{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GDWHIKMLH2XTNECWPJOM5N75EA","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":"f508f0cc1dd2109570362c1638c802bc2522766c046d5a2394993d4b2ecc5fff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T04:29:33Z","title_canon_sha256":"1caa5fe385e239c9c6bc85ce8f28a6884f3d15df7170eda9d9c064b61f0b46c0"},"schema_version":"1.0","source":{"id":"2605.19342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19342","created_at":"2026-05-20T01:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19342v1","created_at":"2026-05-20T01:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19342","created_at":"2026-05-20T01:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"GDWHIKMLH2XT","created_at":"2026-05-20T01:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"GDWHIKMLH2XTNECW","created_at":"2026-05-20T01:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"GDWHIKML","created_at":"2026-05-20T01:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:ffe37335d62496ab803e2e36eb3e340189328c346e6885f36636ff9951715102","target":"graph","created_at":"2026-05-20T01:05:40Z","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/2605.19342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent representations that lack sufficient semantic richness, limiting their ability to support diverse region-level reasoning tasks. In this work, we introduce Semantic-Enriched Latent Visual Reasoning (SLVR), a two-stage learning framework that enriches latent representations with attribute-level visual semantics and aligns them with diverse reasoning objectives. In the f","authors_text":"Feng Chen, Fengyun Rao, Jing Liu, Jing Lyu, Jingyi Lu, Longteng Guo, Qixun Wang, Tianren Zhang, Tianrun Xu, Yuan Wang, Yue Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T04:29:33Z","title":"Semantic-Enriched Latent Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19342","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:f22e55c57a45a38ec987daec6d34c26148a2cb72c8a84c687bcdf0c581fd14bd","target":"record","created_at":"2026-05-20T01:05:40Z","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":"f508f0cc1dd2109570362c1638c802bc2522766c046d5a2394993d4b2ecc5fff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T04:29:33Z","title_canon_sha256":"1caa5fe385e239c9c6bc85ce8f28a6884f3d15df7170eda9d9c064b61f0b46c0"},"schema_version":"1.0","source":{"id":"2605.19342","kind":"arxiv","version":1}},"canonical_sha256":"30ec74298b3eaf3690567a5cceb7fd20020dfbb0401bf596e766e3c85253313a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30ec74298b3eaf3690567a5cceb7fd20020dfbb0401bf596e766e3c85253313a","first_computed_at":"2026-05-20T01:05:40.435616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:40.435616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HaeXu1kKOEx652aXXDP5pCGsDlw9fXbXP3SL4VZqRUy1/Sd96m1W6OOOrg7dbDPQg4SgTUiCEs8bXIRunNGOCA==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:40.436275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f22e55c57a45a38ec987daec6d34c26148a2cb72c8a84c687bcdf0c581fd14bd","sha256:ffe37335d62496ab803e2e36eb3e340189328c346e6885f36636ff9951715102"],"state_sha256":"a0961427dffe26f2878fd31d68465371ef4a3218535b731b227288faae3622a8"}