{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UVMFV2T62J4M4DPNJKZ5GEBD2P","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":"a899c0783d4f66c7ca9ef7b73a6be6221c15a6584f43065fc59708fc1f6c6853","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-20T06:43:14Z","title_canon_sha256":"b8d468f2e9d244d1c400fbedfa26d9dedb3585a5c47871790777cac98697d3d0"},"schema_version":"1.0","source":{"id":"1904.09408","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09408","created_at":"2026-07-05T00:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09408v2","created_at":"2026-07-05T00:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09408","created_at":"2026-07-05T00:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"UVMFV2T62J4M","created_at":"2026-07-05T00:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"UVMFV2T62J4M4DPN","created_at":"2026-07-05T00:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"UVMFV2T6","created_at":"2026-07-05T00:12:51Z"}],"graph_snapshots":[{"event_id":"sha256:40f1b612191b6fc4908a90d3c928e50c4a215890c2380cab3dbd5233813aedc9","target":"graph","created_at":"2026-07-05T00:12:51Z","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/1904.09408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Transformer architecture is superior to RNN-based models in computational efficiency. Recently, GPT and BERT demonstrate the efficacy of Transformer models on various NLP tasks using pre-trained language models on large-scale corpora. Surprisingly, these Transformer architectures are suboptimal for language model itself. Neither self-attention nor the positional encoding in the Transformer is able to efficiently incorporate the word-level sequential context crucial to language modeling.\n  In this paper, we explore effective Transformer architectures for language model, including adding add","authors_text":"Alexander J. Smola, Chenguang Wang, Mu Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-20T06:43:14Z","title":"Language Models with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09408","kind":"arxiv","version":2},"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:b9546742fc086eeb0d9070653b230459fc7dcff31e8ead6bb6ca250d4b9620a4","target":"record","created_at":"2026-07-05T00:12:51Z","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":"a899c0783d4f66c7ca9ef7b73a6be6221c15a6584f43065fc59708fc1f6c6853","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-20T06:43:14Z","title_canon_sha256":"b8d468f2e9d244d1c400fbedfa26d9dedb3585a5c47871790777cac98697d3d0"},"schema_version":"1.0","source":{"id":"1904.09408","kind":"arxiv","version":2}},"canonical_sha256":"a5585aea7ed278ce0ded4ab3d31023d3e775d427d9966369cde67c83691e1934","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5585aea7ed278ce0ded4ab3d31023d3e775d427d9966369cde67c83691e1934","first_computed_at":"2026-07-05T00:12:51.756501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:12:51.756501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ruaWpdrvKE6ruNIfTNldjY5+PyHHZNfJ/aGjzLzGXtTzge3JQcUI1aOXD6PIbwOahEWvqMSPfyfyFUbFOWeBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:12:51.757052Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09408","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9546742fc086eeb0d9070653b230459fc7dcff31e8ead6bb6ca250d4b9620a4","sha256:40f1b612191b6fc4908a90d3c928e50c4a215890c2380cab3dbd5233813aedc9"],"state_sha256":"3a06e8f4633087159cf991a7dc989469d55c9682dd88c8ea7e3e8cf00283c49e"}