{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IA2KQPQIENUOW5RKEIMLLCC6EU","short_pith_number":"pith:IA2KQPQI","schema_version":"1.0","canonical_sha256":"4034a83e082368eb762a2218b5885e2512057e1ed0025beebf353e71cf0f5281","source":{"kind":"arxiv","id":"2608.14138","version":1},"attestation_state":"computed","paper":{"title":"SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feifei Shao, Jianhua Li, Jinsheng Quan, Kewang Deng, Lei Yang, Quan Wang, Siyi Xie, Xuanke Shi, Yawei Luo, Zukai Chen","submitted_at":"2026-08-14T09:44:37Z","abstract_excerpt":"Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations. Existing approaches typically address these capabilities separately using task-specific architectures or external geometric modules, limiting knowledge transfer among complementary representations of the same physical scene. We introduce SPARGen, a unified multimodal framework that casts 3D reconstruction, dense correspondence, and spatial reasoning as instruction-conditioned generation tasks. SPARGen serializes compact structured "},"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":"2608.14138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-14T09:44:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3ba0fb63825c04c2ac197db618c4bee3951c1c132159ffad912f01fdc89776a","abstract_canon_sha256":"efec13c512d675da2708922e44496c8bcb72e1aab25841015c11317257c1308b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-17T01:12:09.830557Z","signature_b64":"Rwv3q1Tqw9PQ1/UBJJkBmQ6TQTJBOVP2EAazaAFufbLi6yuveaWL5cEq05ZdsXdqHeJfhlxkFEp6u6GRyMZoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4034a83e082368eb762a2218b5885e2512057e1ed0025beebf353e71cf0f5281","last_reissued_at":"2026-08-17T01:12:09.828323Z","signature_status":"signed_v1","first_computed_at":"2026-08-17T01:12:09.828323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feifei Shao, Jianhua Li, Jinsheng Quan, Kewang Deng, Lei Yang, Quan Wang, Siyi Xie, Xuanke Shi, Yawei Luo, Zukai Chen","submitted_at":"2026-08-14T09:44:37Z","abstract_excerpt":"Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations. Existing approaches typically address these capabilities separately using task-specific architectures or external geometric modules, limiting knowledge transfer among complementary representations of the same physical scene. We introduce SPARGen, a unified multimodal framework that casts 3D reconstruction, dense correspondence, and spatial reasoning as instruction-conditioned generation tasks. SPARGen serializes compact structured "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.14138","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/2608.14138/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":"2608.14138","created_at":"2026-08-17T01:12:09.828975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.14138v1","created_at":"2026-08-17T01:12:09.828975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.14138","created_at":"2026-08-17T01:12:09.828975+00:00"},{"alias_kind":"pith_short_12","alias_value":"IA2KQPQIENUO","created_at":"2026-08-17T01:12:09.828975+00:00"},{"alias_kind":"pith_short_16","alias_value":"IA2KQPQIENUOW5RK","created_at":"2026-08-17T01:12:09.828975+00:00"},{"alias_kind":"pith_short_8","alias_value":"IA2KQPQI","created_at":"2026-08-17T01:12:09.828975+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/IA2KQPQIENUOW5RKEIMLLCC6EU","json":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU.json","graph_json":"https://pith.science/api/pith-number/IA2KQPQIENUOW5RKEIMLLCC6EU/graph.json","events_json":"https://pith.science/api/pith-number/IA2KQPQIENUOW5RKEIMLLCC6EU/events.json","paper":"https://pith.science/paper/IA2KQPQI"},"agent_actions":{"view_html":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU","download_json":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU.json","view_paper":"https://pith.science/paper/IA2KQPQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.14138&json=true","fetch_graph":"https://pith.science/api/pith-number/IA2KQPQIENUOW5RKEIMLLCC6EU/graph.json","fetch_events":"https://pith.science/api/pith-number/IA2KQPQIENUOW5RKEIMLLCC6EU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU/action/storage_attestation","attest_author":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU/action/author_attestation","sign_citation":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU/action/citation_signature","submit_replication":"https://pith.science/pith/IA2KQPQIENUOW5RKEIMLLCC6EU/action/replication_record"}},"created_at":"2026-08-17T01:12:09.828975+00:00","updated_at":"2026-08-17T01:12:09.828975+00:00"}