{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XE3J3TUGESLNTCLGGCX4SAVBBA","short_pith_number":"pith:XE3J3TUG","schema_version":"1.0","canonical_sha256":"b9369dce862496d9896630afc902a108280d972fa63e594677cc6e373a2a8e9e","source":{"kind":"arxiv","id":"1910.07762","version":2},"attestation_state":"computed","paper":{"title":"Learning Energy-Based Models in High-Dimensional Spaces with Multi-scale Denoising Score Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Friedrich T. Sommer, Yubei Chen, Zengyi Li","submitted_at":"2019-10-17T08:21:17Z","abstract_excerpt":"Energy-Based Models (EBMs) assign unnormalized log-probability to data samples. This functionality has a variety of applications, such as sample synthesis, data denoising, sample restoration, outlier detection, Bayesian reasoning, and many more. But training of EBMs using standard maximum likelihood is extremely slow because it requires sampling from the model distribution. Score matching potentially alleviates this problem. In particular, denoising score matching \\citep{vincent2011connection} has been successfully used to train EBMs. Using noisy data samples with one fixed noise level, these "},"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":"1910.07762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-17T08:21:17Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"8fd3615eccba6141e20c6b6d141b61c896050eada1d6a58410daeaf697091eff","abstract_canon_sha256":"d055ee886aa930b6ea24b7725ae0976580101be63f7a445d3c576e6058305d34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:33.751352Z","signature_b64":"QqueQbsY73VnWDnz7fEizluT9q1ltd7orBcFVjLSpvRsL/cC3i8f4wjwLxdKIXDWI9/OQhk3weHb3nOBeFAbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9369dce862496d9896630afc902a108280d972fa63e594677cc6e373a2a8e9e","last_reissued_at":"2026-07-05T00:27:33.750856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:33.750856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Energy-Based Models in High-Dimensional Spaces with Multi-scale Denoising Score Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Friedrich T. Sommer, Yubei Chen, Zengyi Li","submitted_at":"2019-10-17T08:21:17Z","abstract_excerpt":"Energy-Based Models (EBMs) assign unnormalized log-probability to data samples. This functionality has a variety of applications, such as sample synthesis, data denoising, sample restoration, outlier detection, Bayesian reasoning, and many more. But training of EBMs using standard maximum likelihood is extremely slow because it requires sampling from the model distribution. Score matching potentially alleviates this problem. In particular, denoising score matching \\citep{vincent2011connection} has been successfully used to train EBMs. Using noisy data samples with one fixed noise level, these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07762","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/1910.07762/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":"1910.07762","created_at":"2026-07-05T00:27:33.750916+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.07762v2","created_at":"2026-07-05T00:27:33.750916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07762","created_at":"2026-07-05T00:27:33.750916+00:00"},{"alias_kind":"pith_short_12","alias_value":"XE3J3TUGESLN","created_at":"2026-07-05T00:27:33.750916+00:00"},{"alias_kind":"pith_short_16","alias_value":"XE3J3TUGESLNTCLG","created_at":"2026-07-05T00:27:33.750916+00:00"},{"alias_kind":"pith_short_8","alias_value":"XE3J3TUG","created_at":"2026-07-05T00:27:33.750916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09685","citing_title":"Learning Unified Representations of Normalcy for Time Series Anomaly Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":170,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA","json":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA.json","graph_json":"https://pith.science/api/pith-number/XE3J3TUGESLNTCLGGCX4SAVBBA/graph.json","events_json":"https://pith.science/api/pith-number/XE3J3TUGESLNTCLGGCX4SAVBBA/events.json","paper":"https://pith.science/paper/XE3J3TUG"},"agent_actions":{"view_html":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA","download_json":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA.json","view_paper":"https://pith.science/paper/XE3J3TUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.07762&json=true","fetch_graph":"https://pith.science/api/pith-number/XE3J3TUGESLNTCLGGCX4SAVBBA/graph.json","fetch_events":"https://pith.science/api/pith-number/XE3J3TUGESLNTCLGGCX4SAVBBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA/action/storage_attestation","attest_author":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA/action/author_attestation","sign_citation":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA/action/citation_signature","submit_replication":"https://pith.science/pith/XE3J3TUGESLNTCLGGCX4SAVBBA/action/replication_record"}},"created_at":"2026-07-05T00:27:33.750916+00:00","updated_at":"2026-07-05T00:27:33.750916+00:00"}