{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UZ6LIHCPCFAXYYMHRKVSBDC6IV","short_pith_number":"pith:UZ6LIHCP","canonical_record":{"source":{"id":"1706.04223","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T19:00:53Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"326e28d84c2d03c270beb966b2b6bbc67594efab5f9bfa8df25354de48fb604b","abstract_canon_sha256":"92bc3dad56d84697daea5386cc9ca6d084e62672b0c6ca479cc125a7b1922ede"},"schema_version":"1.0"},"canonical_sha256":"a67cb41c4f11417c61878aab208c5e4554fadeaa9a76339e4ac7a790472b2890","source":{"kind":"arxiv","id":"1706.04223","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04223","created_at":"2026-05-18T00:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04223v3","created_at":"2026-05-18T00:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04223","created_at":"2026-05-18T00:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"UZ6LIHCPCFAX","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UZ6LIHCPCFAXYYMH","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UZ6LIHCP","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UZ6LIHCPCFAXYYMHRKVSBDC6IV","target":"record","payload":{"canonical_record":{"source":{"id":"1706.04223","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T19:00:53Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"326e28d84c2d03c270beb966b2b6bbc67594efab5f9bfa8df25354de48fb604b","abstract_canon_sha256":"92bc3dad56d84697daea5386cc9ca6d084e62672b0c6ca479cc125a7b1922ede"},"schema_version":"1.0"},"canonical_sha256":"a67cb41c4f11417c61878aab208c5e4554fadeaa9a76339e4ac7a790472b2890","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:06.341671Z","signature_b64":"KotSzbhdPHwxGqZp22Rxy8tFvzvXD6fbND27FkqoaGg92crDlsesuKIXC3U2iNzgwSHvjkoO6I9uKg+pAlB/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a67cb41c4f11417c61878aab208c5e4554fadeaa9a76339e4ac7a790472b2890","last_reissued_at":"2026-05-18T00:12:06.341099Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:06.341099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.04223","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X8mv8LIfmDhfBCvLwCdWyvTpT1asUgakS85muy8yNNPUdLVXY2Sjw7JC1iivUC5ijTNRSvLouMJ/PX0n5HMlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:06:00.147561Z"},"content_sha256":"d2bd455f54187bad3d4d94562ceff22f1de0439bfcbb1d0400f47853d4b9069e","schema_version":"1.0","event_id":"sha256:d2bd455f54187bad3d4d94562ceff22f1de0439bfcbb1d0400f47853d4b9069e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UZ6LIHCPCFAXYYMHRKVSBDC6IV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarially Regularized Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexander M. Rush, Jake Zhao (Junbo), Kelly Zhang, Yann LeCun, Yoon Kim","submitted_at":"2017-06-13T19:00:53Z","abstract_excerpt":"Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures, such as text sequences or discretized images, has proven to be more challenging. In this work, we propose a flexible method for training deep latent variable models of discrete structures. Our approach is based on the recently-proposed Wasserstein autoencoder (WAE) which formalizes the adversarial autoencoder (AAE) as an optimal transport problem. We first e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04223","kind":"arxiv","version":3},"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":"2026-05-18T00:12:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xSyfmS1jxkrVWgQb6hnvjyAGgxza3HUmfIr9v7tuwZBUq7Qw0D/w4KO6M5EgjzoOpXS9ozNjF147IeTOXRsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:06:00.148222Z"},"content_sha256":"957114832f230aa3227b5915034052fdbe031cbf5294ea7ce06f68cfec8d6770","schema_version":"1.0","event_id":"sha256:957114832f230aa3227b5915034052fdbe031cbf5294ea7ce06f68cfec8d6770"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UZ6LIHCPCFAXYYMHRKVSBDC6IV/bundle.json","state_url":"https://pith.science/pith/UZ6LIHCPCFAXYYMHRKVSBDC6IV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UZ6LIHCPCFAXYYMHRKVSBDC6IV/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":"2026-05-27T09:06:00Z","links":{"resolver":"https://pith.science/pith/UZ6LIHCPCFAXYYMHRKVSBDC6IV","bundle":"https://pith.science/pith/UZ6LIHCPCFAXYYMHRKVSBDC6IV/bundle.json","state":"https://pith.science/pith/UZ6LIHCPCFAXYYMHRKVSBDC6IV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UZ6LIHCPCFAXYYMHRKVSBDC6IV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UZ6LIHCPCFAXYYMHRKVSBDC6IV","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":"92bc3dad56d84697daea5386cc9ca6d084e62672b0c6ca479cc125a7b1922ede","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T19:00:53Z","title_canon_sha256":"326e28d84c2d03c270beb966b2b6bbc67594efab5f9bfa8df25354de48fb604b"},"schema_version":"1.0","source":{"id":"1706.04223","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04223","created_at":"2026-05-18T00:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04223v3","created_at":"2026-05-18T00:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04223","created_at":"2026-05-18T00:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"UZ6LIHCPCFAX","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UZ6LIHCPCFAXYYMH","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UZ6LIHCP","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:957114832f230aa3227b5915034052fdbe031cbf5294ea7ce06f68cfec8d6770","target":"graph","created_at":"2026-05-18T00:12:06Z","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":"Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures, such as text sequences or discretized images, has proven to be more challenging. In this work, we propose a flexible method for training deep latent variable models of discrete structures. Our approach is based on the recently-proposed Wasserstein autoencoder (WAE) which formalizes the adversarial autoencoder (AAE) as an optimal transport problem. We first e","authors_text":"Alexander M. Rush, Jake Zhao (Junbo), Kelly Zhang, Yann LeCun, Yoon Kim","cross_cats":["cs.CL","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T19:00:53Z","title":"Adversarially Regularized Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04223","kind":"arxiv","version":3},"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:d2bd455f54187bad3d4d94562ceff22f1de0439bfcbb1d0400f47853d4b9069e","target":"record","created_at":"2026-05-18T00:12:06Z","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":"92bc3dad56d84697daea5386cc9ca6d084e62672b0c6ca479cc125a7b1922ede","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T19:00:53Z","title_canon_sha256":"326e28d84c2d03c270beb966b2b6bbc67594efab5f9bfa8df25354de48fb604b"},"schema_version":"1.0","source":{"id":"1706.04223","kind":"arxiv","version":3}},"canonical_sha256":"a67cb41c4f11417c61878aab208c5e4554fadeaa9a76339e4ac7a790472b2890","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a67cb41c4f11417c61878aab208c5e4554fadeaa9a76339e4ac7a790472b2890","first_computed_at":"2026-05-18T00:12:06.341099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:06.341099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KotSzbhdPHwxGqZp22Rxy8tFvzvXD6fbND27FkqoaGg92crDlsesuKIXC3U2iNzgwSHvjkoO6I9uKg+pAlB/Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:06.341671Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.04223","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2bd455f54187bad3d4d94562ceff22f1de0439bfcbb1d0400f47853d4b9069e","sha256:957114832f230aa3227b5915034052fdbe031cbf5294ea7ce06f68cfec8d6770"],"state_sha256":"bf378f3e37d938ceb3d1cf83f44fffd09548ccafa4c46003186ade4a9beb62f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x33r8/l/nThcs+TbH4qrxmu6tAsUUaZauZdYM/0KrnRQt1FhJT6TQ/Bq7eTr4AgC38LRnRbvPohtwIrlVvWSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T09:06:00.151600Z","bundle_sha256":"03fbe42ed46d85fc0da0b136abeefec97c188e0b17ac314fd0bb65f4aae0b013"}}