{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CLADPXSE5TYIBO54GU6LZ5I2IE","short_pith_number":"pith:CLADPXSE","canonical_record":{"source":{"id":"1705.05263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-15T14:24:01Z","cross_cats_sorted":[],"title_canon_sha256":"24ff31e939170db68451657bc17ffb706975deb3aaf660b20152b5dc3927cfad","abstract_canon_sha256":"b4900ecba87a616cc70f29811ab90428a5cdf9a010124eb0dd6fd1929b918c0b"},"schema_version":"1.0"},"canonical_sha256":"12c037de44ecf080bbbc353cbcf51a41030a2fb3afa8824146aa8d43b236a2cc","source":{"kind":"arxiv","id":"1705.05263","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.05263","created_at":"2026-05-18T00:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"1705.05263v1","created_at":"2026-05-18T00:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05263","created_at":"2026-05-18T00:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"CLADPXSE5TYI","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CLADPXSE5TYIBO54","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CLADPXSE","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CLADPXSE5TYIBO54GU6LZ5I2IE","target":"record","payload":{"canonical_record":{"source":{"id":"1705.05263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-15T14:24:01Z","cross_cats_sorted":[],"title_canon_sha256":"24ff31e939170db68451657bc17ffb706975deb3aaf660b20152b5dc3927cfad","abstract_canon_sha256":"b4900ecba87a616cc70f29811ab90428a5cdf9a010124eb0dd6fd1929b918c0b"},"schema_version":"1.0"},"canonical_sha256":"12c037de44ecf080bbbc353cbcf51a41030a2fb3afa8824146aa8d43b236a2cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:30.969654Z","signature_b64":"QV2LAmIvxj6cciDR0fW/c9D25nKUwEUWbR9FkgHYXZhZ/BCLPT3Sj/XfkV5w0Hra/OWTZ2WsXvhFNlTDTuJgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12c037de44ecf080bbbc353cbcf51a41030a2fb3afa8824146aa8d43b236a2cc","last_reissued_at":"2026-05-18T00:44:30.969196Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:30.969196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.05263","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3B4OAlf+H5z4UsI20CBdvH2Lx4Sby3lWV2oMGcesY2gZLXHaJJ0OQNJb3+wW0ZOyUb11F3/Os1SyCm0JNvdbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:48:07.405894Z"},"content_sha256":"db799534564359d0bfad8e7ae09d4364d6d24ef0fb1a788693467b049b2a7859","schema_version":"1.0","event_id":"sha256:db799534564359d0bfad8e7ae09d4364d6d24ef0fb1a788693467b049b2a7859"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CLADPXSE5TYIBO54GU6LZ5I2IE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comparison of Maximum Likelihood and GAN-based training of Real NVPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Balaji Lakshminarayanan, Benigno Uria, Daan Wierstra, Ivo Danihelka, Peter Dayan","submitted_at":"2017-05-15T14:24:01Z","abstract_excerpt":"We train a generator by maximum likelihood and we also train the same generator architecture by Wasserstein GAN. We then compare the generated samples, exact log-probability densities and approximate Wasserstein distances. We show that an independent critic trained to approximate Wasserstein distance between the validation set and the generator distribution helps detect overfitting. Finally, we use ideas from the one-shot learning literature to develop a novel fast learning critic."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05263","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LOcbL/ZaEs+0QoFhx+ilHPTW9X1AJJ9JFhfvF+noY3ZfNKp4iuA68b8hQHFzDDVUAJeAkIdg0eRZ4GXJs6rzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:48:07.406720Z"},"content_sha256":"57718f29d01e9c959311a0885994adf38893e2bfa293ca639df3da1e6d92b6e3","schema_version":"1.0","event_id":"sha256:57718f29d01e9c959311a0885994adf38893e2bfa293ca639df3da1e6d92b6e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLADPXSE5TYIBO54GU6LZ5I2IE/bundle.json","state_url":"https://pith.science/pith/CLADPXSE5TYIBO54GU6LZ5I2IE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLADPXSE5TYIBO54GU6LZ5I2IE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T20:48:07Z","links":{"resolver":"https://pith.science/pith/CLADPXSE5TYIBO54GU6LZ5I2IE","bundle":"https://pith.science/pith/CLADPXSE5TYIBO54GU6LZ5I2IE/bundle.json","state":"https://pith.science/pith/CLADPXSE5TYIBO54GU6LZ5I2IE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLADPXSE5TYIBO54GU6LZ5I2IE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CLADPXSE5TYIBO54GU6LZ5I2IE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b4900ecba87a616cc70f29811ab90428a5cdf9a010124eb0dd6fd1929b918c0b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-15T14:24:01Z","title_canon_sha256":"24ff31e939170db68451657bc17ffb706975deb3aaf660b20152b5dc3927cfad"},"schema_version":"1.0","source":{"id":"1705.05263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.05263","created_at":"2026-05-18T00:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"1705.05263v1","created_at":"2026-05-18T00:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05263","created_at":"2026-05-18T00:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"CLADPXSE5TYI","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CLADPXSE5TYIBO54","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CLADPXSE","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:57718f29d01e9c959311a0885994adf38893e2bfa293ca639df3da1e6d92b6e3","target":"graph","created_at":"2026-05-18T00:44:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We train a generator by maximum likelihood and we also train the same generator architecture by Wasserstein GAN. We then compare the generated samples, exact log-probability densities and approximate Wasserstein distances. We show that an independent critic trained to approximate Wasserstein distance between the validation set and the generator distribution helps detect overfitting. Finally, we use ideas from the one-shot learning literature to develop a novel fast learning critic.","authors_text":"Balaji Lakshminarayanan, Benigno Uria, Daan Wierstra, Ivo Danihelka, Peter Dayan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-15T14:24:01Z","title":"Comparison of Maximum Likelihood and GAN-based training of Real NVPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05263","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db799534564359d0bfad8e7ae09d4364d6d24ef0fb1a788693467b049b2a7859","target":"record","created_at":"2026-05-18T00:44:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b4900ecba87a616cc70f29811ab90428a5cdf9a010124eb0dd6fd1929b918c0b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-15T14:24:01Z","title_canon_sha256":"24ff31e939170db68451657bc17ffb706975deb3aaf660b20152b5dc3927cfad"},"schema_version":"1.0","source":{"id":"1705.05263","kind":"arxiv","version":1}},"canonical_sha256":"12c037de44ecf080bbbc353cbcf51a41030a2fb3afa8824146aa8d43b236a2cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12c037de44ecf080bbbc353cbcf51a41030a2fb3afa8824146aa8d43b236a2cc","first_computed_at":"2026-05-18T00:44:30.969196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:30.969196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QV2LAmIvxj6cciDR0fW/c9D25nKUwEUWbR9FkgHYXZhZ/BCLPT3Sj/XfkV5w0Hra/OWTZ2WsXvhFNlTDTuJgDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:30.969654Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.05263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db799534564359d0bfad8e7ae09d4364d6d24ef0fb1a788693467b049b2a7859","sha256:57718f29d01e9c959311a0885994adf38893e2bfa293ca639df3da1e6d92b6e3"],"state_sha256":"b42196e0729b78e79775fdf71e56afc5a363fbfda633e6dc373f080675025021"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cqpNPMVzbcA0bKJhroSwXP5ERDQJ0pcpTt2Ae2HjAtX/L6n3y5Z5IEBthaxD+lPjHfhDrRHS0Q6uMxQf6Ga5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:48:07.410768Z","bundle_sha256":"022431234bd8bacf5c5753f9a6909bae6efea85c5b9ede498419bf1c6585b6b5"}}