{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WWL2JY76SFQLNM4Y4HJH6HCS4Y","short_pith_number":"pith:WWL2JY76","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"},"canonical_sha256":"b597a4e3fe9160b6b398e1d27f1c52e603952e5f258ee2a3d76d5a63d3079cd0","source":{"kind":"arxiv","id":"2409.03295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03295","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03295v1","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03295","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"WWL2JY76SFQL","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"WWL2JY76SFQLNM4Y","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"WWL2JY76","created_at":"2026-07-05T09:03:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WWL2JY76SFQLNM4Y4HJH6HCS4Y","target":"record","payload":{"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"},"canonical_sha256":"b597a4e3fe9160b6b398e1d27f1c52e603952e5f258ee2a3d76d5a63d3079cd0","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"},"source_kind":"arxiv","source_id":"2409.03295","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RwMTu0+DNLsS52PzNVbCAdwWBkQndAfg/S5AlvKbGUCqcRBnkhWZfq9slvDIpIPcwZUYfONREfFHIAFyYXcxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:15.340562Z"},"content_sha256":"a48d47812635621c899f9b4dd0ead5b4ad15666801275efec5de454f255f1771","schema_version":"1.0","event_id":"sha256:a48d47812635621c899f9b4dd0ead5b4ad15666801275efec5de454f255f1771"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WWL2JY76SFQLNM4Y4HJH6HCS4Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jufAPsboFpSQ6BbsVA2bM3TN52GZGqJjfVjzaIsYSPmdOtDKH3NQPlWWpWZkS9mKIeRinKMGLRuqqrPXHXkYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:15.341471Z"},"content_sha256":"82377953213e210937737910834842234ed8fd1cff2bffa3757506104a93957e","schema_version":"1.0","event_id":"sha256:82377953213e210937737910834842234ed8fd1cff2bffa3757506104a93957e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/bundle.json","state_url":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T11:25:15Z","links":{"resolver":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y","bundle":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/bundle.json","state":"https://pith.science/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWL2JY76SFQLNM4Y4HJH6HCS4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WWL2JY76SFQLNM4Y4HJH6HCS4Y","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":"9b408478c99d2b399fd5c17499bbd10871152ee0607324c0e9707f8a4ab60374","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T07:03:23Z","title_canon_sha256":"8a37115948c8cfcbdf7869ff7c2cdcb6d15be9b36f62ecb1695e4b1259e196bd"},"schema_version":"1.0","source":{"id":"2409.03295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03295","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03295v1","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03295","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"WWL2JY76SFQL","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"WWL2JY76SFQLNM4Y","created_at":"2026-07-05T09:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"WWL2JY76","created_at":"2026-07-05T09:03:29Z"}],"graph_snapshots":[{"event_id":"sha256:82377953213e210937737910834842234ed8fd1cff2bffa3757506104a93957e","target":"graph","created_at":"2026-07-05T09:03:29Z","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/2409.03295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Daniela Noemi Rim, DongNyeong Heo, Heeyoul Choi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T07:03:23Z","title":"N-gram Prediction and Word Difference Representations for Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03295","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:a48d47812635621c899f9b4dd0ead5b4ad15666801275efec5de454f255f1771","target":"record","created_at":"2026-07-05T09:03:29Z","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":"9b408478c99d2b399fd5c17499bbd10871152ee0607324c0e9707f8a4ab60374","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T07:03:23Z","title_canon_sha256":"8a37115948c8cfcbdf7869ff7c2cdcb6d15be9b36f62ecb1695e4b1259e196bd"},"schema_version":"1.0","source":{"id":"2409.03295","kind":"arxiv","version":1}},"canonical_sha256":"b597a4e3fe9160b6b398e1d27f1c52e603952e5f258ee2a3d76d5a63d3079cd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b597a4e3fe9160b6b398e1d27f1c52e603952e5f258ee2a3d76d5a63d3079cd0","first_computed_at":"2026-07-05T09:03:29.179838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:29.179838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yuIsr4tgIvqEkSJsJlkDG1U4fVok+/l45tE9NkUEzqToWqyeS0GmDxq3q+0gUiHkPivxWi0I+JJDSKJQSl7EAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:29.180336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a48d47812635621c899f9b4dd0ead5b4ad15666801275efec5de454f255f1771","sha256:82377953213e210937737910834842234ed8fd1cff2bffa3757506104a93957e"],"state_sha256":"5b4dd23c8f753e08e85deac6b61dc049e782f01e19ff3680d2a3d40dc0300cb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ge0g6YOGQtEJwf5f0n82rD6o0Rs+rx5FLIDC0r66mmTCFJlhK9g+x7gIs4gIK0mo898IRljFAJap3hLm7TgvDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:25:15.347962Z","bundle_sha256":"1b298dd413408b4b2a979bb6656fcb4ae1c8c4eef30fc0aa8b4ba029ca2c49d4"}}