{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2SCC76VPRCDRTKNKL7YNUBTNA7","short_pith_number":"pith:2SCC76VP","schema_version":"1.0","canonical_sha256":"d4842ffaaf888719a9aa5ff0da066d07d381ade04260e84c07bc397ee7114083","source":{"kind":"arxiv","id":"2508.03252","version":2},"attestation_state":"computed","paper":{"title":"Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guofeng Mei, Jing Wang, Liang Xiao, Wentao Qu, Xiaoshui Huang, Yujiao Wu","submitted_at":"2025-08-05T09:30:39Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPMs) have shown success in robust 3D object detection tasks. Existing methods often rely on the score matching from 3D boxes or pre-trained diffusion priors. However, they typically require multi-step iterations in inference, which limits efficiency. To address this, we propose a Robust single-stage fully Sparse 3D object Detection Network with a Detachable Latent Framework (DLF) of DDPMs, named RSDNet. Specifically, RSDNet learns the denoising process in latent feature spaces through lightweight denoising networks like multi-level denoising autoenco"},"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":"2508.03252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T09:30:39Z","cross_cats_sorted":[],"title_canon_sha256":"4ceb77cd73fe8a6ba240006e1f35e09bf03f6c3b3b30ed4d76dd480c24d315f7","abstract_canon_sha256":"fe2ddb9b3c9d12f72e906dfb041f487e1c989d0c78e1e00398635876ad531afd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:07.375544Z","signature_b64":"PQVSeqP8J1t9oXjuk6ee/oF6bRJ2otCbTE4hJNcerp42YWz3xWbmET820+BHeKeS92q22a8q+DGfqhQmorvvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4842ffaaf888719a9aa5ff0da066d07d381ade04260e84c07bc397ee7114083","last_reissued_at":"2026-07-05T12:00:07.374986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:07.374986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guofeng Mei, Jing Wang, Liang Xiao, Wentao Qu, Xiaoshui Huang, Yujiao Wu","submitted_at":"2025-08-05T09:30:39Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPMs) have shown success in robust 3D object detection tasks. Existing methods often rely on the score matching from 3D boxes or pre-trained diffusion priors. However, they typically require multi-step iterations in inference, which limits efficiency. To address this, we propose a Robust single-stage fully Sparse 3D object Detection Network with a Detachable Latent Framework (DLF) of DDPMs, named RSDNet. Specifically, RSDNet learns the denoising process in latent feature spaces through lightweight denoising networks like multi-level denoising autoenco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03252","kind":"arxiv","version":2},"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/2508.03252/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":"2508.03252","created_at":"2026-07-05T12:00:07.375049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03252v2","created_at":"2026-07-05T12:00:07.375049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03252","created_at":"2026-07-05T12:00:07.375049+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SCC76VPRCDR","created_at":"2026-07-05T12:00:07.375049+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SCC76VPRCDRTKNK","created_at":"2026-07-05T12:00:07.375049+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SCC76VP","created_at":"2026-07-05T12:00:07.375049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19620","citing_title":"B\\'ezier Degradation Modeling for LiDAR-based Human Motion Capture","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03306","citing_title":"Deep Image Clustering Based on Curriculum Learning and Density Information","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07326","citing_title":"GEM: Generating LiDAR World Model via Deformable Mamba","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7","json":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7.json","graph_json":"https://pith.science/api/pith-number/2SCC76VPRCDRTKNKL7YNUBTNA7/graph.json","events_json":"https://pith.science/api/pith-number/2SCC76VPRCDRTKNKL7YNUBTNA7/events.json","paper":"https://pith.science/paper/2SCC76VP"},"agent_actions":{"view_html":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7","download_json":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7.json","view_paper":"https://pith.science/paper/2SCC76VP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03252&json=true","fetch_graph":"https://pith.science/api/pith-number/2SCC76VPRCDRTKNKL7YNUBTNA7/graph.json","fetch_events":"https://pith.science/api/pith-number/2SCC76VPRCDRTKNKL7YNUBTNA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7/action/storage_attestation","attest_author":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7/action/author_attestation","sign_citation":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7/action/citation_signature","submit_replication":"https://pith.science/pith/2SCC76VPRCDRTKNKL7YNUBTNA7/action/replication_record"}},"created_at":"2026-07-05T12:00:07.375049+00:00","updated_at":"2026-07-05T12:00:07.375049+00:00"}