{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7QR2TX62N2CUO7NGRWCI7GUHVC","short_pith_number":"pith:7QR2TX62","canonical_record":{"source":{"id":"2402.08018","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T19:27:30Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e549425927e563045cf01f36d69c732a33040666d60f6a43d08c24efb7e83782","abstract_canon_sha256":"ff58b4d8f61fcbf9322ff1812d99c01ec99fe4649903346eb1fb6d7c34abd13e"},"schema_version":"1.0"},"canonical_sha256":"fc23a9dfda6e85477da68d848f9a87a8a8f678b88a2b31d60d136c86787d8399","source":{"kind":"arxiv","id":"2402.08018","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08018","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08018v2","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08018","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"7QR2TX62N2CU","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"7QR2TX62N2CUO7NG","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"7QR2TX62","created_at":"2026-07-05T08:44:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7QR2TX62N2CUO7NGRWCI7GUHVC","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08018","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T19:27:30Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e549425927e563045cf01f36d69c732a33040666d60f6a43d08c24efb7e83782","abstract_canon_sha256":"ff58b4d8f61fcbf9322ff1812d99c01ec99fe4649903346eb1fb6d7c34abd13e"},"schema_version":"1.0"},"canonical_sha256":"fc23a9dfda6e85477da68d848f9a87a8a8f678b88a2b31d60d136c86787d8399","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:50.937814Z","signature_b64":"FjwoOC7ZQPGuctv5idhhabTVsMtHbQxRooQ7pxuQLje24m/HRe/0iSMPxIreStVjHFBRpJuwVeI0AzPDpbfjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc23a9dfda6e85477da68d848f9a87a8a8f678b88a2b31d60d136c86787d8399","last_reissued_at":"2026-07-05T08:44:50.937370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:50.937370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08018","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8fZpMqZYte9oaQJJCkwG3APMkYNmapzQkk8Q8+2nP8GmY7jhRg50SGEdutNpdo0Tk1bR3B1wq2vG+W1tmNbDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:45:04.855744Z"},"content_sha256":"3ebae61c57fc0d74579af45cee5d9af0a22211f0461aa76f8bba5f20707299be","schema_version":"1.0","event_id":"sha256:3ebae61c57fc0d74579af45cee5d9af0a22211f0461aa76f8bba5f20707299be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7QR2TX62N2CUO7NGRWCI7GUHVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nearest Neighbour Score Estimators for Diffusion Generative Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam \\'Scibior, Berend Zwartsenberg, Dylan Green, Frank Wood, Jonathan Wilder Lavington, Ke Zhang, Matthew Niedoba, Saeid Naderiparizi, Setareh Dabiri, Vasileios Lioutas, Xiaoxuan Liang, Yunpeng Liu","submitted_at":"2024-02-12T19:27:30Z","abstract_excerpt":"Score function estimation is the cornerstone of both training and sampling from diffusion generative models. Despite this fact, the most commonly used estimators are either biased neural network approximations or high variance Monte Carlo estimators based on the conditional score. We introduce a novel nearest neighbour score function estimator which utilizes multiple samples from the training set to dramatically decrease estimator variance. We leverage our low variance estimator in two compelling applications. Training consistency models with our estimator, we report a significant increase in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08018","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/2402.08018/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"524y9TWqAqHzp++d8+v3a42A38EA5luOil4pO8jm1Ym7EXyvHjVVs9iuNwlSOi9/9rn3hpd3u+So3dwbLWqKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:45:04.856161Z"},"content_sha256":"ec1f1827e34d2a927dedd4bc44b21f83e88166349fc3491121a735b6f6809168","schema_version":"1.0","event_id":"sha256:ec1f1827e34d2a927dedd4bc44b21f83e88166349fc3491121a735b6f6809168"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QR2TX62N2CUO7NGRWCI7GUHVC/bundle.json","state_url":"https://pith.science/pith/7QR2TX62N2CUO7NGRWCI7GUHVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QR2TX62N2CUO7NGRWCI7GUHVC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T11:45:04Z","links":{"resolver":"https://pith.science/pith/7QR2TX62N2CUO7NGRWCI7GUHVC","bundle":"https://pith.science/pith/7QR2TX62N2CUO7NGRWCI7GUHVC/bundle.json","state":"https://pith.science/pith/7QR2TX62N2CUO7NGRWCI7GUHVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QR2TX62N2CUO7NGRWCI7GUHVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7QR2TX62N2CUO7NGRWCI7GUHVC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ff58b4d8f61fcbf9322ff1812d99c01ec99fe4649903346eb1fb6d7c34abd13e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T19:27:30Z","title_canon_sha256":"e549425927e563045cf01f36d69c732a33040666d60f6a43d08c24efb7e83782"},"schema_version":"1.0","source":{"id":"2402.08018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08018","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08018v2","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08018","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"7QR2TX62N2CU","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"7QR2TX62N2CUO7NG","created_at":"2026-07-05T08:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"7QR2TX62","created_at":"2026-07-05T08:44:50Z"}],"graph_snapshots":[{"event_id":"sha256:ec1f1827e34d2a927dedd4bc44b21f83e88166349fc3491121a735b6f6809168","target":"graph","created_at":"2026-07-05T08:44:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.08018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Score function estimation is the cornerstone of both training and sampling from diffusion generative models. Despite this fact, the most commonly used estimators are either biased neural network approximations or high variance Monte Carlo estimators based on the conditional score. We introduce a novel nearest neighbour score function estimator which utilizes multiple samples from the training set to dramatically decrease estimator variance. We leverage our low variance estimator in two compelling applications. Training consistency models with our estimator, we report a significant increase in ","authors_text":"Adam \\'Scibior, Berend Zwartsenberg, Dylan Green, Frank Wood, Jonathan Wilder Lavington, Ke Zhang, Matthew Niedoba, Saeid Naderiparizi, Setareh Dabiri, Vasileios Lioutas, Xiaoxuan Liang, Yunpeng Liu","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T19:27:30Z","title":"Nearest Neighbour Score Estimators for Diffusion Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08018","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3ebae61c57fc0d74579af45cee5d9af0a22211f0461aa76f8bba5f20707299be","target":"record","created_at":"2026-07-05T08:44:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ff58b4d8f61fcbf9322ff1812d99c01ec99fe4649903346eb1fb6d7c34abd13e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T19:27:30Z","title_canon_sha256":"e549425927e563045cf01f36d69c732a33040666d60f6a43d08c24efb7e83782"},"schema_version":"1.0","source":{"id":"2402.08018","kind":"arxiv","version":2}},"canonical_sha256":"fc23a9dfda6e85477da68d848f9a87a8a8f678b88a2b31d60d136c86787d8399","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc23a9dfda6e85477da68d848f9a87a8a8f678b88a2b31d60d136c86787d8399","first_computed_at":"2026-07-05T08:44:50.937370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:50.937370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FjwoOC7ZQPGuctv5idhhabTVsMtHbQxRooQ7pxuQLje24m/HRe/0iSMPxIreStVjHFBRpJuwVeI0AzPDpbfjDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:50.937814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ebae61c57fc0d74579af45cee5d9af0a22211f0461aa76f8bba5f20707299be","sha256:ec1f1827e34d2a927dedd4bc44b21f83e88166349fc3491121a735b6f6809168"],"state_sha256":"1b3768307a0569e42c7b0bb05e825e5193c0bfef9b9b4e607a5709525d7c9b1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mMWYZaPRP0ORYp8YOI9NGA4ZpVvLhcM3eCnsceeRw+gLW2VcoFxY9gaq02Jblf8EBkGt0IQShdycXHcDjMJ9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:45:04.858120Z","bundle_sha256":"361c719d25a896de9c2c50b7c2dc6a47c8e081791b8a66e176e8e5a2b0298593"}}