{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OC4AVHPEALFMTUCDWS5OIRLYZ5","short_pith_number":"pith:OC4AVHPE","canonical_record":{"source":{"id":"1903.07137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-17T17:42:29Z","cross_cats_sorted":[],"title_canon_sha256":"faf067ff2646007150e37445e3ae4ec73aa17cd24bfb76592e7e7627cc4bdeb0","abstract_canon_sha256":"368d48fbc855a0cb80cf7482139a1d6baf19e3c826448ece256d2cd01f11f775"},"schema_version":"1.0"},"canonical_sha256":"70b80a9de402cac9d043b4bae44578cf5b57cbce6ac5a03df85976c672339c7e","source":{"kind":"arxiv","id":"1903.07137","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07137","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07137v1","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07137","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"OC4AVHPEALFM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OC4AVHPEALFMTUCD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OC4AVHPE","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OC4AVHPEALFMTUCDWS5OIRLYZ5","target":"record","payload":{"canonical_record":{"source":{"id":"1903.07137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-17T17:42:29Z","cross_cats_sorted":[],"title_canon_sha256":"faf067ff2646007150e37445e3ae4ec73aa17cd24bfb76592e7e7627cc4bdeb0","abstract_canon_sha256":"368d48fbc855a0cb80cf7482139a1d6baf19e3c826448ece256d2cd01f11f775"},"schema_version":"1.0"},"canonical_sha256":"70b80a9de402cac9d043b4bae44578cf5b57cbce6ac5a03df85976c672339c7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:04.120174Z","signature_b64":"cpNJhnQzYF+b737CGsNKAXhbHzAMfbN9HPafnd4vfRlIKbJhOjXg/5oRVHcK5LIL8dzRh9A6T5I12KCEd6nPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70b80a9de402cac9d043b4bae44578cf5b57cbce6ac5a03df85976c672339c7e","last_reissued_at":"2026-05-17T23:51:04.119681Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:04.119681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.07137","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":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A1J4oDFdMw8amXGOPy/pAYwZzLBtYfe13z8obLGzDhgvLfnOf7AUlRcGRqrnYGYmZZfsinCpOVxHRvkKFPEYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T12:11:44.064556Z"},"content_sha256":"353c68cb3c494772191dc681086548ec93ede3755bb5a2a5099fef70b829afce","schema_version":"1.0","event_id":"sha256:353c68cb3c494772191dc681086548ec93ede3755bb5a2a5099fef70b829afce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OC4AVHPEALFMTUCDWS5OIRLYZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic-Guided Variational Autoencoders for Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyou Chen, Dinghan Shen, Guoyin Wang, Hongteng Xu, Lawrence Carin, Ruiyi Zhang, Wenlin Wang, Zhe Gan","submitted_at":"2019-03-17T17:42:29Z","abstract_excerpt":"We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our model specifies the prior as a Gaussian mixture model (GMM) parametrized by a neural topic module. Each mixture component corresponds to a latent topic, which provides guidance to generate sentences under the topic. The neural topic module and the VAE-based neural sequence module in our model are learned jointly. In particular, a sequence of invertible Householder transformations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07137","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":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zaclYhSWteo3ebDCb8gHgJtrXO9CCQnKs0l5S7wCK2Ivber9vX0E518HlUHx8y+j3aa7Obnv0SikfeJEXuaSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T12:11:44.064913Z"},"content_sha256":"49069de6ee99b59dc9e7c06fc860fa7b561aa5e9d9422d38bc095d0cb36ecab3","schema_version":"1.0","event_id":"sha256:49069de6ee99b59dc9e7c06fc860fa7b561aa5e9d9422d38bc095d0cb36ecab3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OC4AVHPEALFMTUCDWS5OIRLYZ5/bundle.json","state_url":"https://pith.science/pith/OC4AVHPEALFMTUCDWS5OIRLYZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OC4AVHPEALFMTUCDWS5OIRLYZ5/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":"2026-05-19T12:11:44Z","links":{"resolver":"https://pith.science/pith/OC4AVHPEALFMTUCDWS5OIRLYZ5","bundle":"https://pith.science/pith/OC4AVHPEALFMTUCDWS5OIRLYZ5/bundle.json","state":"https://pith.science/pith/OC4AVHPEALFMTUCDWS5OIRLYZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OC4AVHPEALFMTUCDWS5OIRLYZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OC4AVHPEALFMTUCDWS5OIRLYZ5","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":"368d48fbc855a0cb80cf7482139a1d6baf19e3c826448ece256d2cd01f11f775","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-17T17:42:29Z","title_canon_sha256":"faf067ff2646007150e37445e3ae4ec73aa17cd24bfb76592e7e7627cc4bdeb0"},"schema_version":"1.0","source":{"id":"1903.07137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07137","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07137v1","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07137","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"OC4AVHPEALFM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OC4AVHPEALFMTUCD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OC4AVHPE","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:49069de6ee99b59dc9e7c06fc860fa7b561aa5e9d9422d38bc095d0cb36ecab3","target":"graph","created_at":"2026-05-17T23:51:04Z","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 propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our model specifies the prior as a Gaussian mixture model (GMM) parametrized by a neural topic module. Each mixture component corresponds to a latent topic, which provides guidance to generate sentences under the topic. The neural topic module and the VAE-based neural sequence module in our model are learned jointly. In particular, a sequence of invertible Householder transformations","authors_text":"Changyou Chen, Dinghan Shen, Guoyin Wang, Hongteng Xu, Lawrence Carin, Ruiyi Zhang, Wenlin Wang, Zhe Gan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-17T17:42:29Z","title":"Topic-Guided Variational Autoencoders for Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07137","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":"sha256:353c68cb3c494772191dc681086548ec93ede3755bb5a2a5099fef70b829afce","target":"record","created_at":"2026-05-17T23:51:04Z","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":"368d48fbc855a0cb80cf7482139a1d6baf19e3c826448ece256d2cd01f11f775","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-17T17:42:29Z","title_canon_sha256":"faf067ff2646007150e37445e3ae4ec73aa17cd24bfb76592e7e7627cc4bdeb0"},"schema_version":"1.0","source":{"id":"1903.07137","kind":"arxiv","version":1}},"canonical_sha256":"70b80a9de402cac9d043b4bae44578cf5b57cbce6ac5a03df85976c672339c7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70b80a9de402cac9d043b4bae44578cf5b57cbce6ac5a03df85976c672339c7e","first_computed_at":"2026-05-17T23:51:04.119681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:04.119681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cpNJhnQzYF+b737CGsNKAXhbHzAMfbN9HPafnd4vfRlIKbJhOjXg/5oRVHcK5LIL8dzRh9A6T5I12KCEd6nPCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:04.120174Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.07137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:353c68cb3c494772191dc681086548ec93ede3755bb5a2a5099fef70b829afce","sha256:49069de6ee99b59dc9e7c06fc860fa7b561aa5e9d9422d38bc095d0cb36ecab3"],"state_sha256":"522721f929d902c1a64cd5465c6341789b86550ca1d1609bc47c200b02ff9013"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DLZ6T05tmFakbyWwBj6P2Isr2VNINGtxkK1YHDrp/nsEK0xFaPqigUFpEpFdIJ3ebkiVC2dSDWhlQ+HOxDJvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T12:11:44.066505Z","bundle_sha256":"d1b7f97561aeed1234ba11df739ecb8cb109bb549de57631bd20923a67ecd948"}}