{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2AUJL27PM4UMMAPJYT27URGRYC","short_pith_number":"pith:2AUJL27P","canonical_record":{"source":{"id":"2003.12738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-28T07:48:02Z","cross_cats_sorted":[],"title_canon_sha256":"dec7801188ae98b7f70a19d4e7d92636478c5cecbd42c9947b7af974ec7d0f14","abstract_canon_sha256":"fa75f276bbc21429f71ad6e3165458deceeb049b95f32ee13ede815ae525678a"},"schema_version":"1.0"},"canonical_sha256":"d02895ebef6728c601e9c4f5fa44d1c0b900a596e8ffc12fb04eb600ce4e7f52","source":{"kind":"arxiv","id":"2003.12738","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12738","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12738v1","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12738","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"2AUJL27PM4UM","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"pith_short_16","alias_value":"2AUJL27PM4UMMAPJ","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"pith_short_8","alias_value":"2AUJL27P","created_at":"2026-07-05T00:51:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2AUJL27PM4UMMAPJYT27URGRYC","target":"record","payload":{"canonical_record":{"source":{"id":"2003.12738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-28T07:48:02Z","cross_cats_sorted":[],"title_canon_sha256":"dec7801188ae98b7f70a19d4e7d92636478c5cecbd42c9947b7af974ec7d0f14","abstract_canon_sha256":"fa75f276bbc21429f71ad6e3165458deceeb049b95f32ee13ede815ae525678a"},"schema_version":"1.0"},"canonical_sha256":"d02895ebef6728c601e9c4f5fa44d1c0b900a596e8ffc12fb04eb600ce4e7f52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:09.402779Z","signature_b64":"XlLITpC1dJYIb8PEdt8twAQcvI9zl54WbfXtuKkbYK0lCt7q8vH8IF7Ommae5rehkKrYg80Cxv27kZODgyJEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d02895ebef6728c601e9c4f5fa44d1c0b900a596e8ffc12fb04eb600ce4e7f52","last_reissued_at":"2026-07-05T00:51:09.402361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:09.402361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.12738","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":"2026-07-05T00:51:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcWGT4eBXRA9M9vLZxSaNBQbHt+6DEsr0j8dSq0AQHDMSFsfKwmHDXgRC/ctTEhCF5Y73547ujTmnsdKiK/7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:07:26.999182Z"},"content_sha256":"21200cecbf3a417ed77d52d3f819bd101ac84577af127ab3b98123bb2486827b","schema_version":"1.0","event_id":"sha256:21200cecbf3a417ed77d52d3f819bd101ac84577af127ab3b98123bb2486827b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2AUJL27PM4UMMAPJYT27URGRYC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Transformers for Diverse Response Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Genta Indra Winata, Pascale Fung, Peng Xu, Zhaojiang Lin, Zihan Liu","submitted_at":"2020-03-28T07:48:02Z","abstract_excerpt":"Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work proposes to capture the variability of dialogue responses with a recurrent neural network (RNN)-based conditional variational autoencoder (CVAE). However, the autoregressive computation of the RNN limits the training efficiency. Therefore, we propose the Variational Transformer (VT), a variational self-attentive feed-forward sequence model. The VT combines the pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12738","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.12738/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":"2026-07-05T00:51:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+YQAziTflBMX1bUDtSFnDApsnZmi/ksA323Zzvzyfps/XUfxprhuOSOo0IAhWJE/Gxf/0pSbnIc4Yt8qgW6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:07:26.999777Z"},"content_sha256":"d6be67cf21d485f760eecd96244a574c5fe4cd054702a81d0c9b32ec19a56a47","schema_version":"1.0","event_id":"sha256:d6be67cf21d485f760eecd96244a574c5fe4cd054702a81d0c9b32ec19a56a47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2AUJL27PM4UMMAPJYT27URGRYC/bundle.json","state_url":"https://pith.science/pith/2AUJL27PM4UMMAPJYT27URGRYC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2AUJL27PM4UMMAPJYT27URGRYC/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":"2026-08-22T00:07:27Z","links":{"resolver":"https://pith.science/pith/2AUJL27PM4UMMAPJYT27URGRYC","bundle":"https://pith.science/pith/2AUJL27PM4UMMAPJYT27URGRYC/bundle.json","state":"https://pith.science/pith/2AUJL27PM4UMMAPJYT27URGRYC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2AUJL27PM4UMMAPJYT27URGRYC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2AUJL27PM4UMMAPJYT27URGRYC","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":"fa75f276bbc21429f71ad6e3165458deceeb049b95f32ee13ede815ae525678a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-28T07:48:02Z","title_canon_sha256":"dec7801188ae98b7f70a19d4e7d92636478c5cecbd42c9947b7af974ec7d0f14"},"schema_version":"1.0","source":{"id":"2003.12738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12738","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12738v1","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12738","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"2AUJL27PM4UM","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"pith_short_16","alias_value":"2AUJL27PM4UMMAPJ","created_at":"2026-07-05T00:51:09Z"},{"alias_kind":"pith_short_8","alias_value":"2AUJL27P","created_at":"2026-07-05T00:51:09Z"}],"graph_snapshots":[{"event_id":"sha256:d6be67cf21d485f760eecd96244a574c5fe4cd054702a81d0c9b32ec19a56a47","target":"graph","created_at":"2026-07-05T00:51:09Z","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/2003.12738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work proposes to capture the variability of dialogue responses with a recurrent neural network (RNN)-based conditional variational autoencoder (CVAE). However, the autoregressive computation of the RNN limits the training efficiency. Therefore, we propose the Variational Transformer (VT), a variational self-attentive feed-forward sequence model. The VT combines the pa","authors_text":"Genta Indra Winata, Pascale Fung, Peng Xu, Zhaojiang Lin, Zihan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-28T07:48:02Z","title":"Variational Transformers for Diverse Response Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12738","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":"sha256:21200cecbf3a417ed77d52d3f819bd101ac84577af127ab3b98123bb2486827b","target":"record","created_at":"2026-07-05T00:51:09Z","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":"fa75f276bbc21429f71ad6e3165458deceeb049b95f32ee13ede815ae525678a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-28T07:48:02Z","title_canon_sha256":"dec7801188ae98b7f70a19d4e7d92636478c5cecbd42c9947b7af974ec7d0f14"},"schema_version":"1.0","source":{"id":"2003.12738","kind":"arxiv","version":1}},"canonical_sha256":"d02895ebef6728c601e9c4f5fa44d1c0b900a596e8ffc12fb04eb600ce4e7f52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d02895ebef6728c601e9c4f5fa44d1c0b900a596e8ffc12fb04eb600ce4e7f52","first_computed_at":"2026-07-05T00:51:09.402361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:09.402361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XlLITpC1dJYIb8PEdt8twAQcvI9zl54WbfXtuKkbYK0lCt7q8vH8IF7Ommae5rehkKrYg80Cxv27kZODgyJEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:09.402779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.12738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21200cecbf3a417ed77d52d3f819bd101ac84577af127ab3b98123bb2486827b","sha256:d6be67cf21d485f760eecd96244a574c5fe4cd054702a81d0c9b32ec19a56a47"],"state_sha256":"787c37ce3d65fd29bba745859bae3ade2f47014b61f39b36077621af751ede52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNcdjinfuy1O+XD4VHANDZFCsnsgoXcSxWQS5zZdheKOka0GO5ZhGhKd+bKKgFHOjEWY252zC5PlPW1KmbnJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:07:27.005451Z","bundle_sha256":"4a68cfc12b16636fced6beea69a31c13f78d6aff4df0f999d76adb771b43188d"}}