{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XTHXQGTU5S7QCNEIVBG3OPYPXN","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":"580881edf518b997eb3fbf2828d9153a6e876332ec9a9bb5124441dd97dba92f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T09:20:14Z","title_canon_sha256":"4b80024c1118c05557e1d2c096242d6098d24eeba5fa69dd48d56f7e61249919"},"schema_version":"1.0","source":{"id":"1911.00274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.00274","created_at":"2026-07-05T00:16:25Z"},{"alias_kind":"arxiv_version","alias_value":"1911.00274v1","created_at":"2026-07-05T00:16:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00274","created_at":"2026-07-05T00:16:25Z"},{"alias_kind":"pith_short_12","alias_value":"XTHXQGTU5S7Q","created_at":"2026-07-05T00:16:25Z"},{"alias_kind":"pith_short_16","alias_value":"XTHXQGTU5S7QCNEI","created_at":"2026-07-05T00:16:25Z"},{"alias_kind":"pith_short_8","alias_value":"XTHXQGTU","created_at":"2026-07-05T00:16:25Z"}],"graph_snapshots":[{"event_id":"sha256:cf3eba36f1f8118ca1435371db62cfd84801c7dc669a35a57eae81f16d9d0fc1","target":"graph","created_at":"2026-07-05T00:16:25Z","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/1911.00274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase. Most existing approaches adopt single point embedding for each token. However, a word may have multiple senses according to different context, some of which might be distinct. In this paper, we propose KerBS, a novel approach for learning better embeddings for text generation. KerBS embodies two advantages: (a) it employs a Bayesian composition of embeddings for words with multiple senses; (b) it is adaptive to semantic variances of words and robust to rare sentence context by impo","authors_text":"Chengqi Zhao, Hao Zhou, Lei Li, Ning Miao, Wenxian Shi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T09:20:14Z","title":"Kernelized Bayesian Softmax for Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00274","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":"sha256:2c2685ebf4886678f972d44e70b0af26b9914f46b24b0faccd4b210ac01ddeb2","target":"record","created_at":"2026-07-05T00:16:25Z","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":"580881edf518b997eb3fbf2828d9153a6e876332ec9a9bb5124441dd97dba92f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T09:20:14Z","title_canon_sha256":"4b80024c1118c05557e1d2c096242d6098d24eeba5fa69dd48d56f7e61249919"},"schema_version":"1.0","source":{"id":"1911.00274","kind":"arxiv","version":1}},"canonical_sha256":"bccf781a74ecbf013488a84db73f0fbb6ba611755c3e27aa89fa3bb8a67ec0fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bccf781a74ecbf013488a84db73f0fbb6ba611755c3e27aa89fa3bb8a67ec0fb","first_computed_at":"2026-07-05T00:16:25.430827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:25.430827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xrBsK+l4h5CYONUaSNSDjl5271drItNmf28Qof9q/Zegy68BW154tmHSY8KL2FmYujHoTRCGTuSXqZMjRe8rCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:25.431282Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.00274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c2685ebf4886678f972d44e70b0af26b9914f46b24b0faccd4b210ac01ddeb2","sha256:cf3eba36f1f8118ca1435371db62cfd84801c7dc669a35a57eae81f16d9d0fc1"],"state_sha256":"bcecbd357263877029de67046d5a1016b74ed23c1609fe33b976336abc2ff1af"}