{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DFX6G257KKH7VJYXQBFG7BL5UL","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":"1b47657cd2e11e59c13340683030738cf3f09cc2fded3088b90abca3a209aa41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:02Z","title_canon_sha256":"e0c6d2a18e9a74b9485e5442fae926cfa972f990e8e6f3ecbbbbac84722a1a9f"},"schema_version":"1.0","source":{"id":"2511.20644","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.20644","created_at":"2026-07-10T01:19:40Z"},{"alias_kind":"arxiv_version","alias_value":"2511.20644v2","created_at":"2026-07-10T01:19:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20644","created_at":"2026-07-10T01:19:40Z"},{"alias_kind":"pith_short_12","alias_value":"DFX6G257KKH7","created_at":"2026-07-10T01:19:40Z"},{"alias_kind":"pith_short_16","alias_value":"DFX6G257KKH7VJYX","created_at":"2026-07-10T01:19:40Z"},{"alias_kind":"pith_short_8","alias_value":"DFX6G257","created_at":"2026-07-10T01:19:40Z"}],"graph_snapshots":[{"event_id":"sha256:f7b08360aea667c92ee4224d6a31b429c944d87aad9e9b492aa7e4559fc5ca68","target":"graph","created_at":"2026-07-10T01:19:40Z","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/2511.20644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a semantic-geometric misalignment that prevents consistent 3D understanding, and the absence of persistent memory to retain 3D representation and understanding across frames. To address these limitations, we present VLM$^2$, a Vision-Language Model with persistent Memory for spatial reasoning with a view-consistent, 3D-aware representation purely from 2D videos. Speci","authors_text":"Chen Wang, Cherie Ho, Shaoshu Su, Taimeng Fu, Yi Du, Zuntao Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:02Z","title":"Vision-Language Memory for Spatial Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20644","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":"sha256:822ccb2231a74478cfa804bfb2bf5c55ef488ebcb6af2375391073ca31f0ff12","target":"record","created_at":"2026-07-10T01:19:40Z","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":"1b47657cd2e11e59c13340683030738cf3f09cc2fded3088b90abca3a209aa41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:02Z","title_canon_sha256":"e0c6d2a18e9a74b9485e5442fae926cfa972f990e8e6f3ecbbbbac84722a1a9f"},"schema_version":"1.0","source":{"id":"2511.20644","kind":"arxiv","version":2}},"canonical_sha256":"196fe36bbf528ffaa717804a6f857da2de395b2d569d005e83b88d58bab01d82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"196fe36bbf528ffaa717804a6f857da2de395b2d569d005e83b88d58bab01d82","first_computed_at":"2026-07-10T01:19:40.854650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:40.854650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qql8P4BiTzm+zp0rugfSveqGiCsWr0W7s1YKNC6nSmp+0isaby/7OZ1X0ITt/GLguTsYoPkDFqagsCprASU4BQ==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:40.855204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.20644","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:822ccb2231a74478cfa804bfb2bf5c55ef488ebcb6af2375391073ca31f0ff12","sha256:f7b08360aea667c92ee4224d6a31b429c944d87aad9e9b492aa7e4559fc5ca68"],"state_sha256":"b144c3028baf9aed682c28bf161da001eba67cf1a8bcd8f043669203137f756c"}