{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N2PDFI6OZBWS3B72POJLHKLW2K","short_pith_number":"pith:N2PDFI6O","schema_version":"1.0","canonical_sha256":"6e9e32a3cec86d2d87fa7b92b3a976d2b7f804ee4ecf4742f18096b317d3e398","source":{"kind":"arxiv","id":"2504.17791","version":2},"attestation_state":"computed","paper":{"title":"LiDPM: Rethinking Point Diffusion for Lidar Scene Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Boulch, Gilles Puy, Raoul de Charette, Renaud Marlet, Tetiana Martyniuk","submitted_at":"2025-04-24T17:59:59Z","abstract_excerpt":"Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulati"},"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":"2504.17791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T17:59:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"667a363b6472c77a4cb97a0e697b422f3c1e8b0a7477dc36537a8bc889d5df7f","abstract_canon_sha256":"77bd789208ac7d6c0e59b0fc3d25c78b61a70234005bd3c595d3907f4a5ac976"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:06.782954Z","signature_b64":"NkerxorIBInLojckHCAQ0fAPjCUAkiPmPVL9K4C8KKOu5tP+XToKrG0t6/tg+1yQnZqDdEnixSZ/L/Jjhg57DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e9e32a3cec86d2d87fa7b92b3a976d2b7f804ee4ecf4742f18096b317d3e398","last_reissued_at":"2026-07-05T11:38:06.782409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:06.782409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiDPM: Rethinking Point Diffusion for Lidar Scene Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexandre Boulch, Gilles Puy, Raoul de Charette, Renaud Marlet, Tetiana Martyniuk","submitted_at":"2025-04-24T17:59:59Z","abstract_excerpt":"Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17791","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/2504.17791/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":"2504.17791","created_at":"2026-07-05T11:38:06.782504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17791v2","created_at":"2026-07-05T11:38:06.782504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17791","created_at":"2026-07-05T11:38:06.782504+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2PDFI6OZBWS","created_at":"2026-07-05T11:38:06.782504+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2PDFI6OZBWS3B72","created_at":"2026-07-05T11:38:06.782504+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2PDFI6O","created_at":"2026-07-05T11:38:06.782504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03691","citing_title":"La La LiDAR: Large-Scale Layout Generation from LiDAR Data","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K","json":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K.json","graph_json":"https://pith.science/api/pith-number/N2PDFI6OZBWS3B72POJLHKLW2K/graph.json","events_json":"https://pith.science/api/pith-number/N2PDFI6OZBWS3B72POJLHKLW2K/events.json","paper":"https://pith.science/paper/N2PDFI6O"},"agent_actions":{"view_html":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K","download_json":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K.json","view_paper":"https://pith.science/paper/N2PDFI6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17791&json=true","fetch_graph":"https://pith.science/api/pith-number/N2PDFI6OZBWS3B72POJLHKLW2K/graph.json","fetch_events":"https://pith.science/api/pith-number/N2PDFI6OZBWS3B72POJLHKLW2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K/action/storage_attestation","attest_author":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K/action/author_attestation","sign_citation":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K/action/citation_signature","submit_replication":"https://pith.science/pith/N2PDFI6OZBWS3B72POJLHKLW2K/action/replication_record"}},"created_at":"2026-07-05T11:38:06.782504+00:00","updated_at":"2026-07-05T11:38:06.782504+00:00"}