{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7LNV4V7UQONARXQOD3R3QMSPS5","short_pith_number":"pith:7LNV4V7U","canonical_record":{"source":{"id":"2509.02359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T14:22:43Z","cross_cats_sorted":[],"title_canon_sha256":"5d7a7f2c79b0ab49d583ca5fd227249dc25cd9a1225873b8ede3c7e28851a9fe","abstract_canon_sha256":"7f98d856c70ab3c6eac08edd50af1022dda7506160d5cfedf3a0c3f66a0d3b2b"},"schema_version":"1.0"},"canonical_sha256":"fadb5e57f4839a08de0e1ee3b8324f97705273a566a941d20cc988764a278ac8","source":{"kind":"arxiv","id":"2509.02359","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02359","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02359v1","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02359","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"7LNV4V7UQONA","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"7LNV4V7UQONARXQO","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"7LNV4V7U","created_at":"2026-07-05T12:03:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7LNV4V7UQONARXQOD3R3QMSPS5","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T14:22:43Z","cross_cats_sorted":[],"title_canon_sha256":"5d7a7f2c79b0ab49d583ca5fd227249dc25cd9a1225873b8ede3c7e28851a9fe","abstract_canon_sha256":"7f98d856c70ab3c6eac08edd50af1022dda7506160d5cfedf3a0c3f66a0d3b2b"},"schema_version":"1.0"},"canonical_sha256":"fadb5e57f4839a08de0e1ee3b8324f97705273a566a941d20cc988764a278ac8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:37.072469Z","signature_b64":"kvYNpsA4Rb/MRe3TnzFjGDCeK3PaZ3Il23toSyYACOrYANdQgIxRs7kuIZlAgs1U59xxfv36gYJumXYdfKUZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fadb5e57f4839a08de0e1ee3b8324f97705273a566a941d20cc988764a278ac8","last_reissued_at":"2026-07-05T12:03:37.071820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:37.071820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02359","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wf2fErAvUFG5rbKXGiAa3Wk4T3IP0ACmZ9N3YyGriI8VygT/Abep3BZO29ifGvqDkQxMGzGBYOrx98CfjhJ4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:10:55.247357Z"},"content_sha256":"d5050c5c04d8d74b0f867f0f19f23dd88e8200cf708923deee91527c236afed0","schema_version":"1.0","event_id":"sha256:d5050c5c04d8d74b0f867f0f19f23dd88e8200cf708923deee91527c236afed0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7LNV4V7UQONARXQOD3R3QMSPS5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Helu Zhi, Jiajun Zhang, Jingjing Huang, Shuo Ren, Wang Xu, Wanyue Zhang, Yangbin Xu, Yibin Huang","submitted_at":"2025-09-02T14:22:43Z","abstract_excerpt":"Spatial understanding is essential for Multimodal Large Language Models (MLLMs) to support perception, reasoning, and planning in embodied environments. Despite recent progress, existing studies reveal that MLLMs still struggle with spatial understanding. However, existing research lacks a comprehensive and systematic evaluation of these limitations, often restricted to isolated scenarios, such as single-view or video. In this work, we present a systematic analysis of spatial understanding from both data and architectural perspectives across three representative scenarios: single-view, multi-v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02359","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/2509.02359/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JGRaCJnGBNDI4r/RELuUuKfBoy/Px5zh06z2QG3DqEP1ht0YDU8NNOzEpFBGGZVibzcvJsadVw2IWmgr/pkPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:10:55.248268Z"},"content_sha256":"1ce14f0159fba5e92b6781809bc265bc44703c2391c537a8acc2543365efd39d","schema_version":"1.0","event_id":"sha256:1ce14f0159fba5e92b6781809bc265bc44703c2391c537a8acc2543365efd39d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7LNV4V7UQONARXQOD3R3QMSPS5/bundle.json","state_url":"https://pith.science/pith/7LNV4V7UQONARXQOD3R3QMSPS5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7LNV4V7UQONARXQOD3R3QMSPS5/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":"2026-08-06T02:10:55Z","links":{"resolver":"https://pith.science/pith/7LNV4V7UQONARXQOD3R3QMSPS5","bundle":"https://pith.science/pith/7LNV4V7UQONARXQOD3R3QMSPS5/bundle.json","state":"https://pith.science/pith/7LNV4V7UQONARXQOD3R3QMSPS5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7LNV4V7UQONARXQOD3R3QMSPS5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7LNV4V7UQONARXQOD3R3QMSPS5","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":"7f98d856c70ab3c6eac08edd50af1022dda7506160d5cfedf3a0c3f66a0d3b2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T14:22:43Z","title_canon_sha256":"5d7a7f2c79b0ab49d583ca5fd227249dc25cd9a1225873b8ede3c7e28851a9fe"},"schema_version":"1.0","source":{"id":"2509.02359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02359","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02359v1","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02359","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"7LNV4V7UQONA","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"7LNV4V7UQONARXQO","created_at":"2026-07-05T12:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"7LNV4V7U","created_at":"2026-07-05T12:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:1ce14f0159fba5e92b6781809bc265bc44703c2391c537a8acc2543365efd39d","target":"graph","created_at":"2026-07-05T12:03:37Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.02359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial understanding is essential for Multimodal Large Language Models (MLLMs) to support perception, reasoning, and planning in embodied environments. Despite recent progress, existing studies reveal that MLLMs still struggle with spatial understanding. However, existing research lacks a comprehensive and systematic evaluation of these limitations, often restricted to isolated scenarios, such as single-view or video. In this work, we present a systematic analysis of spatial understanding from both data and architectural perspectives across three representative scenarios: single-view, multi-v","authors_text":"Helu Zhi, Jiajun Zhang, Jingjing Huang, Shuo Ren, Wang Xu, Wanyue Zhang, Yangbin Xu, Yibin Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T14:22:43Z","title":"Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02359","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d5050c5c04d8d74b0f867f0f19f23dd88e8200cf708923deee91527c236afed0","target":"record","created_at":"2026-07-05T12:03:37Z","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":"7f98d856c70ab3c6eac08edd50af1022dda7506160d5cfedf3a0c3f66a0d3b2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T14:22:43Z","title_canon_sha256":"5d7a7f2c79b0ab49d583ca5fd227249dc25cd9a1225873b8ede3c7e28851a9fe"},"schema_version":"1.0","source":{"id":"2509.02359","kind":"arxiv","version":1}},"canonical_sha256":"fadb5e57f4839a08de0e1ee3b8324f97705273a566a941d20cc988764a278ac8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fadb5e57f4839a08de0e1ee3b8324f97705273a566a941d20cc988764a278ac8","first_computed_at":"2026-07-05T12:03:37.071820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:37.071820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kvYNpsA4Rb/MRe3TnzFjGDCeK3PaZ3Il23toSyYACOrYANdQgIxRs7kuIZlAgs1U59xxfv36gYJumXYdfKUZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:37.072469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5050c5c04d8d74b0f867f0f19f23dd88e8200cf708923deee91527c236afed0","sha256:1ce14f0159fba5e92b6781809bc265bc44703c2391c537a8acc2543365efd39d"],"state_sha256":"f1efee655b85a259431c4d09919386efab8488fcd90db09cb779f0fad4e3c112"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4HIvB9d8YMtX/xX16n0IK3AFAL0IbElCpXiCkm6NINXGnai3wBc95X0grwPHbM+ByrCNe2jh7xer1wcFM6bgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:10:55.255585Z","bundle_sha256":"76f1fd6807d77570d82b0c98ccab560a4b775081660a56f1a9940a4abb02dbaf"}}