{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ALC36RCK4AH5VGDFF2DBPDLGXL","short_pith_number":"pith:ALC36RCK","schema_version":"1.0","canonical_sha256":"02c5bf444ae00fda98652e86178d66bae794bb3482606ba775cc774c99bfef3c","source":{"kind":"arxiv","id":"2202.02763","version":3},"attestation_state":"computed","paper":{"title":"Riemannian Score-Based Generative Modelling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Emile Mathieu, James Thornton, Michael Hutchinson, Valentin De Bortoli, Yee Whye Teh","submitted_at":"2022-02-06T11:57:39Z","abstract_excerpt":"Score-based generative models (SGMs) are a powerful class of generative models that exhibit remarkable empirical performance. Score-based generative modelling (SGM) consists of a ``noising'' stage, whereby a diffusion is used to gradually add Gaussian noise to data, and a generative model, which entails a ``denoising'' process defined by approximating the time-reversal of the diffusion. Existing SGMs assume that data is supported on a Euclidean space, i.e. a manifold with flat geometry. In many domains such as robotics, geoscience or protein modelling, data is often naturally described by dist"},"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":"2202.02763","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-06T11:57:39Z","cross_cats_sorted":["math.PR","stat.ML"],"title_canon_sha256":"cc994a8ba40e81341782d73cb77d7280623ee45087583658a9f79caebc7d887e","abstract_canon_sha256":"1bdede4ba9aed13233e6afcf2213205a96503ea4b454c48a0d35ec1cf9a8318e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:01.543000Z","signature_b64":"DtwkP+Cjb2nRhCstU0m9+oAgM6OfzQU6LWgnK8XhI6XVgvUk0vLbCv6bYtX551EPn6ZcSjg5vDGoiAFePmbVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02c5bf444ae00fda98652e86178d66bae794bb3482606ba775cc774c99bfef3c","last_reissued_at":"2026-07-05T05:18:01.542568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:01.542568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Riemannian Score-Based Generative Modelling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Emile Mathieu, James Thornton, Michael Hutchinson, Valentin De Bortoli, Yee Whye Teh","submitted_at":"2022-02-06T11:57:39Z","abstract_excerpt":"Score-based generative models (SGMs) are a powerful class of generative models that exhibit remarkable empirical performance. Score-based generative modelling (SGM) consists of a ``noising'' stage, whereby a diffusion is used to gradually add Gaussian noise to data, and a generative model, which entails a ``denoising'' process defined by approximating the time-reversal of the diffusion. Existing SGMs assume that data is supported on a Euclidean space, i.e. a manifold with flat geometry. In many domains such as robotics, geoscience or protein modelling, data is often naturally described by dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02763","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/2202.02763/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":"2202.02763","created_at":"2026-07-05T05:18:01.542627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02763v3","created_at":"2026-07-05T05:18:01.542627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02763","created_at":"2026-07-05T05:18:01.542627+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALC36RCK4AH5","created_at":"2026-07-05T05:18:01.542627+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALC36RCK4AH5VGDF","created_at":"2026-07-05T05:18:01.542627+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALC36RCK","created_at":"2026-07-05T05:18:01.542627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02415","citing_title":"Generative models on phase space","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26503","citing_title":"Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL","json":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL.json","graph_json":"https://pith.science/api/pith-number/ALC36RCK4AH5VGDFF2DBPDLGXL/graph.json","events_json":"https://pith.science/api/pith-number/ALC36RCK4AH5VGDFF2DBPDLGXL/events.json","paper":"https://pith.science/paper/ALC36RCK"},"agent_actions":{"view_html":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL","download_json":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL.json","view_paper":"https://pith.science/paper/ALC36RCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02763&json=true","fetch_graph":"https://pith.science/api/pith-number/ALC36RCK4AH5VGDFF2DBPDLGXL/graph.json","fetch_events":"https://pith.science/api/pith-number/ALC36RCK4AH5VGDFF2DBPDLGXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL/action/storage_attestation","attest_author":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL/action/author_attestation","sign_citation":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL/action/citation_signature","submit_replication":"https://pith.science/pith/ALC36RCK4AH5VGDFF2DBPDLGXL/action/replication_record"}},"created_at":"2026-07-05T05:18:01.542627+00:00","updated_at":"2026-07-05T05:18:01.542627+00:00"}