{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S2FMRM4JRELJB4VDY7AX64HPLN","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":"f02118c20a48f716f1aca9eba4a67ea22c36036cfbcc9198b65151f7920124fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T08:48:19Z","title_canon_sha256":"43fb3a088ee229ae417e595e35daff322afce9745b948a407d35057b830d7603"},"schema_version":"1.0","source":{"id":"2606.23041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23041","created_at":"2026-06-23T03:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23041v1","created_at":"2026-06-23T03:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23041","created_at":"2026-06-23T03:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"S2FMRM4JRELJ","created_at":"2026-06-23T03:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"S2FMRM4JRELJB4VD","created_at":"2026-06-23T03:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"S2FMRM4J","created_at":"2026-06-23T03:14:07Z"}],"graph_snapshots":[{"event_id":"sha256:4edf098da6031224d59c3baa7109938f6c2fc3412a806874881ccfbfa7b4b7c1","target":"graph","created_at":"2026-06-23T03:14:07Z","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/2606.23041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable success in visual understanding but remain constrained in visual generation due to the fundamental feature discrepancy between semantic perception and pixel-level reconstruction. Bridging this gap requires overcoming two core challenges: endowing semantic encoders with high-fidelity reconstruction capabilities, and effectively aligning generative models with semantic spaces without relying on external teachers. To this end, we propose a novel unified multimodal framework featuring \\textbf{S}emantic-\\textbf{P}ixel self-alignment ","authors_text":"Chenyang Zhu, Hongxiang Li, Hongxu Chen, Jiayin Cai, Long Chen, Xiaolong Jiang, Xiaoshuang Huang, Yao Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T08:48:19Z","title":"SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23041","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":"sha256:5713e1d28df748baa32cbba75836531172166725425dffffecb2239e045ee0fc","target":"record","created_at":"2026-06-23T03:14:07Z","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":"f02118c20a48f716f1aca9eba4a67ea22c36036cfbcc9198b65151f7920124fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T08:48:19Z","title_canon_sha256":"43fb3a088ee229ae417e595e35daff322afce9745b948a407d35057b830d7603"},"schema_version":"1.0","source":{"id":"2606.23041","kind":"arxiv","version":1}},"canonical_sha256":"968ac8b389891690f2a3c7c17f70ef5b63301679fc511b4f67ad8aefa05334d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"968ac8b389891690f2a3c7c17f70ef5b63301679fc511b4f67ad8aefa05334d2","first_computed_at":"2026-06-23T03:14:07.466873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:07.466873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WgcsMMv51zN1nCStBMvYP69V5qrl9Up01MTn34Yp3MANHFl7W9oUxXTbgwCAO+EnmsW9pdyegf/VgPx6WAJuAw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:07.467225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5713e1d28df748baa32cbba75836531172166725425dffffecb2239e045ee0fc","sha256:4edf098da6031224d59c3baa7109938f6c2fc3412a806874881ccfbfa7b4b7c1"],"state_sha256":"cb006d3364a3313d6e4d271bf3de2cc9fe94b9bc17762c95c929742bcfcfb5b9"}