{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FYZJ533RIBCFVZN5IQXCTFSKEI","short_pith_number":"pith:FYZJ533R","schema_version":"1.0","canonical_sha256":"2e329eef7140445ae5bd442e29964a2234653b02d885c093f0e3e57920fad030","source":{"kind":"arxiv","id":"2105.14080","version":1},"attestation_state":"computed","paper":{"title":"Gotta Go Fast When Generating Data with Score-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Ke Li, R\\'emi Pich\\'e-Taillefer, Tal Kachman","submitted_at":"2021-05-28T19:48:51Z","abstract_excerpt":"Score-based (denoising diffusion) generative models have recently gained a lot of success in generating realistic and diverse data. These approaches define a forward diffusion process for transforming data to noise and generate data by reversing it (thereby going from noise to data). Unfortunately, current score-based models generate data very slowly due to the sheer number of score network evaluations required by numerical SDE solvers.\n  In this work, we aim to accelerate this process by devising a more efficient SDE solver. Existing approaches rely on the Euler-Maruyama (EM) solver, which us"},"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":"2105.14080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T19:48:51Z","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"title_canon_sha256":"68b8c4820b798eab1e06bc499aab0d79f6ec4a59cf23482c18695ea92ec47342","abstract_canon_sha256":"c54460228d06ee202722640eb865a3a366c04e730144dfd2621779abd2369995"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:20.021780Z","signature_b64":"UTnlyjiumZp63Tk++81PDCPxJG2GVRCX6r/AZEdDydreH6rSK7WnlJbQWIf7+uMG42AraSKMlGM0hhB7oUvuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e329eef7140445ae5bd442e29964a2234653b02d885c093f0e3e57920fad030","last_reissued_at":"2026-07-05T02:44:20.021269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:20.021269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gotta Go Fast When Generating Data with Score-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Ke Li, R\\'emi Pich\\'e-Taillefer, Tal Kachman","submitted_at":"2021-05-28T19:48:51Z","abstract_excerpt":"Score-based (denoising diffusion) generative models have recently gained a lot of success in generating realistic and diverse data. These approaches define a forward diffusion process for transforming data to noise and generate data by reversing it (thereby going from noise to data). Unfortunately, current score-based models generate data very slowly due to the sheer number of score network evaluations required by numerical SDE solvers.\n  In this work, we aim to accelerate this process by devising a more efficient SDE solver. Existing approaches rely on the Euler-Maruyama (EM) solver, which us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14080","kind":"arxiv","version":1},"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/2105.14080/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":"2105.14080","created_at":"2026-07-05T02:44:20.021381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14080v1","created_at":"2026-07-05T02:44:20.021381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14080","created_at":"2026-07-05T02:44:20.021381+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYZJ533RIBCF","created_at":"2026-07-05T02:44:20.021381+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYZJ533RIBCFVZN5","created_at":"2026-07-05T02:44:20.021381+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYZJ533R","created_at":"2026-07-05T02:44:20.021381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27192","citing_title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07835","citing_title":"Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31026","citing_title":"OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17119","citing_title":"Diffusion and Flow Matching Models for Tabular Data: A Survey","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04938","citing_title":"Improved DDIM Sampling with Moment Matching Gaussian Mixtures","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14429","citing_title":"Compositional amortized inference for large-scale hierarchical Bayesian models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01629","citing_title":"Lipschitz-Guided Design of Interpolation Schedules in Generative Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01095","citing_title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2206.00364","citing_title":"Elucidating the Design Space of Diffusion-Based Generative Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2310.04378","citing_title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14687","citing_title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2202.00512","citing_title":"Progressive Distillation for Fast Sampling of Diffusion Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI","json":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI.json","graph_json":"https://pith.science/api/pith-number/FYZJ533RIBCFVZN5IQXCTFSKEI/graph.json","events_json":"https://pith.science/api/pith-number/FYZJ533RIBCFVZN5IQXCTFSKEI/events.json","paper":"https://pith.science/paper/FYZJ533R"},"agent_actions":{"view_html":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI","download_json":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI.json","view_paper":"https://pith.science/paper/FYZJ533R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14080&json=true","fetch_graph":"https://pith.science/api/pith-number/FYZJ533RIBCFVZN5IQXCTFSKEI/graph.json","fetch_events":"https://pith.science/api/pith-number/FYZJ533RIBCFVZN5IQXCTFSKEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI/action/storage_attestation","attest_author":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI/action/author_attestation","sign_citation":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI/action/citation_signature","submit_replication":"https://pith.science/pith/FYZJ533RIBCFVZN5IQXCTFSKEI/action/replication_record"}},"created_at":"2026-07-05T02:44:20.021381+00:00","updated_at":"2026-07-05T02:44:20.021381+00:00"}