{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FQP6N5XRBVW3YFITAVAM7KNXMO","short_pith_number":"pith:FQP6N5XR","schema_version":"1.0","canonical_sha256":"2c1fe6f6f10d6dbc15130540cfa9b7639e17cf30a6815a46495ba97420726032","source":{"kind":"arxiv","id":"2403.07593","version":2},"attestation_state":"computed","paper":{"title":"MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A. Gil, A. Santo, C. Viegas, J.J. Cabrera, L. Pay\\'a","submitted_at":"2024-03-12T12:25:54Z","abstract_excerpt":"This paper presents MinkUNeXt, an effective and efficient architecture for place-recognition from point clouds entirely based on the new 3D MinkNeXt Block, a residual block composed of 3D sparse convolutions that follows the philosophy established by recent Transformers but purely using simple 3D convolutions. Feature extraction is performed at different scales by a U-Net encoder-decoder network and the feature aggregation of those features into a single descriptor is carried out by a Generalized Mean Pooling (GeM). The proposed architecture demonstrates that it is possible to surpass the curr"},"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":"2403.07593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T12:25:54Z","cross_cats_sorted":[],"title_canon_sha256":"d69e79d54c46bfe5d53d06f4d78f9b1da3e256f3f55dd05e662854dfad786dca","abstract_canon_sha256":"bc71ced9046e17b74e9baa8190fbc008b8001e6cddfdec735a0cc0e4cbee74d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:23.272739Z","signature_b64":"DqMJ1TIJuq7orzxnH63s983qC6q7S+M9Wc7VLJgnNYp3a6z9RJu9GdYJ00HU3sEQsbTKk8l+SL16riddQShAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c1fe6f6f10d6dbc15130540cfa9b7639e17cf30a6815a46495ba97420726032","last_reissued_at":"2026-07-05T09:25:23.272294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:23.272294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A. Gil, A. Santo, C. Viegas, J.J. Cabrera, L. Pay\\'a","submitted_at":"2024-03-12T12:25:54Z","abstract_excerpt":"This paper presents MinkUNeXt, an effective and efficient architecture for place-recognition from point clouds entirely based on the new 3D MinkNeXt Block, a residual block composed of 3D sparse convolutions that follows the philosophy established by recent Transformers but purely using simple 3D convolutions. Feature extraction is performed at different scales by a U-Net encoder-decoder network and the feature aggregation of those features into a single descriptor is carried out by a Generalized Mean Pooling (GeM). The proposed architecture demonstrates that it is possible to surpass the curr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07593","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/2403.07593/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":"2403.07593","created_at":"2026-07-05T09:25:23.272360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07593v2","created_at":"2026-07-05T09:25:23.272360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07593","created_at":"2026-07-05T09:25:23.272360+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQP6N5XRBVW3","created_at":"2026-07-05T09:25:23.272360+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQP6N5XRBVW3YFIT","created_at":"2026-07-05T09:25:23.272360+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQP6N5XR","created_at":"2026-07-05T09:25:23.272360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17591","citing_title":"MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO","json":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO.json","graph_json":"https://pith.science/api/pith-number/FQP6N5XRBVW3YFITAVAM7KNXMO/graph.json","events_json":"https://pith.science/api/pith-number/FQP6N5XRBVW3YFITAVAM7KNXMO/events.json","paper":"https://pith.science/paper/FQP6N5XR"},"agent_actions":{"view_html":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO","download_json":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO.json","view_paper":"https://pith.science/paper/FQP6N5XR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07593&json=true","fetch_graph":"https://pith.science/api/pith-number/FQP6N5XRBVW3YFITAVAM7KNXMO/graph.json","fetch_events":"https://pith.science/api/pith-number/FQP6N5XRBVW3YFITAVAM7KNXMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO/action/storage_attestation","attest_author":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO/action/author_attestation","sign_citation":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO/action/citation_signature","submit_replication":"https://pith.science/pith/FQP6N5XRBVW3YFITAVAM7KNXMO/action/replication_record"}},"created_at":"2026-07-05T09:25:23.272360+00:00","updated_at":"2026-07-05T09:25:23.272360+00:00"}