{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:C5BLS7NT2HFA7HI4QUZ2SG3U5O","short_pith_number":"pith:C5BLS7NT","schema_version":"1.0","canonical_sha256":"1742b97db3d1ca0f9d1c8533a91b74eb9c60006e979b6e163dd5029277aca24a","source":{"kind":"arxiv","id":"2008.06520","version":2},"attestation_state":"computed","paper":{"title":"Learning Gradient Fields for Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Guandao Yang, Hadar Averbuch-Elor, Noah Snavely, Ruojin Cai, Serge Belongie, Zekun Hao","submitted_at":"2020-08-14T18:06:15Z","abstract_excerpt":"In this work, we propose a novel technique to generate shapes from point cloud data. A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape. Point cloud generation thus amounts to moving randomly sampled points to high-density areas. We generate point clouds by performing stochastic gradient ascent on an unnormalized probability density, thereby moving sampled points toward the high-likelihood regions. Our model directly predicts the gradient of the log density field and can be trained with a simple objective adapted "},"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":"2008.06520","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-14T18:06:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62b805f91c6eafb2865c571e22d1468a918c6fc74963eb2b9aa83c7d9e02ff95","abstract_canon_sha256":"669b319aede608880295a69eb1fbca31fe687a0b41ad2e2887b9a91157468951"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:49.304642Z","signature_b64":"jhInkV8lFqSTvoMGxvv7+gq2cstn7krAqYjJhkMvgDinnnLlM740T4cv9q8+sqBR4CRGCfpjU+9e3rCLcm8sCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1742b97db3d1ca0f9d1c8533a91b74eb9c60006e979b6e163dd5029277aca24a","last_reissued_at":"2026-07-05T01:27:49.304195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:49.304195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Gradient Fields for Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Guandao Yang, Hadar Averbuch-Elor, Noah Snavely, Ruojin Cai, Serge Belongie, Zekun Hao","submitted_at":"2020-08-14T18:06:15Z","abstract_excerpt":"In this work, we propose a novel technique to generate shapes from point cloud data. A point cloud can be viewed as samples from a distribution of 3D points whose density is concentrated near the surface of the shape. Point cloud generation thus amounts to moving randomly sampled points to high-density areas. We generate point clouds by performing stochastic gradient ascent on an unnormalized probability density, thereby moving sampled points toward the high-likelihood regions. Our model directly predicts the gradient of the log density field and can be trained with a simple objective adapted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06520","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/2008.06520/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":"2008.06520","created_at":"2026-07-05T01:27:49.304266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06520v2","created_at":"2026-07-05T01:27:49.304266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06520","created_at":"2026-07-05T01:27:49.304266+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5BLS7NT2HFA","created_at":"2026-07-05T01:27:49.304266+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5BLS7NT2HFA7HI4","created_at":"2026-07-05T01:27:49.304266+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5BLS7NT","created_at":"2026-07-05T01:27:49.304266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2202.00512","citing_title":"Progressive Distillation for Fast Sampling of Diffusion Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O","json":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O.json","graph_json":"https://pith.science/api/pith-number/C5BLS7NT2HFA7HI4QUZ2SG3U5O/graph.json","events_json":"https://pith.science/api/pith-number/C5BLS7NT2HFA7HI4QUZ2SG3U5O/events.json","paper":"https://pith.science/paper/C5BLS7NT"},"agent_actions":{"view_html":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O","download_json":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O.json","view_paper":"https://pith.science/paper/C5BLS7NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06520&json=true","fetch_graph":"https://pith.science/api/pith-number/C5BLS7NT2HFA7HI4QUZ2SG3U5O/graph.json","fetch_events":"https://pith.science/api/pith-number/C5BLS7NT2HFA7HI4QUZ2SG3U5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O/action/storage_attestation","attest_author":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O/action/author_attestation","sign_citation":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O/action/citation_signature","submit_replication":"https://pith.science/pith/C5BLS7NT2HFA7HI4QUZ2SG3U5O/action/replication_record"}},"created_at":"2026-07-05T01:27:49.304266+00:00","updated_at":"2026-07-05T01:27:49.304266+00:00"}