{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KFROX5E2WCNAEALVWCDEVSFPTS","short_pith_number":"pith:KFROX5E2","schema_version":"1.0","canonical_sha256":"5162ebf49ab09a020175b0864ac8af9c8a369d3edc087d92857f301068efcc33","source":{"kind":"arxiv","id":"2606.23717","version":1},"attestation_state":"computed","paper":{"title":"SpaCE: Rethinking Spatial Capacity and Generalization in Multi-Frame Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Alberlucia Rafael Soarez, Alejandro Torres, Camila Ferreira, Mariana Costa","submitted_at":"2026-06-16T20:47:15Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have achieved remarkable empirical progress in spatial understanding through large-scale training on spatial visual question answering datasets. However, the theoretical foundations of multi-frame spatial reasoning remain entirely unexplored. We present SpaCE, a rigorous theoretical framework that characterizes the spatial reasoning capacity, sample complexity, and generalization guarantees of MLLMs operating on multi-frame inputs. We establish four main results. First, we prove an information-theoretic upper bound on spatial reasoning accuracy in term"},"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":"2606.23717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2026-06-16T20:47:15Z","cross_cats_sorted":[],"title_canon_sha256":"1e461f621663294274325a1190db29601fc246eae0ece6656c45100f1b8c43f1","abstract_canon_sha256":"28ab948b6a3ad148b4badfaf66a2c5c78eae47310a949ba5d938329edefc7df0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:24.172940Z","signature_b64":"Ugog46h+Uqz1qis3zO4WAvtFeZo4YXRjcsmks3iesgcaAL8yUCaqabge/5O00QP+3bBgaiA44Uih/GX15UFYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5162ebf49ab09a020175b0864ac8af9c8a369d3edc087d92857f301068efcc33","last_reissued_at":"2026-06-24T00:14:24.172488Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:24.172488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpaCE: Rethinking Spatial Capacity and Generalization in Multi-Frame Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Alberlucia Rafael Soarez, Alejandro Torres, Camila Ferreira, Mariana Costa","submitted_at":"2026-06-16T20:47:15Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have achieved remarkable empirical progress in spatial understanding through large-scale training on spatial visual question answering datasets. However, the theoretical foundations of multi-frame spatial reasoning remain entirely unexplored. We present SpaCE, a rigorous theoretical framework that characterizes the spatial reasoning capacity, sample complexity, and generalization guarantees of MLLMs operating on multi-frame inputs. We establish four main results. First, we prove an information-theoretic upper bound on spatial reasoning accuracy in term"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23717","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/2606.23717/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":"2606.23717","created_at":"2026-06-24T00:14:24.172553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23717v1","created_at":"2026-06-24T00:14:24.172553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23717","created_at":"2026-06-24T00:14:24.172553+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFROX5E2WCNA","created_at":"2026-06-24T00:14:24.172553+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFROX5E2WCNAEALV","created_at":"2026-06-24T00:14:24.172553+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFROX5E2","created_at":"2026-06-24T00:14:24.172553+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/KFROX5E2WCNAEALVWCDEVSFPTS","json":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS.json","graph_json":"https://pith.science/api/pith-number/KFROX5E2WCNAEALVWCDEVSFPTS/graph.json","events_json":"https://pith.science/api/pith-number/KFROX5E2WCNAEALVWCDEVSFPTS/events.json","paper":"https://pith.science/paper/KFROX5E2"},"agent_actions":{"view_html":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS","download_json":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS.json","view_paper":"https://pith.science/paper/KFROX5E2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23717&json=true","fetch_graph":"https://pith.science/api/pith-number/KFROX5E2WCNAEALVWCDEVSFPTS/graph.json","fetch_events":"https://pith.science/api/pith-number/KFROX5E2WCNAEALVWCDEVSFPTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS/action/storage_attestation","attest_author":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS/action/author_attestation","sign_citation":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS/action/citation_signature","submit_replication":"https://pith.science/pith/KFROX5E2WCNAEALVWCDEVSFPTS/action/replication_record"}},"created_at":"2026-06-24T00:14:24.172553+00:00","updated_at":"2026-06-24T00:14:24.172553+00:00"}