{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YHOYE4ITP52HLAFCO5HLGKGWWS","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":"656819747b01f13ea5bc3f487f14d8f7580548f9d4851da7005b0247aa600b0a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T23:59:32Z","title_canon_sha256":"49749d33be401e02ee73903f8561295e28f3248fc2aed5c295183112ee387b37"},"schema_version":"1.0","source":{"id":"2509.07295","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07295","created_at":"2026-06-26T01:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07295v4","created_at":"2026-06-26T01:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07295","created_at":"2026-06-26T01:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"YHOYE4ITP52H","created_at":"2026-06-26T01:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"YHOYE4ITP52HLAFC","created_at":"2026-06-26T01:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"YHOYE4IT","created_at":"2026-06-26T01:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:b9f7e4a4b4b0a6d02d85fd6d6ec4475b185d231aea4c4d38877d9a53a83cba15","target":"graph","created_at":"2026-06-26T01:15:14Z","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/2509.07295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details, even when they use hundreds of words to describe a simple image. We introduce Reconstruction Alignment (RECA), a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense \"text prompts\", providing rich supervision without captions. Concretely, RECA conditions a UMM on its own visual understanding embe","authors_text":"Ji Xie, Luke Zettlemoyer, Trevor Darrell, Xudong Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T23:59:32Z","title":"Reconstruction Alignment Improves Unified Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07295","kind":"arxiv","version":4},"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:ad09d7ba36dbbd4bc78403dc8721074800997a4ec26e40fe6a0e4e6c60b45964","target":"record","created_at":"2026-06-26T01:15:14Z","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":"656819747b01f13ea5bc3f487f14d8f7580548f9d4851da7005b0247aa600b0a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T23:59:32Z","title_canon_sha256":"49749d33be401e02ee73903f8561295e28f3248fc2aed5c295183112ee387b37"},"schema_version":"1.0","source":{"id":"2509.07295","kind":"arxiv","version":4}},"canonical_sha256":"c1dd8271137f747580a2774eb328d6b4996c5cdd762cbb0ea9f0e444d510328e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1dd8271137f747580a2774eb328d6b4996c5cdd762cbb0ea9f0e444d510328e","first_computed_at":"2026-06-26T01:15:14.368840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:14.368840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4l/7JC6+TlK9judOjAbXf7xsNlrKhmPUIyMmO4Igzl/ckvmtS4zEXakKvcaIiSIFkXG55muH/9wK2tFZ/I3TDQ==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:14.369287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.07295","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad09d7ba36dbbd4bc78403dc8721074800997a4ec26e40fe6a0e4e6c60b45964","sha256:b9f7e4a4b4b0a6d02d85fd6d6ec4475b185d231aea4c4d38877d9a53a83cba15"],"state_sha256":"a6563fda3ee2bf3e5caf285c1e10ba1afb791e0b96e45b7d889425f630e9ed2c"}