{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DW7H6IMUC4HRFANIXJJTL6DIMQ","short_pith_number":"pith:DW7H6IMU","canonical_record":{"source":{"id":"1808.09012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:40:53Z","cross_cats_sorted":[],"title_canon_sha256":"0d4a12e23a1f33c3decf0a24649695b510d5e431711ec95370048d7c7adf08f0","abstract_canon_sha256":"9f7be18588c512b1b43ab7f45131a2f9a5f46cfaf73c73411bb40621fe1417de"},"schema_version":"1.0"},"canonical_sha256":"1dbe7f2194170f1281a8ba5335f868642cde22ba1723e43824cbee63e1bb58a3","source":{"kind":"arxiv","id":"1808.09012","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09012","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09012v1","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09012","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"DW7H6IMUC4HR","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DW7H6IMUC4HRFANI","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DW7H6IMU","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DW7H6IMUC4HRFANIXJJTL6DIMQ","target":"record","payload":{"canonical_record":{"source":{"id":"1808.09012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:40:53Z","cross_cats_sorted":[],"title_canon_sha256":"0d4a12e23a1f33c3decf0a24649695b510d5e431711ec95370048d7c7adf08f0","abstract_canon_sha256":"9f7be18588c512b1b43ab7f45131a2f9a5f46cfaf73c73411bb40621fe1417de"},"schema_version":"1.0"},"canonical_sha256":"1dbe7f2194170f1281a8ba5335f868642cde22ba1723e43824cbee63e1bb58a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:04.899204Z","signature_b64":"/QEaLq3TKYcDXVNpHadTGt8pl/ueWnxSBnlKV5VyvmgmSizduj7JDpyzzfEvICrNhxguszksIlHsCKL01m/nBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dbe7f2194170f1281a8ba5335f868642cde22ba1723e43824cbee63e1bb58a3","last_reissued_at":"2026-05-18T00:07:04.898490Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:04.898490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.09012","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":"2026-05-18T00:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDlQRDLqxyqRoQajvC10lynjCAKKt0si446/K+gAFAlyQkK40LivR1Vf1kgjUbTeAktGxcvamkzrJoIXdShZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T01:09:11.358301Z"},"content_sha256":"914d776c4838464992d53321591f85d6779ee1a0aec06ce74b32950a3d675246","schema_version":"1.0","event_id":"sha256:914d776c4838464992d53321591f85d6779ee1a0aec06ce74b32950a3d675246"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DW7H6IMUC4HRFANIXJJTL6DIMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language Generation with Neural Variational Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hareesh Bahuleyan","submitted_at":"2018-08-27T19:40:53Z","abstract_excerpt":"In this thesis, we explore the use of deep neural networks for generation of natural language. Specifically, we implement two sequence-to-sequence neural variational models - variational autoencoders (VAE) and variational encoder-decoders (VED). VAEs for text generation are difficult to train due to issues associated with the Kullback-Leibler (KL) divergence term of the loss function vanishing to zero. We successfully train VAEs by implementing optimization heuristics such as KL weight annealing and word dropout. We also demonstrate the effectiveness of this continuous latent space through exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09012","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":"2026-05-18T00:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9f86SoBzG1yah4UzioL8G4pH91j0Hucnj+80ifHBpHCjoh3WoVAF13HnLZ3QZSRfaK/lcT1MdfywbxUsmiKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T01:09:11.358654Z"},"content_sha256":"66ed6d40a8ef5e59d41e6d5b83686484e8539a61f0322cd3954942fa84de644e","schema_version":"1.0","event_id":"sha256:66ed6d40a8ef5e59d41e6d5b83686484e8539a61f0322cd3954942fa84de644e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DW7H6IMUC4HRFANIXJJTL6DIMQ/bundle.json","state_url":"https://pith.science/pith/DW7H6IMUC4HRFANIXJJTL6DIMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DW7H6IMUC4HRFANIXJJTL6DIMQ/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":"2026-06-09T01:09:11Z","links":{"resolver":"https://pith.science/pith/DW7H6IMUC4HRFANIXJJTL6DIMQ","bundle":"https://pith.science/pith/DW7H6IMUC4HRFANIXJJTL6DIMQ/bundle.json","state":"https://pith.science/pith/DW7H6IMUC4HRFANIXJJTL6DIMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DW7H6IMUC4HRFANIXJJTL6DIMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DW7H6IMUC4HRFANIXJJTL6DIMQ","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":"9f7be18588c512b1b43ab7f45131a2f9a5f46cfaf73c73411bb40621fe1417de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:40:53Z","title_canon_sha256":"0d4a12e23a1f33c3decf0a24649695b510d5e431711ec95370048d7c7adf08f0"},"schema_version":"1.0","source":{"id":"1808.09012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09012","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09012v1","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09012","created_at":"2026-05-18T00:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"DW7H6IMUC4HR","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DW7H6IMUC4HRFANI","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DW7H6IMU","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:66ed6d40a8ef5e59d41e6d5b83686484e8539a61f0322cd3954942fa84de644e","target":"graph","created_at":"2026-05-18T00:07:04Z","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":"In this thesis, we explore the use of deep neural networks for generation of natural language. Specifically, we implement two sequence-to-sequence neural variational models - variational autoencoders (VAE) and variational encoder-decoders (VED). VAEs for text generation are difficult to train due to issues associated with the Kullback-Leibler (KL) divergence term of the loss function vanishing to zero. We successfully train VAEs by implementing optimization heuristics such as KL weight annealing and word dropout. We also demonstrate the effectiveness of this continuous latent space through exp","authors_text":"Hareesh Bahuleyan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:40:53Z","title":"Natural Language Generation with Neural Variational Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09012","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":"sha256:914d776c4838464992d53321591f85d6779ee1a0aec06ce74b32950a3d675246","target":"record","created_at":"2026-05-18T00:07:04Z","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":"9f7be18588c512b1b43ab7f45131a2f9a5f46cfaf73c73411bb40621fe1417de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:40:53Z","title_canon_sha256":"0d4a12e23a1f33c3decf0a24649695b510d5e431711ec95370048d7c7adf08f0"},"schema_version":"1.0","source":{"id":"1808.09012","kind":"arxiv","version":1}},"canonical_sha256":"1dbe7f2194170f1281a8ba5335f868642cde22ba1723e43824cbee63e1bb58a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1dbe7f2194170f1281a8ba5335f868642cde22ba1723e43824cbee63e1bb58a3","first_computed_at":"2026-05-18T00:07:04.898490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:04.898490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/QEaLq3TKYcDXVNpHadTGt8pl/ueWnxSBnlKV5VyvmgmSizduj7JDpyzzfEvICrNhxguszksIlHsCKL01m/nBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:04.899204Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:914d776c4838464992d53321591f85d6779ee1a0aec06ce74b32950a3d675246","sha256:66ed6d40a8ef5e59d41e6d5b83686484e8539a61f0322cd3954942fa84de644e"],"state_sha256":"211694f033ac20d51fc80c9e88e601c77eb81f865eb0a93e8b9f824cb78e74d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+zWfCC3KWOB83GBYse5nNs6nOUzStnhFR4I1r0Q6VYs0fx82HaTkLUVql+ZcPcijBKVfT7KFBW6kkD3bmUBrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T01:09:11.360522Z","bundle_sha256":"9f3020423c123e70af2f59f21719b908ebde8592431f6e6fce08aaedfa41cab4"}}