{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VQ63C3UWHHQY5AVX7IIUM46KOM","short_pith_number":"pith:VQ63C3UW","schema_version":"1.0","canonical_sha256":"ac3db16e9639e18e82b7fa114673ca733a3514730d6018de72d87c2305d46e29","source":{"kind":"arxiv","id":"2210.02030","version":1},"attestation_state":"computed","paper":{"title":"Point Cloud Recognition with Position-to-Structure Attention Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"James Hou, Zheng Ding, Zhuowen Tu","submitted_at":"2022-10-05T05:40:33Z","abstract_excerpt":"In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not positioned in a fixed grid structure and have limited feature description (only 3D coordinates ($x, y, z$) for scattered points). Existing Transformer-based architectures in this domain often require a pre-specified feature engineering step to extract point features. Here, we introduce two new aspects in PS-Former: 1) a learnable condensation layer that performs "},"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":"2210.02030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T05:40:33Z","cross_cats_sorted":[],"title_canon_sha256":"4fb370e1324d029453d7e51aa24ae5e0292c20398d726660cb2138b997dbd9f3","abstract_canon_sha256":"def8dd5b0f97b3446994ba7eca90b98a4ff0cfc53cac533c5ecbcae5ac19ef49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:42.502170Z","signature_b64":"aV9rr/uC6aLgPh4nyfjOi85vVlVCCZoZPA2lZTqrseMukbPqijRR325PHG0knc6lw8DyRGhx34iw0pILducPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac3db16e9639e18e82b7fa114673ca733a3514730d6018de72d87c2305d46e29","last_reissued_at":"2026-07-05T05:03:42.501671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:42.501671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point Cloud Recognition with Position-to-Structure Attention Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"James Hou, Zheng Ding, Zhuowen Tu","submitted_at":"2022-10-05T05:40:33Z","abstract_excerpt":"In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not positioned in a fixed grid structure and have limited feature description (only 3D coordinates ($x, y, z$) for scattered points). Existing Transformer-based architectures in this domain often require a pre-specified feature engineering step to extract point features. Here, we introduce two new aspects in PS-Former: 1) a learnable condensation layer that performs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02030","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/2210.02030/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":"2210.02030","created_at":"2026-07-05T05:03:42.501736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02030v1","created_at":"2026-07-05T05:03:42.501736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02030","created_at":"2026-07-05T05:03:42.501736+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQ63C3UWHHQY","created_at":"2026-07-05T05:03:42.501736+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQ63C3UWHHQY5AVX","created_at":"2026-07-05T05:03:42.501736+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQ63C3UW","created_at":"2026-07-05T05:03:42.501736+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/VQ63C3UWHHQY5AVX7IIUM46KOM","json":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM.json","graph_json":"https://pith.science/api/pith-number/VQ63C3UWHHQY5AVX7IIUM46KOM/graph.json","events_json":"https://pith.science/api/pith-number/VQ63C3UWHHQY5AVX7IIUM46KOM/events.json","paper":"https://pith.science/paper/VQ63C3UW"},"agent_actions":{"view_html":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM","download_json":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM.json","view_paper":"https://pith.science/paper/VQ63C3UW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02030&json=true","fetch_graph":"https://pith.science/api/pith-number/VQ63C3UWHHQY5AVX7IIUM46KOM/graph.json","fetch_events":"https://pith.science/api/pith-number/VQ63C3UWHHQY5AVX7IIUM46KOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM/action/storage_attestation","attest_author":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM/action/author_attestation","sign_citation":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM/action/citation_signature","submit_replication":"https://pith.science/pith/VQ63C3UWHHQY5AVX7IIUM46KOM/action/replication_record"}},"created_at":"2026-07-05T05:03:42.501736+00:00","updated_at":"2026-07-05T05:03:42.501736+00:00"}