{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G4GAQJAAUUAHKQA2Q4XZBB5TTT","short_pith_number":"pith:G4GAQJAA","schema_version":"1.0","canonical_sha256":"370c082400a50075401a872f9087b39cc3c2c87b5b1123cc15380c6b9bb6ae87","source":{"kind":"arxiv","id":"2311.17633","version":2},"attestation_state":"computed","paper":{"title":"Introduction to Transformers: an NLP Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingbo Zhu, Tong Xiao","submitted_at":"2023-11-29T13:51:04Z","abstract_excerpt":"Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes a description of the standard Transformer architecture, a series of model refinements, and common applications. Given that Transformers and related deep learning techniques might be evolving in ways we have never seen, we cannot dive into all the model details or cover all the technical areas. Instead, we focus on just those concepts that are helpful for ga"},"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":"2311.17633","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T13:51:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"09fb945d3eaeec54055631a3e9f101278e0fbd31c83cacce0db12b2a65090351","abstract_canon_sha256":"addeff2720e64b6f204947f0250e8e6e56050e1d3e1294bd91da98a46e5f7930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:09.619188Z","signature_b64":"4TEBaUDJtPADpow59ZT49yPzU0zXewnYRoAOviB69K0K3rga0zPPbVMutKpE4qlJkDQOj0K0oIRLoeNcPkkdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"370c082400a50075401a872f9087b39cc3c2c87b5b1123cc15380c6b9bb6ae87","last_reissued_at":"2026-07-03T01:17:09.618732Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:09.618732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Introduction to Transformers: an NLP Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingbo Zhu, Tong Xiao","submitted_at":"2023-11-29T13:51:04Z","abstract_excerpt":"Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes a description of the standard Transformer architecture, a series of model refinements, and common applications. Given that Transformers and related deep learning techniques might be evolving in ways we have never seen, we cannot dive into all the model details or cover all the technical areas. Instead, we focus on just those concepts that are helpful for ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17633","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/2311.17633/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":"2311.17633","created_at":"2026-07-03T01:17:09.618802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17633v2","created_at":"2026-07-03T01:17:09.618802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17633","created_at":"2026-07-03T01:17:09.618802+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4GAQJAAUUAH","created_at":"2026-07-03T01:17:09.618802+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4GAQJAAUUAHKQA2","created_at":"2026-07-03T01:17:09.618802+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4GAQJAA","created_at":"2026-07-03T01:17:09.618802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14294","citing_title":"Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT","json":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT.json","graph_json":"https://pith.science/api/pith-number/G4GAQJAAUUAHKQA2Q4XZBB5TTT/graph.json","events_json":"https://pith.science/api/pith-number/G4GAQJAAUUAHKQA2Q4XZBB5TTT/events.json","paper":"https://pith.science/paper/G4GAQJAA"},"agent_actions":{"view_html":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT","download_json":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT.json","view_paper":"https://pith.science/paper/G4GAQJAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17633&json=true","fetch_graph":"https://pith.science/api/pith-number/G4GAQJAAUUAHKQA2Q4XZBB5TTT/graph.json","fetch_events":"https://pith.science/api/pith-number/G4GAQJAAUUAHKQA2Q4XZBB5TTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT/action/storage_attestation","attest_author":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT/action/author_attestation","sign_citation":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT/action/citation_signature","submit_replication":"https://pith.science/pith/G4GAQJAAUUAHKQA2Q4XZBB5TTT/action/replication_record"}},"created_at":"2026-07-03T01:17:09.618802+00:00","updated_at":"2026-07-03T01:17:09.618802+00:00"}