{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2U7UQKAVDZMOKZYUZXKA3WCJWB","short_pith_number":"pith:2U7UQKAV","schema_version":"1.0","canonical_sha256":"d53f4828151e58e56714cdd40dd849b04e1d6c2707ebe28b775cfe99d6575df9","source":{"kind":"arxiv","id":"2210.01784","version":2},"attestation_state":"computed","paper":{"title":"COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh-Quan Cao, Raoul de Charette, Rong Li","submitted_at":"2022-10-04T17:54:53Z","abstract_excerpt":"Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel architecture-agnostic contrastive learning strategy for 3D segmentation. Since contrastive learning requires rich and diverse examples as keys and anchors, we leverage a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys. An entropy-driven sampling technique then allows us to select good pi"},"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":"2210.01784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-04T17:54:53Z","cross_cats_sorted":[],"title_canon_sha256":"84dc0a612ff265859652700a322eda8d59e2a5cee30ecf9d8133d8d26a5f3e4d","abstract_canon_sha256":"75cbb0092bd72747cc09370d6ce7c4705d3814306fc93d3785897ff9620914c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:31.533203Z","signature_b64":"agxKIoglKEP34bvfw8dBtFYUKrvb1Qdw/3XOFYwjs0hbyVVptuyd6VWAzEhtpzjIImdjsFI+T798K3ENG2ihBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d53f4828151e58e56714cdd40dd849b04e1d6c2707ebe28b775cfe99d6575df9","last_reissued_at":"2026-07-05T05:04:31.532830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:31.532830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh-Quan Cao, Raoul de Charette, Rong Li","submitted_at":"2022-10-04T17:54:53Z","abstract_excerpt":"Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel architecture-agnostic contrastive learning strategy for 3D segmentation. Since contrastive learning requires rich and diverse examples as keys and anchors, we leverage a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys. An entropy-driven sampling technique then allows us to select good pi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01784","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/2210.01784/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":"2210.01784","created_at":"2026-07-05T05:04:31.532883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01784v2","created_at":"2026-07-05T05:04:31.532883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01784","created_at":"2026-07-05T05:04:31.532883+00:00"},{"alias_kind":"pith_short_12","alias_value":"2U7UQKAVDZMO","created_at":"2026-07-05T05:04:31.532883+00:00"},{"alias_kind":"pith_short_16","alias_value":"2U7UQKAVDZMOKZYU","created_at":"2026-07-05T05:04:31.532883+00:00"},{"alias_kind":"pith_short_8","alias_value":"2U7UQKAV","created_at":"2026-07-05T05:04:31.532883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17661","citing_title":"Monocular Semantic Scene Completion via Masked Recurrent Networks","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB","json":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB.json","graph_json":"https://pith.science/api/pith-number/2U7UQKAVDZMOKZYUZXKA3WCJWB/graph.json","events_json":"https://pith.science/api/pith-number/2U7UQKAVDZMOKZYUZXKA3WCJWB/events.json","paper":"https://pith.science/paper/2U7UQKAV"},"agent_actions":{"view_html":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB","download_json":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB.json","view_paper":"https://pith.science/paper/2U7UQKAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01784&json=true","fetch_graph":"https://pith.science/api/pith-number/2U7UQKAVDZMOKZYUZXKA3WCJWB/graph.json","fetch_events":"https://pith.science/api/pith-number/2U7UQKAVDZMOKZYUZXKA3WCJWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB/action/storage_attestation","attest_author":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB/action/author_attestation","sign_citation":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB/action/citation_signature","submit_replication":"https://pith.science/pith/2U7UQKAVDZMOKZYUZXKA3WCJWB/action/replication_record"}},"created_at":"2026-07-05T05:04:31.532883+00:00","updated_at":"2026-07-05T05:04:31.532883+00:00"}