{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JFKP4MROUVF5ZGUAJOTKTQVMLA","short_pith_number":"pith:JFKP4MRO","schema_version":"1.0","canonical_sha256":"4954fe322ea54bdc9a804ba6a9c2ac583c85925d1102e205b0ac4d2b3794cf68","source":{"kind":"arxiv","id":"2006.06897","version":2},"attestation_state":"computed","paper":{"title":"MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Pang, Erik Nijkamp, Pavel Sountsov, Ruiqi Gao, Song-Chun Zhu, Srinivas Vasudevan, Ying Nian Wu","submitted_at":"2020-06-12T01:25:51Z","abstract_excerpt":"Learning energy-based model (EBM) requires MCMC sampling of the learned model as an inner loop of the learning algorithm. However, MCMC sampling of EBMs in high-dimensional data space is generally not mixing, because the energy function, which is usually parametrized by a deep network, is highly multi-modal in the data space. This is a serious handicap for both theory and practice of EBMs. In this paper, we propose to learn an EBM with a flow-based model (or in general a latent variable model) serving as a backbone, so that the EBM is a correction or an exponential tilting of the flow-based mo"},"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":"2006.06897","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-12T01:25:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a13cc69bf9b40e11713ad109613cfa24a907915649efe7ddb194e44d4290bbf","abstract_canon_sha256":"8bc2d5bd9e7a09fd8e21ec9c86c49409a16fd7afe31f622feed2d5a0456b1aaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:29.258123Z","signature_b64":"JDA6DZxB41KX7r0kyw4PEfnjf++g0o+6/LG+nuyKkTuPXvs8ceCyQWwhR4Gu3XggVvfD9gug8d6NK0NrxQyDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4954fe322ea54bdc9a804ba6a9c2ac583c85925d1102e205b0ac4d2b3794cf68","last_reissued_at":"2026-07-05T04:05:29.257615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:29.257615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Pang, Erik Nijkamp, Pavel Sountsov, Ruiqi Gao, Song-Chun Zhu, Srinivas Vasudevan, Ying Nian Wu","submitted_at":"2020-06-12T01:25:51Z","abstract_excerpt":"Learning energy-based model (EBM) requires MCMC sampling of the learned model as an inner loop of the learning algorithm. However, MCMC sampling of EBMs in high-dimensional data space is generally not mixing, because the energy function, which is usually parametrized by a deep network, is highly multi-modal in the data space. This is a serious handicap for both theory and practice of EBMs. In this paper, we propose to learn an EBM with a flow-based model (or in general a latent variable model) serving as a backbone, so that the EBM is a correction or an exponential tilting of the flow-based mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06897","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/2006.06897/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":"2006.06897","created_at":"2026-07-05T04:05:29.257679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06897v2","created_at":"2026-07-05T04:05:29.257679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06897","created_at":"2026-07-05T04:05:29.257679+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFKP4MROUVF5","created_at":"2026-07-05T04:05:29.257679+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFKP4MROUVF5ZGUA","created_at":"2026-07-05T04:05:29.257679+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFKP4MRO","created_at":"2026-07-05T04:05:29.257679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01793","citing_title":"ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA","json":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA.json","graph_json":"https://pith.science/api/pith-number/JFKP4MROUVF5ZGUAJOTKTQVMLA/graph.json","events_json":"https://pith.science/api/pith-number/JFKP4MROUVF5ZGUAJOTKTQVMLA/events.json","paper":"https://pith.science/paper/JFKP4MRO"},"agent_actions":{"view_html":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA","download_json":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA.json","view_paper":"https://pith.science/paper/JFKP4MRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06897&json=true","fetch_graph":"https://pith.science/api/pith-number/JFKP4MROUVF5ZGUAJOTKTQVMLA/graph.json","fetch_events":"https://pith.science/api/pith-number/JFKP4MROUVF5ZGUAJOTKTQVMLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA/action/storage_attestation","attest_author":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA/action/author_attestation","sign_citation":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA/action/citation_signature","submit_replication":"https://pith.science/pith/JFKP4MROUVF5ZGUAJOTKTQVMLA/action/replication_record"}},"created_at":"2026-07-05T04:05:29.257679+00:00","updated_at":"2026-07-05T04:05:29.257679+00:00"}