{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WZHGXU5IFJKPQ4FLLWR2I2JXW4","short_pith_number":"pith:WZHGXU5I","schema_version":"1.0","canonical_sha256":"b64e6bd3a82a54f870ab5da3a46937b714e3c9c601b177bb798dde3ab67ab42c","source":{"kind":"arxiv","id":"1611.01799","version":1},"attestation_state":"computed","paper":{"title":"Generative Adversarial Networks as Variational Training of Energy Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rogerio Feris, Shuangfei Zhai, Yu Cheng, Zhongfei Zhang","submitted_at":"2016-11-06T16:04:48Z","abstract_excerpt":"In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelihood (NLL) of an energy based model (EBM), where the model density $p(\\mathbf{x})$ is approximated by a variational distribution $q(\\mathbf{x})$ that is easy to sample from. The training of VGAN takes a two step procedure: given $p(\\mathbf{x})$, $q(\\mathbf{x})$ is updated to maximize the lower bound; $p(\\mathbf{x})$ is then updated one step with samples drawn from $q(\\mathbf{x})$ to decrease the lower bound. VGAN is i"},"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":"1611.01799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-06T16:04:48Z","cross_cats_sorted":[],"title_canon_sha256":"5246233b3a6011939d97aac4e2b862867b813f17e1694a56562a1e9c5b68007b","abstract_canon_sha256":"ee3a6a69b767afbe9fa73c3fdadae0d459e6cd16d775f6326065108dfd7a4478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:04.459950Z","signature_b64":"SZ2KbrkQ9DbztWyQwQEfJBT1iAPXie2WYohThq5yhn1dMzZxN9gn2NDXrcgY8aossUO1OHdK2JsOTRxppbJRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64e6bd3a82a54f870ab5da3a46937b714e3c9c601b177bb798dde3ab67ab42c","last_reissued_at":"2026-05-18T01:00:04.459343Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:04.459343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Adversarial Networks as Variational Training of Energy Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rogerio Feris, Shuangfei Zhai, Yu Cheng, Zhongfei Zhang","submitted_at":"2016-11-06T16:04:48Z","abstract_excerpt":"In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelihood (NLL) of an energy based model (EBM), where the model density $p(\\mathbf{x})$ is approximated by a variational distribution $q(\\mathbf{x})$ that is easy to sample from. The training of VGAN takes a two step procedure: given $p(\\mathbf{x})$, $q(\\mathbf{x})$ is updated to maximize the lower bound; $p(\\mathbf{x})$ is then updated one step with samples drawn from $q(\\mathbf{x})$ to decrease the lower bound. VGAN is i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01799","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":""},"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":"1611.01799","created_at":"2026-05-18T01:00:04.459441+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.01799v1","created_at":"2026-05-18T01:00:04.459441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01799","created_at":"2026-05-18T01:00:04.459441+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZHGXU5IFJKP","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZHGXU5IFJKPQ4FL","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZHGXU5I","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04609","citing_title":"Exploring bidirectional bounds for minimax-training of Energy-based models","ref_index":86,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4","json":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4.json","graph_json":"https://pith.science/api/pith-number/WZHGXU5IFJKPQ4FLLWR2I2JXW4/graph.json","events_json":"https://pith.science/api/pith-number/WZHGXU5IFJKPQ4FLLWR2I2JXW4/events.json","paper":"https://pith.science/paper/WZHGXU5I"},"agent_actions":{"view_html":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4","download_json":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4.json","view_paper":"https://pith.science/paper/WZHGXU5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.01799&json=true","fetch_graph":"https://pith.science/api/pith-number/WZHGXU5IFJKPQ4FLLWR2I2JXW4/graph.json","fetch_events":"https://pith.science/api/pith-number/WZHGXU5IFJKPQ4FLLWR2I2JXW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4/action/storage_attestation","attest_author":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4/action/author_attestation","sign_citation":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4/action/citation_signature","submit_replication":"https://pith.science/pith/WZHGXU5IFJKPQ4FLLWR2I2JXW4/action/replication_record"}},"created_at":"2026-05-18T01:00:04.459441+00:00","updated_at":"2026-05-18T01:00:04.459441+00:00"}