{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2DG2TEBFPFDSJG65ZN2IQ5EQ5L","short_pith_number":"pith:2DG2TEBF","schema_version":"1.0","canonical_sha256":"d0cda990257947249bddcb74887490eaec93b8dcba53cabc22f35d67a39128b1","source":{"kind":"arxiv","id":"2204.02394","version":2},"attestation_state":"computed","paper":{"title":"SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Edgar Dobriban, Evangelos Chatzipantazis, Kostas Daniilidis, Stefanos Pertigkiozoglou","submitted_at":"2022-04-05T17:59:15Z","abstract_excerpt":"We propose a method for 3D shape reconstruction from unoriented point clouds. Our method consists of a novel SE(3)-equivariant coordinate-based network (TF-ONet), that parametrizes the occupancy field of the shape and respects the inherent symmetries of the problem. In contrast to previous shape reconstruction methods that align the input to a regular grid, we operate directly on the irregular point cloud. Our architecture leverages equivariant attention layers that operate on local tokens. This mechanism enables local shape modelling, a crucial property for scalability to large scenes. Given "},"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":"2204.02394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-05T17:59:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b847b19aee4a4500ae2feb7301e0746dfcd5b42e6af6dbac11a564a9100b6923","abstract_canon_sha256":"f3b08c048f7eaaf2442d7c80b226ae97400bf7d2aad3b93a5b47ab67a40a8300"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:20.430648Z","signature_b64":"AgO+ed31zZO7x9XqwIpqd9QxG18dP37BH8J/3WtfHgfMticoPClaEYGNe1Knl3L2LomSUkgnhQgSk9yvFHjPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0cda990257947249bddcb74887490eaec93b8dcba53cabc22f35d67a39128b1","last_reissued_at":"2026-07-05T05:40:20.430165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:20.430165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Edgar Dobriban, Evangelos Chatzipantazis, Kostas Daniilidis, Stefanos Pertigkiozoglou","submitted_at":"2022-04-05T17:59:15Z","abstract_excerpt":"We propose a method for 3D shape reconstruction from unoriented point clouds. Our method consists of a novel SE(3)-equivariant coordinate-based network (TF-ONet), that parametrizes the occupancy field of the shape and respects the inherent symmetries of the problem. In contrast to previous shape reconstruction methods that align the input to a regular grid, we operate directly on the irregular point cloud. Our architecture leverages equivariant attention layers that operate on local tokens. This mechanism enables local shape modelling, a crucial property for scalability to large scenes. Given "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02394","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/2204.02394/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":"2204.02394","created_at":"2026-07-05T05:40:20.430221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02394v2","created_at":"2026-07-05T05:40:20.430221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02394","created_at":"2026-07-05T05:40:20.430221+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DG2TEBFPFDS","created_at":"2026-07-05T05:40:20.430221+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DG2TEBFPFDSJG65","created_at":"2026-07-05T05:40:20.430221+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DG2TEBF","created_at":"2026-07-05T05:40:20.430221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27864","citing_title":"A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\\mathrm{O}(2)$","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27864","citing_title":"A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\\mathrm{O}(2)$","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08189","citing_title":"Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L","json":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L.json","graph_json":"https://pith.science/api/pith-number/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/graph.json","events_json":"https://pith.science/api/pith-number/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/events.json","paper":"https://pith.science/paper/2DG2TEBF"},"agent_actions":{"view_html":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L","download_json":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L.json","view_paper":"https://pith.science/paper/2DG2TEBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02394&json=true","fetch_graph":"https://pith.science/api/pith-number/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/graph.json","fetch_events":"https://pith.science/api/pith-number/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/action/storage_attestation","attest_author":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/action/author_attestation","sign_citation":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/action/citation_signature","submit_replication":"https://pith.science/pith/2DG2TEBFPFDSJG65ZN2IQ5EQ5L/action/replication_record"}},"created_at":"2026-07-05T05:40:20.430221+00:00","updated_at":"2026-07-05T05:40:20.430221+00:00"}