{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UVMFV2T62J4M4DPNJKZ5GEBD2P","short_pith_number":"pith:UVMFV2T6","schema_version":"1.0","canonical_sha256":"a5585aea7ed278ce0ded4ab3d31023d3e775d427d9966369cde67c83691e1934","source":{"kind":"arxiv","id":"1904.09408","version":2},"attestation_state":"computed","paper":{"title":"Language Models with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander J. Smola, Chenguang Wang, Mu Li","submitted_at":"2019-04-20T06:43:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.09408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-20T06:43:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b8d468f2e9d244d1c400fbedfa26d9dedb3585a5c47871790777cac98697d3d0","abstract_canon_sha256":"a899c0783d4f66c7ca9ef7b73a6be6221c15a6584f43065fc59708fc1f6c6853"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:51.757052Z","signature_b64":"ruaWpdrvKE6ruNIfTNldjY5+PyHHZNfJ/aGjzLzGXtTzge3JQcUI1aOXD6PIbwOahEWvqMSPfyfyFUbFOWeBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5585aea7ed278ce0ded4ab3d31023d3e775d427d9966369cde67c83691e1934","last_reissued_at":"2026-07-05T00:12:51.756501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:51.756501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander J. Smola, Chenguang Wang, Mu Li","submitted_at":"2019-04-20T06:43:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09408","kind":"arxiv","version":2},"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/1904.09408/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.09408","created_at":"2026-07-05T00:12:51.756557+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09408v2","created_at":"2026-07-05T00:12:51.756557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09408","created_at":"2026-07-05T00:12:51.756557+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVMFV2T62J4M","created_at":"2026-07-05T00:12:51.756557+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVMFV2T62J4M4DPN","created_at":"2026-07-05T00:12:51.756557+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVMFV2T6","created_at":"2026-07-05T00:12:51.756557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P","json":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P.json","graph_json":"https://pith.science/api/pith-number/UVMFV2T62J4M4DPNJKZ5GEBD2P/graph.json","events_json":"https://pith.science/api/pith-number/UVMFV2T62J4M4DPNJKZ5GEBD2P/events.json","paper":"https://pith.science/paper/UVMFV2T6"},"agent_actions":{"view_html":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P","download_json":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P.json","view_paper":"https://pith.science/paper/UVMFV2T6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09408&json=true","fetch_graph":"https://pith.science/api/pith-number/UVMFV2T62J4M4DPNJKZ5GEBD2P/graph.json","fetch_events":"https://pith.science/api/pith-number/UVMFV2T62J4M4DPNJKZ5GEBD2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P/action/storage_attestation","attest_author":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P/action/author_attestation","sign_citation":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P/action/citation_signature","submit_replication":"https://pith.science/pith/UVMFV2T62J4M4DPNJKZ5GEBD2P/action/replication_record"}},"created_at":"2026-07-05T00:12:51.756557+00:00","updated_at":"2026-07-05T00:12:51.756557+00:00"}