{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZCI4GZKKS2TNZPZITOYDSY3OZ3","short_pith_number":"pith:ZCI4GZKK","canonical_record":{"source":{"id":"2004.04092","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:20:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bf6e317eef980ce9db4a4a8b756812b8e7ecf45513db73e633b4b238f0e1ab1d","abstract_canon_sha256":"9424c924ac1c2c311477044708f80fe9a17658e07fc91442d857177762bcc850"},"schema_version":"1.0"},"canonical_sha256":"c891c3654a96a6dcbf289bb039636ecee8b7601cc6b9b2658c23e62feda0d7fd","source":{"kind":"arxiv","id":"2004.04092","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.04092","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"2004.04092v4","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04092","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZCI4GZKKS2TN","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZCI4GZKKS2TNZPZI","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZCI4GZKK","created_at":"2026-07-05T01:41:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZCI4GZKKS2TNZPZITOYDSY3OZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2004.04092","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:20:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bf6e317eef980ce9db4a4a8b756812b8e7ecf45513db73e633b4b238f0e1ab1d","abstract_canon_sha256":"9424c924ac1c2c311477044708f80fe9a17658e07fc91442d857177762bcc850"},"schema_version":"1.0"},"canonical_sha256":"c891c3654a96a6dcbf289bb039636ecee8b7601cc6b9b2658c23e62feda0d7fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:51.878073Z","signature_b64":"+UAKpn3NNmH9FRrUD3Gk7EM7Q9r/x24EFov2Pa2tqvlolYyGnzmkH6yPmPu6I7tC3kHOqyUEeX4zjqumVgTsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c891c3654a96a6dcbf289bb039636ecee8b7601cc6b9b2658c23e62feda0d7fd","last_reissued_at":"2026-07-05T01:41:51.877620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:51.877620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.04092","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uKc4byiqbbsGgFRd3E6AtrSWf4nkghD8vjgB+Yk31BAa4GCuwYyiPu3EKydKxGgdLIUVZxoPJL+Vh3GKATiyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:33:45.256045Z"},"content_sha256":"1f548b2c4f2665289ccacb9f7e52aa40e1fa0044319da32862c3de847c7999df","schema_version":"1.0","event_id":"sha256:1f548b2c4f2665289ccacb9f7e52aa40e1fa0044319da32862c3de847c7999df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZCI4GZKKS2TNZPZITOYDSY3OZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Chunyuan Li, Jianfeng Gao, Xiang Gao, Xiujun Li, Yizhe Zhang, Yuan Li","submitted_at":"2020-04-05T06:20:18Z","abstract_excerpt":"When trained effectively, the Variational Autoencoder (VAE) can be both a powerful generative model and an effective representation learning framework for natural language. In this paper, we propose the first large-scale language VAE model, Optimus. A universal latent embedding space for sentences is first pre-trained on large text corpus, and then fine-tuned for various language generation and understanding tasks. Compared with GPT-2, Optimus enables guided language generation from an abstract level using the latent vectors. Compared with BERT, Optimus can generalize better on low-resource la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04092","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.04092/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KnO3JG0XWhn+PhQ52q+hOddQiiM0awlQUrn3t0YQ2QvjW706QOpyi2b/mWFwkOW4sPYsKc1r71EVaRCTN31FDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:33:45.256597Z"},"content_sha256":"86e2675bc07af815024bd4244585758165df0a77d0b8cdc39f4d5a43c2d6f15e","schema_version":"1.0","event_id":"sha256:86e2675bc07af815024bd4244585758165df0a77d0b8cdc39f4d5a43c2d6f15e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZCI4GZKKS2TNZPZITOYDSY3OZ3/bundle.json","state_url":"https://pith.science/pith/ZCI4GZKKS2TNZPZITOYDSY3OZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZCI4GZKKS2TNZPZITOYDSY3OZ3/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":"2026-08-03T14:33:45Z","links":{"resolver":"https://pith.science/pith/ZCI4GZKKS2TNZPZITOYDSY3OZ3","bundle":"https://pith.science/pith/ZCI4GZKKS2TNZPZITOYDSY3OZ3/bundle.json","state":"https://pith.science/pith/ZCI4GZKKS2TNZPZITOYDSY3OZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZCI4GZKKS2TNZPZITOYDSY3OZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZCI4GZKKS2TNZPZITOYDSY3OZ3","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":"9424c924ac1c2c311477044708f80fe9a17658e07fc91442d857177762bcc850","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:20:18Z","title_canon_sha256":"bf6e317eef980ce9db4a4a8b756812b8e7ecf45513db73e633b4b238f0e1ab1d"},"schema_version":"1.0","source":{"id":"2004.04092","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.04092","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"2004.04092v4","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04092","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZCI4GZKKS2TN","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZCI4GZKKS2TNZPZI","created_at":"2026-07-05T01:41:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZCI4GZKK","created_at":"2026-07-05T01:41:51Z"}],"graph_snapshots":[{"event_id":"sha256:86e2675bc07af815024bd4244585758165df0a77d0b8cdc39f4d5a43c2d6f15e","target":"graph","created_at":"2026-07-05T01:41:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.04092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When trained effectively, the Variational Autoencoder (VAE) can be both a powerful generative model and an effective representation learning framework for natural language. In this paper, we propose the first large-scale language VAE model, Optimus. A universal latent embedding space for sentences is first pre-trained on large text corpus, and then fine-tuned for various language generation and understanding tasks. Compared with GPT-2, Optimus enables guided language generation from an abstract level using the latent vectors. Compared with BERT, Optimus can generalize better on low-resource la","authors_text":"Baolin Peng, Chunyuan Li, Jianfeng Gao, Xiang Gao, Xiujun Li, Yizhe Zhang, Yuan Li","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:20:18Z","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04092","kind":"arxiv","version":4},"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":"sha256:1f548b2c4f2665289ccacb9f7e52aa40e1fa0044319da32862c3de847c7999df","target":"record","created_at":"2026-07-05T01:41:51Z","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":"9424c924ac1c2c311477044708f80fe9a17658e07fc91442d857177762bcc850","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T06:20:18Z","title_canon_sha256":"bf6e317eef980ce9db4a4a8b756812b8e7ecf45513db73e633b4b238f0e1ab1d"},"schema_version":"1.0","source":{"id":"2004.04092","kind":"arxiv","version":4}},"canonical_sha256":"c891c3654a96a6dcbf289bb039636ecee8b7601cc6b9b2658c23e62feda0d7fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c891c3654a96a6dcbf289bb039636ecee8b7601cc6b9b2658c23e62feda0d7fd","first_computed_at":"2026-07-05T01:41:51.877620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:51.877620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+UAKpn3NNmH9FRrUD3Gk7EM7Q9r/x24EFov2Pa2tqvlolYyGnzmkH6yPmPu6I7tC3kHOqyUEeX4zjqumVgTsCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:51.878073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.04092","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f548b2c4f2665289ccacb9f7e52aa40e1fa0044319da32862c3de847c7999df","sha256:86e2675bc07af815024bd4244585758165df0a77d0b8cdc39f4d5a43c2d6f15e"],"state_sha256":"533fe18d723eb1e046fcccdf490ca3a7b339526aae36b6af14e15c492e16100b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"550ZQImKcZMWI44CzGlzF5CXjsTr2CfdfyaVHL2eDkr2vg6/mM9VK/sAzq5zt2lT6RZrRQ+1cFfTV5JnvC85BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T14:33:45.261731Z","bundle_sha256":"b0e60e2b227b92986ac1b1c01d423b2b0faf7bf06827b0addbe5fe380e28e8b8"}}