{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WWL2JY76SFQLNM4Y4HJH6HCS4Y","short_pith_number":"pith:WWL2JY76","schema_version":"1.0","canonical_sha256":"b597a4e3fe9160b6b398e1d27f1c52e603952e5f258ee2a3d76d5a63d3079cd0","source":{"kind":"arxiv","id":"2409.03295","version":1},"attestation_state":"computed","paper":{"title":"N-gram Prediction and Word Difference Representations for Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniela Noemi Rim, DongNyeong Heo, Heeyoul Choi","submitted_at":"2024-09-05T07:03:23Z","abstract_excerpt":"Causal language modeling (CLM) serves as the foundational framework underpinning remarkable successes of recent large language models (LLMs). Despite its success, the training approach for next word prediction poses a potential risk of causing the model to overly focus on local dependencies within a sentence. While prior studies have been introduced to predict future N words simultaneously, they were primarily applied to tasks such as masked language modeling (MLM) and neural machine translation (NMT). In this study, we introduce a simple N-gram prediction framework for the CLM task. Moreover,"},"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":"2409.03295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T07:03:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a37115948c8cfcbdf7869ff7c2cdcb6d15be9b36f62ecb1695e4b1259e196bd","abstract_canon_sha256":"9b408478c99d2b399fd5c17499bbd10871152ee0607324c0e9707f8a4ab60374"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:29.180336Z","signature_b64":"yuIsr4tgIvqEkSJsJlkDG1U4fVok+/l45tE9NkUEzqToWqyeS0GmDxq3q+0gUiHkPivxWi0I+JJDSKJQSl7EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b597a4e3fe9160b6b398e1d27f1c52e603952e5f258ee2a3d76d5a63d3079cd0","last_reissued_at":"2026-07-05T09:03:29.179838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:29.179838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"N-gram Prediction and Word Difference Representations for Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniela Noemi Rim, DongNyeong Heo, Heeyoul Choi","submitted_at":"2024-09-05T07:03:23Z","abstract_excerpt":"Causal language modeling (CLM) serves as the foundational framework underpinning remarkable successes of recent large language models (LLMs). Despite its success, the training approach for next word prediction poses a potential risk of causing the model to overly focus on local dependencies within a sentence. While prior studies have been introduced to predict future N words simultaneously, they were primarily applied to tasks such as masked language modeling (MLM) and neural machine translation (NMT). In this study, we introduce a simple N-gram prediction framework for the CLM task. Moreover,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03295","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/2409.03295/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":"2409.03295","created_at":"2026-07-05T09:03:29.179897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03295v1","created_at":"2026-07-05T09:03:29.179897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03295","created_at":"2026-07-05T09:03:29.179897+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWL2JY76SFQL","created_at":"2026-07-05T09:03:29.179897+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWL2JY76SFQLNM4Y","created_at":"2026-07-05T09:03:29.179897+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWL2JY76","created_at":"2026-07-05T09:03:29.179897+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/WWL2JY76SFQLNM4Y4HJH6HCS4Y","json":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y.json","graph_json":"https://pith.science/api/pith-number/WWL2JY76SFQLNM4Y4HJH6HCS4Y/graph.json","events_json":"https://pith.science/api/pith-number/WWL2JY76SFQLNM4Y4HJH6HCS4Y/events.json","paper":"https://pith.science/paper/WWL2JY76"},"agent_actions":{"view_html":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y","download_json":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y.json","view_paper":"https://pith.science/paper/WWL2JY76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03295&json=true","fetch_graph":"https://pith.science/api/pith-number/WWL2JY76SFQLNM4Y4HJH6HCS4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/WWL2JY76SFQLNM4Y4HJH6HCS4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/action/storage_attestation","attest_author":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/action/author_attestation","sign_citation":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/action/citation_signature","submit_replication":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/action/replication_record"}},"created_at":"2026-07-05T09:03:29.179897+00:00","updated_at":"2026-07-05T09:03:29.179897+00:00"}