previous diffusion-based unified models face two primary limitations. One approach uses only the MLLM's final hidden state as the generative condition. This creates a shallow connection, as the generator is isolated from the rich, hierarchical representations within the MLLM's intermediate layers. The other approach, pretraining a unified generati","authors_text":"Junzhe Xu, Xi Chen, Yuyang Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T15:37:22Z","title":"TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08098","kind":"arxiv","version":2},"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:e57c23c71b6b9173b32a36b38998c06412052e8c69ec4843fa818be2a9916462","target":"record","created_at":"2026-07-05T11:53:50Z","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":"0d05214e092c0e2895054b28b3910ac89c71b9d3c9d76b80b6a86323bc7cb48c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T15:37:22Z","title_canon_sha256":"3a22edde2aeffb38fd6bb8d57e00af2c92a00fe5b1e71c18ea91ec9b3b94b80f"},"schema_version":"1.0","source":{"id":"2508.08098","kind":"arxiv","version":2}},"canonical_sha256":"6bbfc9b9e3e2e3badfcb407b789636ae95811b8f0d821ce868b7a77a33be2ac2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bbfc9b9e3e2e3badfcb407b789636ae95811b8f0d821ce868b7a77a33be2ac2","first_computed_at":"2026-07-05T11:53:50.489001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:50.489001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QLnQ7toqkoYc9oQcC8AufKRAbweFuQC94sSgGgoN3Pa6BZly5AAA7RnUi+uLW4ZQ9YfIVhqEQt9yBOUa3d5HCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:50.489410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08098","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e57c23c71b6b9173b32a36b38998c06412052e8c69ec4843fa818be2a9916462","sha256:362c11bfc95813759235b0d4e9b82ed75a32b8a1b0478b552d7ebcf9e7829502"],"state_sha256":"5d2df575f0fb1b54f810eaa956073ac57b137de4006cb1552f903c26fcaa42af"}