{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:L7JJXLNXYDOKDMVJKSJSIRZEWO","short_pith_number":"pith:L7JJXLNX","schema_version":"1.0","canonical_sha256":"5fd29badb7c0dca1b2a95493244724b3a29a6f8e603520505f85f1211f74e025","source":{"kind":"arxiv","id":"1705.08868","version":2},"attestation_state":"computed","paper":{"title":"Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Grover, Manik Dhar, Stefano Ermon","submitted_at":"2017-05-24T17:11:25Z","abstract_excerpt":"Adversarial learning of probabilistic models has recently emerged as a promising alternative to maximum likelihood. Implicit models such as generative adversarial networks (GAN) often generate better samples compared to explicit models trained by maximum likelihood. Yet, GANs sidestep the characterization of an explicit density which makes quantitative evaluations challenging. To bridge this gap, we propose Flow-GANs, a generative adversarial network for which we can perform exact likelihood evaluation, thus supporting both adversarial and maximum likelihood training. When trained adversariall"},"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":"1705.08868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-24T17:11:25Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"6a85213e1706edfdffc102125497141e0c09d071044af594d5607d88629852f6","abstract_canon_sha256":"41b48a106ce2f99a2a2e8327233920eea46ba39cbe56f805cf58ac3baf670c91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:46.168989Z","signature_b64":"506HepEh/3Olta7Wzr02kc6uGFrzF3C4OUCQijAc2NVX3PDIYdipBzn2jmQCn57RN3taIGY2LDvweg/ghKlpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fd29badb7c0dca1b2a95493244724b3a29a6f8e603520505f85f1211f74e025","last_reissued_at":"2026-05-18T00:26:46.168183Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:46.168183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Grover, Manik Dhar, Stefano Ermon","submitted_at":"2017-05-24T17:11:25Z","abstract_excerpt":"Adversarial learning of probabilistic models has recently emerged as a promising alternative to maximum likelihood. Implicit models such as generative adversarial networks (GAN) often generate better samples compared to explicit models trained by maximum likelihood. Yet, GANs sidestep the characterization of an explicit density which makes quantitative evaluations challenging. To bridge this gap, we propose Flow-GANs, a generative adversarial network for which we can perform exact likelihood evaluation, thus supporting both adversarial and maximum likelihood training. When trained adversariall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08868","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":"1705.08868","created_at":"2026-05-18T00:26:46.168326+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08868v2","created_at":"2026-05-18T00:26:46.168326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08868","created_at":"2026-05-18T00:26:46.168326+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7JJXLNXYDOK","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7JJXLNXYDOKDMVJ","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7JJXLNX","created_at":"2026-05-18T12:31:28.150371+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/L7JJXLNXYDOKDMVJKSJSIRZEWO","json":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO.json","graph_json":"https://pith.science/api/pith-number/L7JJXLNXYDOKDMVJKSJSIRZEWO/graph.json","events_json":"https://pith.science/api/pith-number/L7JJXLNXYDOKDMVJKSJSIRZEWO/events.json","paper":"https://pith.science/paper/L7JJXLNX"},"agent_actions":{"view_html":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO","download_json":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO.json","view_paper":"https://pith.science/paper/L7JJXLNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08868&json=true","fetch_graph":"https://pith.science/api/pith-number/L7JJXLNXYDOKDMVJKSJSIRZEWO/graph.json","fetch_events":"https://pith.science/api/pith-number/L7JJXLNXYDOKDMVJKSJSIRZEWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO/action/storage_attestation","attest_author":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO/action/author_attestation","sign_citation":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO/action/citation_signature","submit_replication":"https://pith.science/pith/L7JJXLNXYDOKDMVJKSJSIRZEWO/action/replication_record"}},"created_at":"2026-05-18T00:26:46.168326+00:00","updated_at":"2026-05-18T00:26:46.168326+00:00"}