{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G5OQ6SEMJG5BKUKJFDKJPBXMSF","short_pith_number":"pith:G5OQ6SEM","schema_version":"1.0","canonical_sha256":"375d0f488c49ba15514928d49786ec916e11e0fdbf4440b66cdd28d2f0b124d2","source":{"kind":"arxiv","id":"2104.04891","version":3},"attestation_state":"computed","paper":{"title":"SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ales Leonardis, Andrew Markham, Bo Yang, Guangchi Fang, Niki Trigoni, Qingyong Hu, Yulan Guo","submitted_at":"2021-04-11T01:29:50Z","abstract_excerpt":"Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighborhood is relatively homogeneous, exhibiting st"},"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":"2104.04891","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-11T01:29:50Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3fd87d5dcc1ffa8de973d9e76740a48b89cb4cc316b1fa591cace0d585899256","abstract_canon_sha256":"5af3f34286b8e055d89e733a1f97ae1e0344a89d98a8d7fbb0a4d6be52e33f77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:48.425413Z","signature_b64":"x4+bAP4JuBAIDZo0vY2L0iy/IdIKVyXK8PwDkdD92ZuA8T8RekyJtHKUy+XRNjhPrOib2SBiWpu5tQHB/a5pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375d0f488c49ba15514928d49786ec916e11e0fdbf4440b66cdd28d2f0b124d2","last_reissued_at":"2026-07-05T06:04:48.425058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:48.425058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ales Leonardis, Andrew Markham, Bo Yang, Guangchi Fang, Niki Trigoni, Qingyong Hu, Yulan Guo","submitted_at":"2021-04-11T01:29:50Z","abstract_excerpt":"Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighborhood is relatively homogeneous, exhibiting st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04891","kind":"arxiv","version":3},"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/2104.04891/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":"2104.04891","created_at":"2026-07-05T06:04:48.425116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04891v3","created_at":"2026-07-05T06:04:48.425116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04891","created_at":"2026-07-05T06:04:48.425116+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5OQ6SEMJG5B","created_at":"2026-07-05T06:04:48.425116+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5OQ6SEMJG5BKUKJ","created_at":"2026-07-05T06:04:48.425116+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5OQ6SEM","created_at":"2026-07-05T06:04:48.425116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.28660","citing_title":"Industrial3D: A Water-Treatment TLS Point Cloud Dataset and Cross-Paradigm Benchmark for MEP Scene Understanding","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF","json":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF.json","graph_json":"https://pith.science/api/pith-number/G5OQ6SEMJG5BKUKJFDKJPBXMSF/graph.json","events_json":"https://pith.science/api/pith-number/G5OQ6SEMJG5BKUKJFDKJPBXMSF/events.json","paper":"https://pith.science/paper/G5OQ6SEM"},"agent_actions":{"view_html":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF","download_json":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF.json","view_paper":"https://pith.science/paper/G5OQ6SEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04891&json=true","fetch_graph":"https://pith.science/api/pith-number/G5OQ6SEMJG5BKUKJFDKJPBXMSF/graph.json","fetch_events":"https://pith.science/api/pith-number/G5OQ6SEMJG5BKUKJFDKJPBXMSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF/action/storage_attestation","attest_author":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF/action/author_attestation","sign_citation":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF/action/citation_signature","submit_replication":"https://pith.science/pith/G5OQ6SEMJG5BKUKJFDKJPBXMSF/action/replication_record"}},"created_at":"2026-07-05T06:04:48.425116+00:00","updated_at":"2026-07-05T06:04:48.425116+00:00"}