{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XUUVJK6X7AJ3JFO7FE73WMZN4P","short_pith_number":"pith:XUUVJK6X","schema_version":"1.0","canonical_sha256":"bd2954abd7f813b495df293fbb332de3ec4e59b56c7e40fd1d8be57bd0015b0a","source":{"kind":"arxiv","id":"1812.10907","version":2},"attestation_state":"computed","paper":{"title":"Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Erik Nijkamp, Mitch Hill, Song-Chun Zhu, Tian Han, Xiaolin Fang, Ying Nian Wu","submitted_at":"2018-12-28T06:35:39Z","abstract_excerpt":"This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, and contrastive divergence in a unified probabilistic formulation. This unification makes the processes of sampling, inference, energy evaluation readily available without the need for costly Markov chain Monte Carlo methods. Our experiments demonstrate that the divergence triangle"},"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":"1812.10907","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-28T06:35:39Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c77656c4089641ec6afeba4f6355e2bc6e3b141f88d202e69c9109fb128ef4f0","abstract_canon_sha256":"0264a83e3f964199a1351be11a75a89b76ee5112c45ab5d6d11ba377c0e296fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:03.022838Z","signature_b64":"lGpoiVaFaqdlsld305ADU3LTXW1NaCayeH8FboKXFsq2NGoMJp0DwK466oIpFwu57lba2nm8S4LyHAN7BxAlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd2954abd7f813b495df293fbb332de3ec4e59b56c7e40fd1d8be57bd0015b0a","last_reissued_at":"2026-05-17T23:55:03.022310Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:03.022310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Erik Nijkamp, Mitch Hill, Song-Chun Zhu, Tian Han, Xiaolin Fang, Ying Nian Wu","submitted_at":"2018-12-28T06:35:39Z","abstract_excerpt":"This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, and contrastive divergence in a unified probabilistic formulation. This unification makes the processes of sampling, inference, energy evaluation readily available without the need for costly Markov chain Monte Carlo methods. Our experiments demonstrate that the divergence triangle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10907","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":""},"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":"1812.10907","created_at":"2026-05-17T23:55:03.022406+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10907v2","created_at":"2026-05-17T23:55:03.022406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10907","created_at":"2026-05-17T23:55:03.022406+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUUVJK6X7AJ3","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUUVJK6X7AJ3JFO7","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUUVJK6X","created_at":"2026-05-18T12:33:01.666342+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/XUUVJK6X7AJ3JFO7FE73WMZN4P","json":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P.json","graph_json":"https://pith.science/api/pith-number/XUUVJK6X7AJ3JFO7FE73WMZN4P/graph.json","events_json":"https://pith.science/api/pith-number/XUUVJK6X7AJ3JFO7FE73WMZN4P/events.json","paper":"https://pith.science/paper/XUUVJK6X"},"agent_actions":{"view_html":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P","download_json":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P.json","view_paper":"https://pith.science/paper/XUUVJK6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10907&json=true","fetch_graph":"https://pith.science/api/pith-number/XUUVJK6X7AJ3JFO7FE73WMZN4P/graph.json","fetch_events":"https://pith.science/api/pith-number/XUUVJK6X7AJ3JFO7FE73WMZN4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P/action/storage_attestation","attest_author":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P/action/author_attestation","sign_citation":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P/action/citation_signature","submit_replication":"https://pith.science/pith/XUUVJK6X7AJ3JFO7FE73WMZN4P/action/replication_record"}},"created_at":"2026-05-17T23:55:03.022406+00:00","updated_at":"2026-05-17T23:55:03.022406+00:00"}