{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IQ6NLZ7EZ74LA7RQZYCOH5ZJID","short_pith_number":"pith:IQ6NLZ7E","canonical_record":{"source":{"id":"2010.08178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-16T05:50:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37ceb9e7b5713eafc2f9e0ab6556bb809b5448dc540a3faed8988ca6f42c14ff","abstract_canon_sha256":"0985f2d4edfb1b22c25d882f55701bb0cd24a985d32a87f653edc187d4b4470d"},"schema_version":"1.0"},"canonical_sha256":"443cd5e7e4cff8b07e30ce04e3f72940d794b3d6650484dad302ba9c79bdaf44","source":{"kind":"arxiv","id":"2010.08178","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.08178","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2010.08178v1","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08178","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"IQ6NLZ7EZ74L","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"IQ6NLZ7EZ74LA7RQ","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"IQ6NLZ7E","created_at":"2026-07-05T01:43:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IQ6NLZ7EZ74LA7RQZYCOH5ZJID","target":"record","payload":{"canonical_record":{"source":{"id":"2010.08178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-16T05:50:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37ceb9e7b5713eafc2f9e0ab6556bb809b5448dc540a3faed8988ca6f42c14ff","abstract_canon_sha256":"0985f2d4edfb1b22c25d882f55701bb0cd24a985d32a87f653edc187d4b4470d"},"schema_version":"1.0"},"canonical_sha256":"443cd5e7e4cff8b07e30ce04e3f72940d794b3d6650484dad302ba9c79bdaf44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:32.243129Z","signature_b64":"Z5ZGefpgH+V1GwlcJn2c40zIX2ibZNAGR3x52n60u7JA6O53XjvCVR32Di6+cjgNz3VBJq6dd+vcsAiq5x2pCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"443cd5e7e4cff8b07e30ce04e3f72940d794b3d6650484dad302ba9c79bdaf44","last_reissued_at":"2026-07-05T01:43:32.242785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:32.242785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.08178","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":"2026-07-05T01:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZ387AH0qUrFGJM1jSNVpuyZrZVTLUjwwH5xTu6smSStjBmL9sj+H4jkeoDYEmMHpV6f4SMzwEcnF5P/QyeaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:33:43.422986Z"},"content_sha256":"8cf5af21b9642d5b02b2bc368c6478a3bbdb640022ebbc39ae4a664cf349afff","schema_version":"1.0","event_id":"sha256:8cf5af21b9642d5b02b2bc368c6478a3bbdb640022ebbc39ae4a664cf349afff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IQ6NLZ7EZ74LA7RQZYCOH5ZJID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Diverse Translation from Model Distribution with Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenze Shao, Xuanfu Wu, Yang Feng","submitted_at":"2020-10-16T05:50:00Z","abstract_excerpt":"Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08178","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/2010.08178/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":"2026-07-05T01:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ODf6s6MiRyTh3dUHKxLUcxxBzTsqdxeLJIfoTsN/VhEZXHvhqZptHyv+Ckti3UqwVYrbiOLbHChuIlu17bamCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:33:43.423544Z"},"content_sha256":"c683d7f8f227d98d30fdb7bf4e6e0a71e67262187bda46badd790872e6837a75","schema_version":"1.0","event_id":"sha256:c683d7f8f227d98d30fdb7bf4e6e0a71e67262187bda46badd790872e6837a75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQ6NLZ7EZ74LA7RQZYCOH5ZJID/bundle.json","state_url":"https://pith.science/pith/IQ6NLZ7EZ74LA7RQZYCOH5ZJID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQ6NLZ7EZ74LA7RQZYCOH5ZJID/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":"2026-08-21T04:33:43Z","links":{"resolver":"https://pith.science/pith/IQ6NLZ7EZ74LA7RQZYCOH5ZJID","bundle":"https://pith.science/pith/IQ6NLZ7EZ74LA7RQZYCOH5ZJID/bundle.json","state":"https://pith.science/pith/IQ6NLZ7EZ74LA7RQZYCOH5ZJID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQ6NLZ7EZ74LA7RQZYCOH5ZJID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IQ6NLZ7EZ74LA7RQZYCOH5ZJID","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":"0985f2d4edfb1b22c25d882f55701bb0cd24a985d32a87f653edc187d4b4470d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-16T05:50:00Z","title_canon_sha256":"37ceb9e7b5713eafc2f9e0ab6556bb809b5448dc540a3faed8988ca6f42c14ff"},"schema_version":"1.0","source":{"id":"2010.08178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.08178","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2010.08178v1","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08178","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"IQ6NLZ7EZ74L","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"IQ6NLZ7EZ74LA7RQ","created_at":"2026-07-05T01:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"IQ6NLZ7E","created_at":"2026-07-05T01:43:32Z"}],"graph_snapshots":[{"event_id":"sha256:c683d7f8f227d98d30fdb7bf4e6e0a71e67262187bda46badd790872e6837a75","target":"graph","created_at":"2026-07-05T01:43:32Z","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/2010.08178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inferenc","authors_text":"Chenze Shao, Xuanfu Wu, Yang Feng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-16T05:50:00Z","title":"Generating Diverse Translation from Model Distribution with Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08178","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":"sha256:8cf5af21b9642d5b02b2bc368c6478a3bbdb640022ebbc39ae4a664cf349afff","target":"record","created_at":"2026-07-05T01:43:32Z","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":"0985f2d4edfb1b22c25d882f55701bb0cd24a985d32a87f653edc187d4b4470d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-16T05:50:00Z","title_canon_sha256":"37ceb9e7b5713eafc2f9e0ab6556bb809b5448dc540a3faed8988ca6f42c14ff"},"schema_version":"1.0","source":{"id":"2010.08178","kind":"arxiv","version":1}},"canonical_sha256":"443cd5e7e4cff8b07e30ce04e3f72940d794b3d6650484dad302ba9c79bdaf44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"443cd5e7e4cff8b07e30ce04e3f72940d794b3d6650484dad302ba9c79bdaf44","first_computed_at":"2026-07-05T01:43:32.242785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:32.242785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z5ZGefpgH+V1GwlcJn2c40zIX2ibZNAGR3x52n60u7JA6O53XjvCVR32Di6+cjgNz3VBJq6dd+vcsAiq5x2pCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:32.243129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.08178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cf5af21b9642d5b02b2bc368c6478a3bbdb640022ebbc39ae4a664cf349afff","sha256:c683d7f8f227d98d30fdb7bf4e6e0a71e67262187bda46badd790872e6837a75"],"state_sha256":"b9d921d058dcdfd7c088c20e1bb339f3b8b24d028b620f834031ef36c1665538"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ORyQBSkQbqT83zGqtc74qp06Q/3KmpJNaW4eT1sPpw9w95VHTFzJzkc76jRyqvka/OfXTZERjntUfLWakSD9BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T04:33:43.428451Z","bundle_sha256":"7a4d12d3598a9c73d14bb851e78d69e493207fae21561e88c6251c56a81d2cb4"}}