{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2KHGD3GVEQM57QC4LY2L55ABEC","short_pith_number":"pith:2KHGD3GV","schema_version":"1.0","canonical_sha256":"d28e61ecd52419dfc05c5e34bef40120b3f6a5c48d08c12235c65deb5f7b24dd","source":{"kind":"arxiv","id":"2202.12176","version":1},"attestation_state":"computed","paper":{"title":"Clarifying MCMC-based training of modern EBMs : Contrastive Divergence versus Maximum Likelihood","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guillaume Lajoie, L\\'eo Gagnon","submitted_at":"2022-02-24T16:21:11Z","abstract_excerpt":"The Energy-Based Model (EBM) framework is a very general approach to generative modeling that tries to learn and exploit probability distributions only defined though unnormalized scores. It has risen in popularity recently thanks to the impressive results obtained in image generation by parameterizing the distribution with Convolutional Neural Networks (CNN). However, the motivation and theoretical foundations behind modern EBMs are often absent from recent papers and this sometimes results in some confusion. In particular, the theoretical justifications behind the popular MCMC-based learning"},"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":"2202.12176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T16:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"288062379fd2e3fe5c902690b4e1229286415c521cc511b24f2f8dea64946881","abstract_canon_sha256":"5d707d7a4fa991b345fcf2d0ecae8d5fe2d0a8b6af88681369340b1d1bfe11eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:50.781220Z","signature_b64":"SJ3l6+l6rlQnAoUL7bXsEl6n1SX+O3G5qB+IoHJ3kvC30xc1etXHhjAT8fl/pNSYECoSOBxNeKHmD7d8Yot3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d28e61ecd52419dfc05c5e34bef40120b3f6a5c48d08c12235c65deb5f7b24dd","last_reissued_at":"2026-07-05T03:59:50.780756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:50.780756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clarifying MCMC-based training of modern EBMs : Contrastive Divergence versus Maximum Likelihood","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guillaume Lajoie, L\\'eo Gagnon","submitted_at":"2022-02-24T16:21:11Z","abstract_excerpt":"The Energy-Based Model (EBM) framework is a very general approach to generative modeling that tries to learn and exploit probability distributions only defined though unnormalized scores. It has risen in popularity recently thanks to the impressive results obtained in image generation by parameterizing the distribution with Convolutional Neural Networks (CNN). However, the motivation and theoretical foundations behind modern EBMs are often absent from recent papers and this sometimes results in some confusion. In particular, the theoretical justifications behind the popular MCMC-based learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12176","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/2202.12176/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":"2202.12176","created_at":"2026-07-05T03:59:50.780813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.12176v1","created_at":"2026-07-05T03:59:50.780813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12176","created_at":"2026-07-05T03:59:50.780813+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KHGD3GVEQM5","created_at":"2026-07-05T03:59:50.780813+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KHGD3GVEQM57QC4","created_at":"2026-07-05T03:59:50.780813+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KHGD3GV","created_at":"2026-07-05T03:59:50.780813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31660","citing_title":"Contrastive Regularization of Machine Learning Potentials","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC","json":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC.json","graph_json":"https://pith.science/api/pith-number/2KHGD3GVEQM57QC4LY2L55ABEC/graph.json","events_json":"https://pith.science/api/pith-number/2KHGD3GVEQM57QC4LY2L55ABEC/events.json","paper":"https://pith.science/paper/2KHGD3GV"},"agent_actions":{"view_html":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC","download_json":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC.json","view_paper":"https://pith.science/paper/2KHGD3GV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.12176&json=true","fetch_graph":"https://pith.science/api/pith-number/2KHGD3GVEQM57QC4LY2L55ABEC/graph.json","fetch_events":"https://pith.science/api/pith-number/2KHGD3GVEQM57QC4LY2L55ABEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC/action/storage_attestation","attest_author":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC/action/author_attestation","sign_citation":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC/action/citation_signature","submit_replication":"https://pith.science/pith/2KHGD3GVEQM57QC4LY2L55ABEC/action/replication_record"}},"created_at":"2026-07-05T03:59:50.780813+00:00","updated_at":"2026-07-05T03:59:50.780813+00:00"}