{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQZNRNRNKOVFDEHTOFSPIYV4NW","short_pith_number":"pith:CQZNRNRN","schema_version":"1.0","canonical_sha256":"1432d8b62d53aa5190f37164f462bc6dba32d856b3ce508fc12ff40f933f6a22","source":{"kind":"arxiv","id":"2604.22409","version":2},"attestation_state":"computed","paper":{"title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Vision-language models maintain spatial beliefs only when given text histories and collapse without them in changing environments.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chih-Ting Liao, Chunlei Meng, Tianyang Wang, Weilin Zhou, Xin Cao, Xi Xiao, Xu Zheng, Yitong Qiao, Zhangquan Chen","submitted_at":"2026-04-24T10:06:41Z","abstract_excerpt":"Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric observations under environmental change. We introduce SpaMEM (Spatial Memory from Action Sequences), a large-scale diagnostic benchmark that isolates the mechanics of spatial belief evolution via action-conditioned scene transformations (spawn, place, remove) over long interaction horizons. SpaMEM is built on a physically grounded dataset with 10,601,392 high-fideli"},"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":"2604.22409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-24T10:06:41Z","cross_cats_sorted":[],"title_canon_sha256":"88552223190eb8eab4e5a62e0269a9b12c58aef3119a7d9d3c437a1f48ed538f","abstract_canon_sha256":"5c6819cb01593edb325e8f0a29987e33fb3df71f7068b8f575f68e0331ad0835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:10.479715Z","signature_b64":"VoaLe1dC1j08FEPpipvP9WJwixRaCZPNDSxBm0iJ/V+RBJhE/L+f+ssxPZ32q9s1P3rxA2724M5tZPu2QEncDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1432d8b62d53aa5190f37164f462bc6dba32d856b3ce508fc12ff40f933f6a22","last_reissued_at":"2026-05-29T01:05:10.479074Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:10.479074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Vision-language models maintain spatial beliefs only when given text histories and collapse without them in changing environments.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chih-Ting Liao, Chunlei Meng, Tianyang Wang, Weilin Zhou, Xin Cao, Xi Xiao, Xu Zheng, Yitong Qiao, Zhangquan Chen","submitted_at":"2026-04-24T10:06:41Z","abstract_excerpt":"Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric observations under environmental change. We introduce SpaMEM (Spatial Memory from Action Sequences), a large-scale diagnostic benchmark that isolates the mechanics of spatial belief evolution via action-conditioned scene transformations (spawn, place, remove) over long interaction horizons. SpaMEM is built on a physically grounded dataset with 10,601,392 high-fideli"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Benchmarking representative open-source VLM families reveals a consistent stacked bottleneck: coordinate-consistent grounding remains a hard ceiling, and the sharp collapse from Level 2 to Level 3 exposes a pronounced symbolic scaffolding dependency, where models succeed with text-based bookkeeping but struggle to sustain robust visual memory.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the procedurally generated houses, action sequences (spawn, place, remove), and three-level task hierarchy isolate spatial belief evolution without introducing simulation artifacts or task-specific biases that do not appear in real embodied settings.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SpaMEM benchmark shows multimodal LLMs succeed at spatial tasks with text histories but sharply fail at long-horizon belief maintenance from raw visual streams alone.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Vision-language models maintain spatial beliefs only when given text histories and collapse without them in changing environments.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8097cc1a1a6efda0760862e192342df6de894f45cbfe100507443f4f6d405811"},"source":{"id":"2604.22409","kind":"arxiv","version":2},"verdict":{"id":"cdf74359-034b-4e8a-bb2b-161706349604","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T12:29:34.022871Z","strongest_claim":"Benchmarking representative open-source VLM families reveals a consistent stacked bottleneck: coordinate-consistent grounding remains a hard ceiling, and the sharp collapse from Level 2 to Level 3 exposes a pronounced symbolic scaffolding dependency, where models succeed with text-based bookkeeping but struggle to sustain robust visual memory.","one_line_summary":"SpaMEM benchmark shows multimodal LLMs succeed at spatial tasks with text histories but sharply fail at long-horizon belief maintenance from raw visual streams alone.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the procedurally generated houses, action sequences (spawn, place, remove), and three-level task hierarchy isolate spatial belief evolution without introducing simulation artifacts or task-specific biases that do not appear in real embodied settings.","pith_extraction_headline":"Vision-language models maintain spatial beliefs only when given text histories and collapse without them in changing environments."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.22409/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T10:40:36.394346Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T00:03:40.140806Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"67bf1259c6a25510706a17a3d92f5f87875235c59a524d485cd6e2c8addbc6e4"},"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":"2604.22409","created_at":"2026-05-29T01:05:10.479151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.22409v2","created_at":"2026-05-29T01:05:10.479151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.22409","created_at":"2026-05-29T01:05:10.479151+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQZNRNRNKOVF","created_at":"2026-05-29T01:05:10.479151+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQZNRNRNKOVFDEHT","created_at":"2026-05-29T01:05:10.479151+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQZNRNRN","created_at":"2026-05-29T01:05:10.479151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.28277","citing_title":"Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW","json":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW.json","graph_json":"https://pith.science/api/pith-number/CQZNRNRNKOVFDEHTOFSPIYV4NW/graph.json","events_json":"https://pith.science/api/pith-number/CQZNRNRNKOVFDEHTOFSPIYV4NW/events.json","paper":"https://pith.science/paper/CQZNRNRN"},"agent_actions":{"view_html":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW","download_json":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW.json","view_paper":"https://pith.science/paper/CQZNRNRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.22409&json=true","fetch_graph":"https://pith.science/api/pith-number/CQZNRNRNKOVFDEHTOFSPIYV4NW/graph.json","fetch_events":"https://pith.science/api/pith-number/CQZNRNRNKOVFDEHTOFSPIYV4NW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/action/storage_attestation","attest_author":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/action/author_attestation","sign_citation":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/action/citation_signature","submit_replication":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/action/replication_record"}},"created_at":"2026-05-29T01:05:10.479151+00:00","updated_at":"2026-05-29T01:05:10.479151+00:00"}