{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IDWEPPOJDMDWPHMI2RS76U65Q3","short_pith_number":"pith:IDWEPPOJ","schema_version":"1.0","canonical_sha256":"40ec47bdc91b07679d88d465ff53dd86f661e986ed46f998fd5656ef8d8bab3d","source":{"kind":"arxiv","id":"1906.12320","version":3},"attestation_state":"computed","paper":{"title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Guandao Yang, Ming-Yu Liu, Serge Belongie, Xun Huang, Zekun Hao","submitted_at":"2019-06-28T17:25:54Z","abstract_excerpt":"As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the"},"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":"1906.12320","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-28T17:25:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"02dd80bee2191287b093a45588a1b83149e3d302c09bb9a4569b4ea9a80fbad4","abstract_canon_sha256":"359c95ea335fe65cdf1fe05377b1d46c7e7c6d729902293ecea78e7e1851428b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:01.344867Z","signature_b64":"ZNCdmq9tgGk3uK6+bEg95VLYq+UgJXQp4c3GNIGQWnWSu82HUQczMGskFNRulSVltqic6Qi5aQnzqUUrne6vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40ec47bdc91b07679d88d465ff53dd86f661e986ed46f998fd5656ef8d8bab3d","last_reissued_at":"2026-07-05T00:01:01.344412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:01.344412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Guandao Yang, Ming-Yu Liu, Serge Belongie, Xun Huang, Zekun Hao","submitted_at":"2019-06-28T17:25:54Z","abstract_excerpt":"As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12320","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/1906.12320/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":"1906.12320","created_at":"2026-07-05T00:01:01.344474+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.12320v3","created_at":"2026-07-05T00:01:01.344474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12320","created_at":"2026-07-05T00:01:01.344474+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDWEPPOJDMDW","created_at":"2026-07-05T00:01:01.344474+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDWEPPOJDMDWPHMI","created_at":"2026-07-05T00:01:01.344474+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDWEPPOJ","created_at":"2026-07-05T00:01:01.344474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.02463","citing_title":"Shap-E: Generating Conditional 3D Implicit Functions","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3","json":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3.json","graph_json":"https://pith.science/api/pith-number/IDWEPPOJDMDWPHMI2RS76U65Q3/graph.json","events_json":"https://pith.science/api/pith-number/IDWEPPOJDMDWPHMI2RS76U65Q3/events.json","paper":"https://pith.science/paper/IDWEPPOJ"},"agent_actions":{"view_html":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3","download_json":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3.json","view_paper":"https://pith.science/paper/IDWEPPOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.12320&json=true","fetch_graph":"https://pith.science/api/pith-number/IDWEPPOJDMDWPHMI2RS76U65Q3/graph.json","fetch_events":"https://pith.science/api/pith-number/IDWEPPOJDMDWPHMI2RS76U65Q3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3/action/storage_attestation","attest_author":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3/action/author_attestation","sign_citation":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3/action/citation_signature","submit_replication":"https://pith.science/pith/IDWEPPOJDMDWPHMI2RS76U65Q3/action/replication_record"}},"created_at":"2026-07-05T00:01:01.344474+00:00","updated_at":"2026-07-05T00:01:01.344474+00:00"}