{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:66JKJOZPOYQAOXULIV5U2TDZZ4","short_pith_number":"pith:66JKJOZP","schema_version":"1.0","canonical_sha256":"f792a4bb2f7620075e8b457b4d4c79cf308624443670755cfb5e7c48f6b59088","source":{"kind":"arxiv","id":"2003.03653","version":4},"attestation_state":"computed","paper":{"title":"SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eren Erdal Aksoy, George Tzelepis, Tiago Cortinhal","submitted_at":"2020-03-07T20:17:06Z","abstract_excerpt":"In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet [1] which has an encoder-decoder architecture where the encoder unit has a set of ResNet blocks and the decoder part combines upsampled features from the residual blocks. In contrast to SalsaNet, we introduce a new context module, replace the ResNet encoder blocks with a new residual dilated convolution stack with gradually increasing receptive fields and add the pixel-shuffle layer in the decoder. Additionally, we switch f"},"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":"2003.03653","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-07T20:17:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12a7cefbd0c5e5b87b40efb90baca72475c7ab1741c0ef19a8c0d9f206165c4d","abstract_canon_sha256":"3622ad83d0149a0ca984385722cae7c327c96fcf3ab5ae49a7e8e9cffec4b61d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:19.152824Z","signature_b64":"v6JOH4NyocruKkuevRexHhiVQssQLQQYqppSTgU0gr1gcRN9GgLHFNb0dHe0yPxL3xTuM91BA4VyuJ8M85IpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f792a4bb2f7620075e8b457b4d4c79cf308624443670755cfb5e7c48f6b59088","last_reissued_at":"2026-07-05T09:38:19.152484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:19.152484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eren Erdal Aksoy, George Tzelepis, Tiago Cortinhal","submitted_at":"2020-03-07T20:17:06Z","abstract_excerpt":"In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time. SalsaNext is the next version of SalsaNet [1] which has an encoder-decoder architecture where the encoder unit has a set of ResNet blocks and the decoder part combines upsampled features from the residual blocks. In contrast to SalsaNet, we introduce a new context module, replace the ResNet encoder blocks with a new residual dilated convolution stack with gradually increasing receptive fields and add the pixel-shuffle layer in the decoder. Additionally, we switch f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03653","kind":"arxiv","version":4},"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/2003.03653/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":"2003.03653","created_at":"2026-07-05T09:38:19.152535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.03653v4","created_at":"2026-07-05T09:38:19.152535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03653","created_at":"2026-07-05T09:38:19.152535+00:00"},{"alias_kind":"pith_short_12","alias_value":"66JKJOZPOYQA","created_at":"2026-07-05T09:38:19.152535+00:00"},{"alias_kind":"pith_short_16","alias_value":"66JKJOZPOYQAOXUL","created_at":"2026-07-05T09:38:19.152535+00:00"},{"alias_kind":"pith_short_8","alias_value":"66JKJOZP","created_at":"2026-07-05T09:38:19.152535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00978","citing_title":"Privacy-Preserving Depth-Only Open-Vocabulary 3D Semantic Segmentation Via Uncertainty-Guided Test-Time Optimization","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4","json":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4.json","graph_json":"https://pith.science/api/pith-number/66JKJOZPOYQAOXULIV5U2TDZZ4/graph.json","events_json":"https://pith.science/api/pith-number/66JKJOZPOYQAOXULIV5U2TDZZ4/events.json","paper":"https://pith.science/paper/66JKJOZP"},"agent_actions":{"view_html":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4","download_json":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4.json","view_paper":"https://pith.science/paper/66JKJOZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.03653&json=true","fetch_graph":"https://pith.science/api/pith-number/66JKJOZPOYQAOXULIV5U2TDZZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/66JKJOZPOYQAOXULIV5U2TDZZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4/action/storage_attestation","attest_author":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4/action/author_attestation","sign_citation":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4/action/citation_signature","submit_replication":"https://pith.science/pith/66JKJOZPOYQAOXULIV5U2TDZZ4/action/replication_record"}},"created_at":"2026-07-05T09:38:19.152535+00:00","updated_at":"2026-07-05T09:38:19.152535+00:00"}