{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BMVRGVXPLFN3IUWUZ6JVDABST6","short_pith_number":"pith:BMVRGVXP","schema_version":"1.0","canonical_sha256":"0b2b1356ef595bb452d4cf935180329fa6305d56a5520703af5071baba664e6b","source":{"kind":"arxiv","id":"2301.04545","version":1},"attestation_state":"computed","paper":{"title":"AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Xumin Yu, Yongming Rao, Ziyi Wang","submitted_at":"2023-01-11T16:14:12Z","abstract_excerpt":"In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion. By representing the point cloud as a set of unordered groups of points with position embeddings, we convert the input data to a sequence of point proxies and employ the Transformers for generation. To facilitate Transformers to better leverage the inductive bias about 3D geometric structures of point clouds, we further devise a geometry-aware block that model"},"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":"2301.04545","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-11T16:14:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5059ac5a0e20b6b721c13b7481814929e6d7d0947361f5cb269e460ecb9c86cd","abstract_canon_sha256":"2eed65e342f0cfb31929820b4dd393123db1ae24a08d6bd69ad2319a2a897a1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:26.679571Z","signature_b64":"mPYFRSeXPZC3j7tZDMZ0cwyUK5rxm5c1tdaij3lPGAjmDpFhDd22YagqhV1oSd+qay/ZJM8NFmaQAk0toTEUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b2b1356ef595bb452d4cf935180329fa6305d56a5520703af5071baba664e6b","last_reissued_at":"2026-07-05T05:32:26.679169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:26.679169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Xumin Yu, Yongming Rao, Ziyi Wang","submitted_at":"2023-01-11T16:14:12Z","abstract_excerpt":"In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion. By representing the point cloud as a set of unordered groups of points with position embeddings, we convert the input data to a sequence of point proxies and employ the Transformers for generation. To facilitate Transformers to better leverage the inductive bias about 3D geometric structures of point clouds, we further devise a geometry-aware block that model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04545","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/2301.04545/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":"2301.04545","created_at":"2026-07-05T05:32:26.679225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04545v1","created_at":"2026-07-05T05:32:26.679225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04545","created_at":"2026-07-05T05:32:26.679225+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMVRGVXPLFN3","created_at":"2026-07-05T05:32:26.679225+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMVRGVXPLFN3IUWU","created_at":"2026-07-05T05:32:26.679225+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMVRGVXP","created_at":"2026-07-05T05:32:26.679225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16743","citing_title":"Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6","json":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6.json","graph_json":"https://pith.science/api/pith-number/BMVRGVXPLFN3IUWUZ6JVDABST6/graph.json","events_json":"https://pith.science/api/pith-number/BMVRGVXPLFN3IUWUZ6JVDABST6/events.json","paper":"https://pith.science/paper/BMVRGVXP"},"agent_actions":{"view_html":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6","download_json":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6.json","view_paper":"https://pith.science/paper/BMVRGVXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04545&json=true","fetch_graph":"https://pith.science/api/pith-number/BMVRGVXPLFN3IUWUZ6JVDABST6/graph.json","fetch_events":"https://pith.science/api/pith-number/BMVRGVXPLFN3IUWUZ6JVDABST6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6/action/storage_attestation","attest_author":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6/action/author_attestation","sign_citation":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6/action/citation_signature","submit_replication":"https://pith.science/pith/BMVRGVXPLFN3IUWUZ6JVDABST6/action/replication_record"}},"created_at":"2026-07-05T05:32:26.679225+00:00","updated_at":"2026-07-05T05:32:26.679225+00:00"}