{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OZGHFWT4KMZJTWNFNOZJCSBH4R","short_pith_number":"pith:OZGHFWT4","schema_version":"1.0","canonical_sha256":"764c72da7c533299d9a56bb2914827e465d6024cac7c8cda132f7959563f7b43","source":{"kind":"arxiv","id":"2508.20135","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Point Cloud Semantic Segmentation Pipeline for Unimproved Roads","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.IV","authors_text":"Andrew Yarovoi, Christopher R. Valenta","submitted_at":"2025-08-26T20:00:36Z","abstract_excerpt":"In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a projection-based convolutional neural network is pre-trained on a mixture of public urban datasets and a small, curated in-domain dataset; then, a lightweight prediction head is fine-tuned exclusively on in-domain data. Along the way, we explore the application of Point Prompt Training to batch normalization layers and the effects of Manifold Mixup as a regularize"},"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":"2508.20135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-08-26T20:00:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6aae1f1982659d25edb3396c74d2acfcad49f0c06ee5ddbdbad5d6b8fff3c40","abstract_canon_sha256":"16a7b35ce1fbf985ee3c54f5e40cc99af8ca45273778aa2404fce39abf42e8b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:30.100617Z","signature_b64":"IoOQBg2x2e17sZbW5GDOmWNx9rIEKPoemZ80cTgd7jcaHDWAbBC6vk9HrqPnO+PWG0f675MhSJffeoxrwOBxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"764c72da7c533299d9a56bb2914827e465d6024cac7c8cda132f7959563f7b43","last_reissued_at":"2026-07-05T12:00:30.100042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:30.100042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Point Cloud Semantic Segmentation Pipeline for Unimproved Roads","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.IV","authors_text":"Andrew Yarovoi, Christopher R. Valenta","submitted_at":"2025-08-26T20:00:36Z","abstract_excerpt":"In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a projection-based convolutional neural network is pre-trained on a mixture of public urban datasets and a small, curated in-domain dataset; then, a lightweight prediction head is fine-tuned exclusively on in-domain data. Along the way, we explore the application of Point Prompt Training to batch normalization layers and the effects of Manifold Mixup as a regularize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20135","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/2508.20135/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":"2508.20135","created_at":"2026-07-05T12:00:30.100101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20135v1","created_at":"2026-07-05T12:00:30.100101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20135","created_at":"2026-07-05T12:00:30.100101+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZGHFWT4KMZJ","created_at":"2026-07-05T12:00:30.100101+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZGHFWT4KMZJTWNF","created_at":"2026-07-05T12:00:30.100101+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZGHFWT4","created_at":"2026-07-05T12:00:30.100101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R","json":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R.json","graph_json":"https://pith.science/api/pith-number/OZGHFWT4KMZJTWNFNOZJCSBH4R/graph.json","events_json":"https://pith.science/api/pith-number/OZGHFWT4KMZJTWNFNOZJCSBH4R/events.json","paper":"https://pith.science/paper/OZGHFWT4"},"agent_actions":{"view_html":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R","download_json":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R.json","view_paper":"https://pith.science/paper/OZGHFWT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20135&json=true","fetch_graph":"https://pith.science/api/pith-number/OZGHFWT4KMZJTWNFNOZJCSBH4R/graph.json","fetch_events":"https://pith.science/api/pith-number/OZGHFWT4KMZJTWNFNOZJCSBH4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R/action/storage_attestation","attest_author":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R/action/author_attestation","sign_citation":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R/action/citation_signature","submit_replication":"https://pith.science/pith/OZGHFWT4KMZJTWNFNOZJCSBH4R/action/replication_record"}},"created_at":"2026-07-05T12:00:30.100101+00:00","updated_at":"2026-07-05T12:00:30.100101+00:00"}