{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6PKVHVIPUDH67FT6XJPIVH7LP3","short_pith_number":"pith:6PKVHVIP","schema_version":"1.0","canonical_sha256":"f3d553d50fa0cfef967eba5e8a9feb7ee1cb425de5f9fd68044c91a0c9b0b173","source":{"kind":"arxiv","id":"2509.05296","version":1},"attestation_state":"computed","paper":{"title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Haoyi Zhu, Haoyu Guo, Jianjun Zhou, Junyi Chen, Tong He, Wenzheng Chang, Yang Zhou, Yifan Wang, Zizun Li","submitted_at":"2025-09-05T17:59:47Z","abstract_excerpt":"We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficient information exchange among frames within the window, thereby improving the quality of geometric predictions without large computation. In addition, we leverage a compact representation of cameras and maintain a global camera token pool, which enhances the reliability of camera"},"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":"2509.05296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T17:59:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9371876c3ef605e41efa12a5c0b90b7d69ea54d83c13d21daea826fe1da5d988","abstract_canon_sha256":"cf8ff9fdaf2e1bf96799fd9daedc24a5f935aefd9f5b3382aceae208a5899ab9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:39.048426Z","signature_b64":"dH7afiHHu3hyFpDorri4p+8GBv8s2YYr2Lya4k5F2vE9KmQDpbJry+h/4Aykm8Gjdz2+GySTTN1lsvdwwYgxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3d553d50fa0cfef967eba5e8a9feb7ee1cb425de5f9fd68044c91a0c9b0b173","last_reissued_at":"2026-07-05T12:05:39.047926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:39.047926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Haoyi Zhu, Haoyu Guo, Jianjun Zhou, Junyi Chen, Tong He, Wenzheng Chang, Yang Zhou, Yifan Wang, Zizun Li","submitted_at":"2025-09-05T17:59:47Z","abstract_excerpt":"We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficient information exchange among frames within the window, thereby improving the quality of geometric predictions without large computation. In addition, we leverage a compact representation of cameras and maintain a global camera token pool, which enhances the reliability of camera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05296","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/2509.05296/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":"2509.05296","created_at":"2026-07-05T12:05:39.047984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05296v1","created_at":"2026-07-05T12:05:39.047984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05296","created_at":"2026-07-05T12:05:39.047984+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PKVHVIPUDH6","created_at":"2026-07-05T12:05:39.047984+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PKVHVIPUDH67FT6","created_at":"2026-07-05T12:05:39.047984+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PKVHVIP","created_at":"2026-07-05T12:05:39.047984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05035","citing_title":"Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27367","citing_title":"SpatialBench: Is Your Spatial Foundation Model an All-Round Player?","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16981","citing_title":"Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07690","citing_title":"FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15178","citing_title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09644","citing_title":"Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3","json":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3.json","graph_json":"https://pith.science/api/pith-number/6PKVHVIPUDH67FT6XJPIVH7LP3/graph.json","events_json":"https://pith.science/api/pith-number/6PKVHVIPUDH67FT6XJPIVH7LP3/events.json","paper":"https://pith.science/paper/6PKVHVIP"},"agent_actions":{"view_html":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3","download_json":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3.json","view_paper":"https://pith.science/paper/6PKVHVIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05296&json=true","fetch_graph":"https://pith.science/api/pith-number/6PKVHVIPUDH67FT6XJPIVH7LP3/graph.json","fetch_events":"https://pith.science/api/pith-number/6PKVHVIPUDH67FT6XJPIVH7LP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3/action/storage_attestation","attest_author":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3/action/author_attestation","sign_citation":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3/action/citation_signature","submit_replication":"https://pith.science/pith/6PKVHVIPUDH67FT6XJPIVH7LP3/action/replication_record"}},"created_at":"2026-07-05T12:05:39.047984+00:00","updated_at":"2026-07-05T12:05:39.047984+00:00"}