{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S2FMRM4JRELJB4VDY7AX64HPLN","short_pith_number":"pith:S2FMRM4J","schema_version":"1.0","canonical_sha256":"968ac8b389891690f2a3c7c17f70ef5b63301679fc511b4f67ad8aefa05334d2","source":{"kind":"arxiv","id":"2606.23041","version":1},"attestation_state":"computed","paper":{"title":"SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Zhu, Hongxiang Li, Hongxu Chen, Jiayin Cai, Long Chen, Xiaolong Jiang, Xiaoshuang Huang, Yao Hu","submitted_at":"2026-06-22T08:48:19Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.23041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T08:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"43fb3a088ee229ae417e595e35daff322afce9745b948a407d35057b830d7603","abstract_canon_sha256":"f02118c20a48f716f1aca9eba4a67ea22c36036cfbcc9198b65151f7920124fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:07.467225Z","signature_b64":"WgcsMMv51zN1nCStBMvYP69V5qrl9Up01MTn34Yp3MANHFl7W9oUxXTbgwCAO+EnmsW9pdyegf/VgPx6WAJuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"968ac8b389891690f2a3c7c17f70ef5b63301679fc511b4f67ad8aefa05334d2","last_reissued_at":"2026-06-23T03:14:07.466873Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:07.466873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Zhu, Hongxiang Li, Hongxu Chen, Jiayin Cai, Long Chen, Xiaolong Jiang, Xiaoshuang Huang, Yao Hu","submitted_at":"2026-06-22T08:48:19Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23041","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.23041/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.23041","created_at":"2026-06-23T03:14:07.466933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23041v1","created_at":"2026-06-23T03:14:07.466933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23041","created_at":"2026-06-23T03:14:07.466933+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2FMRM4JRELJ","created_at":"2026-06-23T03:14:07.466933+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2FMRM4JRELJB4VD","created_at":"2026-06-23T03:14:07.466933+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2FMRM4J","created_at":"2026-06-23T03:14:07.466933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN","json":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN.json","graph_json":"https://pith.science/api/pith-number/S2FMRM4JRELJB4VDY7AX64HPLN/graph.json","events_json":"https://pith.science/api/pith-number/S2FMRM4JRELJB4VDY7AX64HPLN/events.json","paper":"https://pith.science/paper/S2FMRM4J"},"agent_actions":{"view_html":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN","download_json":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN.json","view_paper":"https://pith.science/paper/S2FMRM4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23041&json=true","fetch_graph":"https://pith.science/api/pith-number/S2FMRM4JRELJB4VDY7AX64HPLN/graph.json","fetch_events":"https://pith.science/api/pith-number/S2FMRM4JRELJB4VDY7AX64HPLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN/action/storage_attestation","attest_author":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN/action/author_attestation","sign_citation":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN/action/citation_signature","submit_replication":"https://pith.science/pith/S2FMRM4JRELJB4VDY7AX64HPLN/action/replication_record"}},"created_at":"2026-06-23T03:14:07.466933+00:00","updated_at":"2026-06-23T03:14:07.466933+00:00"}