{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CICVJ6DV4BBGLH2GC3DFWBDPM6","short_pith_number":"pith:CICVJ6DV","schema_version":"1.0","canonical_sha256":"120554f875e042659f4616c65b046f67828954d6f9b219393bc445658e503812","source":{"kind":"arxiv","id":"2606.00963","version":1},"attestation_state":"computed","paper":{"title":"Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chieh Hubert Lin, Jixuan He, Ming-Hsuan Yang, Xueting Li","submitted_at":"2026-05-31T02:36:57Z","abstract_excerpt":"Vision-Language Models (VLMs) exhibit emerging spatial reasoning capabilities, yet they remain unreliable on tasks requiring precise spatial understanding, such as viewpoint reasoning, directional comparison, and distance estimation. In multi-view images and monocular videos, relevant spatial cues are often sparse and distributed across redundant observations, making them difficult to organize and exploit. Reconstruction-based Vision Foundation Models (VFMs) offer a natural way to aggregate such observations into explicit spatial memory, such as point clouds. However, simply exposing reconstru"},"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":"2606.00963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T02:36:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c5dc10c29dcc89f50c2b4a34478660cd9f3e56526ee09cb49b7d03305a3a7967","abstract_canon_sha256":"45f4259f57b0f9659336e5f4c97d340c32bc2eb8ce4c6f10b3efcebe204d52ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:10.557437Z","signature_b64":"JU0KeiJtBNyWe/Kcqv50K5R1o2bDIc5xSTA/HsnRSMYvAMSShhhGBFCv8WPSuazIw/ymH9ysNbqcf6N15b7vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"120554f875e042659f4616c65b046f67828954d6f9b219393bc445658e503812","last_reissued_at":"2026-06-02T01:04:10.556934Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:10.556934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chieh Hubert Lin, Jixuan He, Ming-Hsuan Yang, Xueting Li","submitted_at":"2026-05-31T02:36:57Z","abstract_excerpt":"Vision-Language Models (VLMs) exhibit emerging spatial reasoning capabilities, yet they remain unreliable on tasks requiring precise spatial understanding, such as viewpoint reasoning, directional comparison, and distance estimation. In multi-view images and monocular videos, relevant spatial cues are often sparse and distributed across redundant observations, making them difficult to organize and exploit. Reconstruction-based Vision Foundation Models (VFMs) offer a natural way to aggregate such observations into explicit spatial memory, such as point clouds. However, simply exposing reconstru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00963","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/2606.00963/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.00963","created_at":"2026-06-02T01:04:10.557012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00963v1","created_at":"2026-06-02T01:04:10.557012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00963","created_at":"2026-06-02T01:04:10.557012+00:00"},{"alias_kind":"pith_short_12","alias_value":"CICVJ6DV4BBG","created_at":"2026-06-02T01:04:10.557012+00:00"},{"alias_kind":"pith_short_16","alias_value":"CICVJ6DV4BBGLH2G","created_at":"2026-06-02T01:04:10.557012+00:00"},{"alias_kind":"pith_short_8","alias_value":"CICVJ6DV","created_at":"2026-06-02T01:04:10.557012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6","json":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6.json","graph_json":"https://pith.science/api/pith-number/CICVJ6DV4BBGLH2GC3DFWBDPM6/graph.json","events_json":"https://pith.science/api/pith-number/CICVJ6DV4BBGLH2GC3DFWBDPM6/events.json","paper":"https://pith.science/paper/CICVJ6DV"},"agent_actions":{"view_html":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6","download_json":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6.json","view_paper":"https://pith.science/paper/CICVJ6DV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00963&json=true","fetch_graph":"https://pith.science/api/pith-number/CICVJ6DV4BBGLH2GC3DFWBDPM6/graph.json","fetch_events":"https://pith.science/api/pith-number/CICVJ6DV4BBGLH2GC3DFWBDPM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6/action/storage_attestation","attest_author":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6/action/author_attestation","sign_citation":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6/action/citation_signature","submit_replication":"https://pith.science/pith/CICVJ6DV4BBGLH2GC3DFWBDPM6/action/replication_record"}},"created_at":"2026-06-02T01:04:10.557012+00:00","updated_at":"2026-06-02T01:04:10.557012+00:00"}