{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HFDRWFJ4TYVTZIH73CONIHD4NG","short_pith_number":"pith:HFDRWFJ4","schema_version":"1.0","canonical_sha256":"39471b153c9e2b3ca0ffd89cd41c7c69b772bbc85bfb04b56fdd71a7e5ccf52c","source":{"kind":"arxiv","id":"2501.12387","version":1},"attestation_state":"computed","paper":{"title":"Continuous 3D Perception Model with Persistent State","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alexei A. Efros, Angjoo Kanazawa, Qianqian Wang, Yifei Zhang","submitted_at":"2025-01-21T18:59:23Z","abstract_excerpt":"We present a unified framework capable of solving a broad range of 3D tasks. Our approach features a stateful recurrent model that continuously updates its state representation with each new observation. Given a stream of images, this evolving state can be used to generate metric-scale pointmaps (per-pixel 3D points) for each new input in an online fashion. These pointmaps reside within a common coordinate system, and can be accumulated into a coherent, dense scene reconstruction that updates as new images arrive. Our model, called CUT3R (Continuous Updating Transformer for 3D Reconstruction),"},"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":"2501.12387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T18:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"dcb717b72c364ed023cf45ab9b713f50c5a67d58990fcb8662cfe37e439ae0cb","abstract_canon_sha256":"cf6edc054a4f1cc4efdb317e1f635f911fc6046c201d719e4113063dda5cde91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:35.452106Z","signature_b64":"0F9uwn7ncu/ej2wXjtn2ktAJdAm9CVn8Of9vjq+6NveBmTbYW24/90dw+SGuQjCTnauw7+7EdEUtwFe9DCqoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39471b153c9e2b3ca0ffd89cd41c7c69b772bbc85bfb04b56fdd71a7e5ccf52c","last_reissued_at":"2026-07-05T10:03:35.451614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:35.451614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous 3D Perception Model with Persistent State","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alexei A. Efros, Angjoo Kanazawa, Qianqian Wang, Yifei Zhang","submitted_at":"2025-01-21T18:59:23Z","abstract_excerpt":"We present a unified framework capable of solving a broad range of 3D tasks. Our approach features a stateful recurrent model that continuously updates its state representation with each new observation. Given a stream of images, this evolving state can be used to generate metric-scale pointmaps (per-pixel 3D points) for each new input in an online fashion. These pointmaps reside within a common coordinate system, and can be accumulated into a coherent, dense scene reconstruction that updates as new images arrive. Our model, called CUT3R (Continuous Updating Transformer for 3D Reconstruction),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12387","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/2501.12387/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":"2501.12387","created_at":"2026-07-05T10:03:35.451674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12387v1","created_at":"2026-07-05T10:03:35.451674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12387","created_at":"2026-07-05T10:03:35.451674+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFDRWFJ4TYVT","created_at":"2026-07-05T10:03:35.451674+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFDRWFJ4TYVTZIH7","created_at":"2026-07-05T10:03:35.451674+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFDRWFJ4","created_at":"2026-07-05T10:03:35.451674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30855","citing_title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25308","citing_title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29505","citing_title":"ESAM++: Efficient Online 3D Perception on the Edge","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17015","citing_title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23889","citing_title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21862","citing_title":"EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12549","citing_title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19656","citing_title":"Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19539","citing_title":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20279","citing_title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2508.17588","citing_title":"HERO: Hierarchical Extrapolation and Refresh for Efficient World Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14751","citing_title":"Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16443","citing_title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05959","citing_title":"OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27222","citing_title":"HD-VGGT: High-Resolution Visual Geometry Transformer","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08371","citing_title":"PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09449","citing_title":"SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05207","citing_title":"Syn4D: A Multiview Synthetic 4D Dataset","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21921","citing_title":"Context Unrolling in Omni Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10593","citing_title":"MonoEM-GS: Monocular Expectation-Maximization Gaussian Splatting SLAM","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09862","citing_title":"FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07264","citing_title":"Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG","json":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG.json","graph_json":"https://pith.science/api/pith-number/HFDRWFJ4TYVTZIH73CONIHD4NG/graph.json","events_json":"https://pith.science/api/pith-number/HFDRWFJ4TYVTZIH73CONIHD4NG/events.json","paper":"https://pith.science/paper/HFDRWFJ4"},"agent_actions":{"view_html":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG","download_json":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG.json","view_paper":"https://pith.science/paper/HFDRWFJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12387&json=true","fetch_graph":"https://pith.science/api/pith-number/HFDRWFJ4TYVTZIH73CONIHD4NG/graph.json","fetch_events":"https://pith.science/api/pith-number/HFDRWFJ4TYVTZIH73CONIHD4NG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG/action/storage_attestation","attest_author":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG/action/author_attestation","sign_citation":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG/action/citation_signature","submit_replication":"https://pith.science/pith/HFDRWFJ4TYVTZIH73CONIHD4NG/action/replication_record"}},"created_at":"2026-07-05T10:03:35.451674+00:00","updated_at":"2026-07-05T10:03:35.451674+00:00"}