{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CQZNRNRNKOVFDEHTOFSPIYV4NW","short_pith_number":"pith:CQZNRNRN","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"},"canonical_sha256":"1432d8b62d53aa5190f37164f462bc6dba32d856b3ce508fc12ff40f933f6a22","source":{"kind":"arxiv","id":"2604.22409","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.22409","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.22409v2","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.22409","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"CQZNRNRNKOVF","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"CQZNRNRNKOVFDEHT","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"CQZNRNRN","created_at":"2026-05-29T01:05:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CQZNRNRNKOVFDEHTOFSPIYV4NW","target":"record","payload":{"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"},"canonical_sha256":"1432d8b62d53aa5190f37164f462bc6dba32d856b3ce508fc12ff40f933f6a22","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"},"source_kind":"arxiv","source_id":"2604.22409","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/6ps8H/VHKpMeUS7M0lLxGBPIs2JQzeDbA4HkArjV5D/l4wgX90emWl1ULxPdaWQHXIy/UUGesfLLTQXw3QgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:13:51.129394Z"},"content_sha256":"d6d52eba22f0a625f168cf0e326adbcd9cf4bc2680cf34c92b67fe337900bb28","schema_version":"1.0","event_id":"sha256:d6d52eba22f0a625f168cf0e326adbcd9cf4bc2680cf34c92b67fe337900bb28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CQZNRNRNKOVFDEHTOFSPIYV4NW","target":"graph","payload":{"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"},"verdict_id":"cdf74359-034b-4e8a-bb2b-161706349604"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lgb66D6TS+pwGeYD8Zif2Z0QTs6bk7X4Gro/2HdSsTmR5uoJm+fV14cCwgqlLxsGlZA+djIHgaPhZOz81vgKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:13:51.129874Z"},"content_sha256":"e033f58df87f36073ec4a5c05415733b8c6128d248b5a2a74451c4a8eeb13e2b","schema_version":"1.0","event_id":"sha256:e033f58df87f36073ec4a5c05415733b8c6128d248b5a2a74451c4a8eeb13e2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/bundle.json","state_url":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T18:13:51Z","links":{"resolver":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW","bundle":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/bundle.json","state":"https://pith.science/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQZNRNRNKOVFDEHTOFSPIYV4NW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CQZNRNRNKOVFDEHTOFSPIYV4NW","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":"5c6819cb01593edb325e8f0a29987e33fb3df71f7068b8f575f68e0331ad0835","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-24T10:06:41Z","title_canon_sha256":"88552223190eb8eab4e5a62e0269a9b12c58aef3119a7d9d3c437a1f48ed538f"},"schema_version":"1.0","source":{"id":"2604.22409","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.22409","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.22409v2","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.22409","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"CQZNRNRNKOVF","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"CQZNRNRNKOVFDEHT","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"CQZNRNRN","created_at":"2026-05-29T01:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:e033f58df87f36073ec4a5c05415733b8c6128d248b5a2a74451c4a8eeb13e2b","target":"graph","created_at":"2026-05-29T01:05:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Vision-language models maintain spatial beliefs only when given text histories and collapse without them in changing environments."}],"snapshot_sha256":"8097cc1a1a6efda0760862e192342df6de894f45cbfe100507443f4f6d405811"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2604.22409/integrity.json","findings":[],"snapshot_sha256":"67bf1259c6a25510706a17a3d92f5f87875235c59a524d485cd6e2c8addbc6e4","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chih-Ting Liao, Chunlei Meng, Tianyang Wang, Weilin Zhou, Xin Cao, Xi Xiao, Xu Zheng, Yitong Qiao, Zhangquan Chen","cross_cats":[],"headline":"Vision-language models maintain spatial beliefs only when given text histories and collapse without them in changing environments.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-24T10:06:41Z","title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.22409","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T12:29:34.022871Z","id":"cdf74359-034b-4e8a-bb2b-161706349604","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Vision-language models maintain spatial beliefs only when given text histories and collapse without them in changing environments.","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.","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."}},"verdict_id":"cdf74359-034b-4e8a-bb2b-161706349604"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d6d52eba22f0a625f168cf0e326adbcd9cf4bc2680cf34c92b67fe337900bb28","target":"record","created_at":"2026-05-29T01:05:10Z","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":"5c6819cb01593edb325e8f0a29987e33fb3df71f7068b8f575f68e0331ad0835","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-24T10:06:41Z","title_canon_sha256":"88552223190eb8eab4e5a62e0269a9b12c58aef3119a7d9d3c437a1f48ed538f"},"schema_version":"1.0","source":{"id":"2604.22409","kind":"arxiv","version":2}},"canonical_sha256":"1432d8b62d53aa5190f37164f462bc6dba32d856b3ce508fc12ff40f933f6a22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1432d8b62d53aa5190f37164f462bc6dba32d856b3ce508fc12ff40f933f6a22","first_computed_at":"2026-05-29T01:05:10.479074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:10.479074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VoaLe1dC1j08FEPpipvP9WJwixRaCZPNDSxBm0iJ/V+RBJhE/L+f+ssxPZ32q9s1P3rxA2724M5tZPu2QEncDA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:10.479715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.22409","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6d52eba22f0a625f168cf0e326adbcd9cf4bc2680cf34c92b67fe337900bb28","sha256:e033f58df87f36073ec4a5c05415733b8c6128d248b5a2a74451c4a8eeb13e2b"],"state_sha256":"27a5e8e600b24e5b6fe83af5846bb8adf20cc366f939c7d3aa397a1ceecf33a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dz/RntgMCrI7h1GlfOdv6xvFFLk2QnLJ3Xa+PFQzvJssoP2UD7w3PmNWEuo7grSp5NPO5nglgVhsXlndjPbKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T18:13:51.132078Z","bundle_sha256":"761a995a2e5b277b4f2464bd23597d6ad74758ef001115c5a7052a283eeb78a5"}}