{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B7TUFM57ZKVL4KP4E6LSDIM7L7","short_pith_number":"pith:B7TUFM57","schema_version":"1.0","canonical_sha256":"0fe742b3bfcaaabe29fc279721a19f5ff2f6491a3357bfeb8f9758f8a219a4aa","source":{"kind":"arxiv","id":"2307.01668","version":1},"attestation_state":"computed","paper":{"title":"Training Energy-Based Models with Diffusion Contrastive Divergences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Jiang, Jiacheng Sun, Tianyang Hu, Weijian Luo, Zhenguo Li, Zhihua Zhang","submitted_at":"2023-07-04T12:00:06Z","abstract_excerpt":"Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an irreconcilable trade-off between the computational burden and the validity of the CD. Running MCMCs till convergence is computationally intensive. On the other hand, short-run MCMC brings in an extra non-negligible parameter gradient term that is difficult to handle. In this paper, we provide a general interpretation of CD, viewing it as a special instance "},"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":"2307.01668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T12:00:06Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"496b0e9e75e81c8bae8f7ed3fd7e7508bf1e98e845af903064f0e0f15a0dbb59","abstract_canon_sha256":"755f2c2d987580d9e62336d8bf750c9eb0e800fb5345aedaf1972e06a00d4714"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:59.390864Z","signature_b64":"gOST0tvJaOb1PRwSLqPACIcApV8tTQmGgTQjGCBOMhTAjFI3ZxAfKEmYAGwWGOzEx1QWu2WjIPwoXS5yHC9uCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fe742b3bfcaaabe29fc279721a19f5ff2f6491a3357bfeb8f9758f8a219a4aa","last_reissued_at":"2026-07-05T06:27:59.390469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:59.390469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Energy-Based Models with Diffusion Contrastive Divergences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Jiang, Jiacheng Sun, Tianyang Hu, Weijian Luo, Zhenguo Li, Zhihua Zhang","submitted_at":"2023-07-04T12:00:06Z","abstract_excerpt":"Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an irreconcilable trade-off between the computational burden and the validity of the CD. Running MCMCs till convergence is computationally intensive. On the other hand, short-run MCMC brings in an extra non-negligible parameter gradient term that is difficult to handle. In this paper, we provide a general interpretation of CD, viewing it as a special instance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01668","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/2307.01668/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":"2307.01668","created_at":"2026-07-05T06:27:59.390527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01668v1","created_at":"2026-07-05T06:27:59.390527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01668","created_at":"2026-07-05T06:27:59.390527+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7TUFM57ZKVL","created_at":"2026-07-05T06:27:59.390527+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7TUFM57ZKVL4KP4","created_at":"2026-07-05T06:27:59.390527+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7TUFM57","created_at":"2026-07-05T06:27:59.390527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7","json":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7.json","graph_json":"https://pith.science/api/pith-number/B7TUFM57ZKVL4KP4E6LSDIM7L7/graph.json","events_json":"https://pith.science/api/pith-number/B7TUFM57ZKVL4KP4E6LSDIM7L7/events.json","paper":"https://pith.science/paper/B7TUFM57"},"agent_actions":{"view_html":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7","download_json":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7.json","view_paper":"https://pith.science/paper/B7TUFM57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01668&json=true","fetch_graph":"https://pith.science/api/pith-number/B7TUFM57ZKVL4KP4E6LSDIM7L7/graph.json","fetch_events":"https://pith.science/api/pith-number/B7TUFM57ZKVL4KP4E6LSDIM7L7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7/action/storage_attestation","attest_author":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7/action/author_attestation","sign_citation":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7/action/citation_signature","submit_replication":"https://pith.science/pith/B7TUFM57ZKVL4KP4E6LSDIM7L7/action/replication_record"}},"created_at":"2026-07-05T06:27:59.390527+00:00","updated_at":"2026-07-05T06:27:59.390527+00:00"}