{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A3YCGTKUM62USIOH5G3CJ4VO5V","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":"df65beb600ca217ed613750354e1297030eec6c320111def284e02aa815e47c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-21T13:50:26Z","title_canon_sha256":"35d1fb434658121a546e6d79154fa1595262425a069ffbd30c1928db67a144db"},"schema_version":"1.0","source":{"id":"2512.18735","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.18735","created_at":"2026-05-26T02:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2512.18735v2","created_at":"2026-05-26T02:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.18735","created_at":"2026-05-26T02:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"A3YCGTKUM62U","created_at":"2026-05-26T02:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"A3YCGTKUM62USIOH","created_at":"2026-05-26T02:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"A3YCGTKU","created_at":"2026-05-26T02:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:8a4be79df643d4f546584bcd1275f90554214808eae0283aaf33c07612b0968e","target":"graph","created_at":"2026-05-26T02:05:05Z","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/2512.18735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern Large Multimodal Models (LMMs) have demonstrated extraordinary ability in static image and single-state spatial-temporal understanding. However, their capacity to comprehend the dynamic changes of objects within a shared spatial context between two distinct video observations, remains largely unexplored. This ability to reason about transformations within a consistent environment is particularly crucial for advancements in the field of spatial intelligence. In this paper, we introduce $M^3-Verse$, a Multi-Modal, Multi-State, Multi-Dimensional benchmark, to formally evaluate this capabil","authors_text":"Bocheng Hu, Ciyun Zhao, Gaoang Wang, Jiaao Wu, Jian Zhang, Jie Cao, Junchen He, Kewei Wei, Mingyu Jia, Weili Xu, Wubing Xia, Xiaohan Chen, Ye Sun, Yizhi Li, Zhengxi Lu, Zhonghan Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-21T13:50:26Z","title":"$M^3-Verse$: A \"Spot the Difference\" Challenge for Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.18735","kind":"arxiv","version":2},"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:e771088cb0e44dc9cd90052549c624e7b7e34b510694c3d95a0baee1df214b41","target":"record","created_at":"2026-05-26T02:05:05Z","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":"df65beb600ca217ed613750354e1297030eec6c320111def284e02aa815e47c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-21T13:50:26Z","title_canon_sha256":"35d1fb434658121a546e6d79154fa1595262425a069ffbd30c1928db67a144db"},"schema_version":"1.0","source":{"id":"2512.18735","kind":"arxiv","version":2}},"canonical_sha256":"06f0234d5467b54921c7e9b624f2aeed569d33cbf5f16cfa0350fb7c7efe752f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06f0234d5467b54921c7e9b624f2aeed569d33cbf5f16cfa0350fb7c7efe752f","first_computed_at":"2026-05-26T02:05:05.109405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:05.109405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sjCnTmZJAznICKD91/rOOd1arRbhEs0ez3ZANKHrjiLe8L5wt91dEw4oEzUrq1VLnzWtNlAUUwYYYnvrweC4BQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:05.109991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.18735","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e771088cb0e44dc9cd90052549c624e7b7e34b510694c3d95a0baee1df214b41","sha256:8a4be79df643d4f546584bcd1275f90554214808eae0283aaf33c07612b0968e"],"state_sha256":"db709fd884b24d64b8eedd7e4ac3232947ea48a1c9ad34de650978ad0b429d81"}