{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GDWHIKMLH2XTNECWPJOM5N75EA","short_pith_number":"pith:GDWHIKML","schema_version":"1.0","canonical_sha256":"30ec74298b3eaf3690567a5cceb7fd20020dfbb0401bf596e766e3c85253313a","source":{"kind":"arxiv","id":"2605.19342","version":1},"attestation_state":"computed","paper":{"title":"Semantic-Enriched Latent Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Chen, Fengyun Rao, Jing Liu, Jing Lyu, Jingyi Lu, Longteng Guo, Qixun Wang, Tianren Zhang, Tianrun Xu, Yuan Wang, Yue Sun","submitted_at":"2026-05-19T04:29:33Z","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"},"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":"2605.19342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T04:29:33Z","cross_cats_sorted":[],"title_canon_sha256":"1caa5fe385e239c9c6bc85ce8f28a6884f3d15df7170eda9d9c064b61f0b46c0","abstract_canon_sha256":"f508f0cc1dd2109570362c1638c802bc2522766c046d5a2394993d4b2ecc5fff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:40.436275Z","signature_b64":"HaeXu1kKOEx652aXXDP5pCGsDlw9fXbXP3SL4VZqRUy1/Sd96m1W6OOOrg7dbDPQg4SgTUiCEs8bXIRunNGOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30ec74298b3eaf3690567a5cceb7fd20020dfbb0401bf596e766e3c85253313a","last_reissued_at":"2026-05-20T01:05:40.435616Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:40.435616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic-Enriched Latent Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Chen, Fengyun Rao, Jing Liu, Jing Lyu, Jingyi Lu, Longteng Guo, Qixun Wang, Tianren Zhang, Tianrun Xu, Yuan Wang, Yue Sun","submitted_at":"2026-05-19T04:29:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19342","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/2605.19342/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":"2605.19342","created_at":"2026-05-20T01:05:40.435717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19342v1","created_at":"2026-05-20T01:05:40.435717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19342","created_at":"2026-05-20T01:05:40.435717+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDWHIKMLH2XT","created_at":"2026-05-20T01:05:40.435717+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDWHIKMLH2XTNECW","created_at":"2026-05-20T01:05:40.435717+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDWHIKML","created_at":"2026-05-20T01:05:40.435717+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/GDWHIKMLH2XTNECWPJOM5N75EA","json":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA.json","graph_json":"https://pith.science/api/pith-number/GDWHIKMLH2XTNECWPJOM5N75EA/graph.json","events_json":"https://pith.science/api/pith-number/GDWHIKMLH2XTNECWPJOM5N75EA/events.json","paper":"https://pith.science/paper/GDWHIKML"},"agent_actions":{"view_html":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA","download_json":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA.json","view_paper":"https://pith.science/paper/GDWHIKML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19342&json=true","fetch_graph":"https://pith.science/api/pith-number/GDWHIKMLH2XTNECWPJOM5N75EA/graph.json","fetch_events":"https://pith.science/api/pith-number/GDWHIKMLH2XTNECWPJOM5N75EA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA/action/storage_attestation","attest_author":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA/action/author_attestation","sign_citation":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA/action/citation_signature","submit_replication":"https://pith.science/pith/GDWHIKMLH2XTNECWPJOM5N75EA/action/replication_record"}},"created_at":"2026-05-20T01:05:40.435717+00:00","updated_at":"2026-05-20T01:05:40.435717+00:00"}