{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PJWBLHESSPQPBF427ELZS3L2IJ","short_pith_number":"pith:PJWBLHES","schema_version":"1.0","canonical_sha256":"7a6c159c9293e0f0979af917996d7a424efa8fbd985888cc3f4775c9b0967d94","source":{"kind":"arxiv","id":"2505.22107","version":4},"attestation_state":"computed","paper":{"title":"Curse of High Dimensionality Issue in Transformer for Long-context Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Mingkui Tan, Qianyue Wang, Shuhai Zhang, Yaofo Chen, Yuanqing Li, Zeng You, Zhijie Qiu, Zhiquan Wen","submitted_at":"2025-05-28T08:34:46Z","abstract_excerpt":"Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies due to \\textit{redundant} attention computations: while attention weights are often \\textit{sparse}, all tokens consume \\textit{equal} computational resources. In this paper, we reformulate traditional probabilistic sequence modeling as a \\textit{supervised learning task}, enabling the separation of relevant and irrelevant tokens and providing a clearer unde"},"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":"2505.22107","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T08:34:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0d7eadf8836729b712f087a2033da633b5b16d5183c44e714a3506623f25754c","abstract_canon_sha256":"69af495bbbe3c464a5e2ad813ba66fd1f71793b1589e3cf2afc7f6ea6f49d314"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:47.184533Z","signature_b64":"7WU45smn+Czdyt5s9fFDeuOD3/5cG01/kzm82+m8Un1qBsKXS7B3eY6IC8M14WOnxjyg8fMNw2TBQlYaY9AwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a6c159c9293e0f0979af917996d7a424efa8fbd985888cc3f4775c9b0967d94","last_reissued_at":"2026-07-05T11:53:47.184030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:47.184030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curse of High Dimensionality Issue in Transformer for Long-context Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Mingkui Tan, Qianyue Wang, Shuhai Zhang, Yaofo Chen, Yuanqing Li, Zeng You, Zhijie Qiu, Zhiquan Wen","submitted_at":"2025-05-28T08:34:46Z","abstract_excerpt":"Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies due to \\textit{redundant} attention computations: while attention weights are often \\textit{sparse}, all tokens consume \\textit{equal} computational resources. In this paper, we reformulate traditional probabilistic sequence modeling as a \\textit{supervised learning task}, enabling the separation of relevant and irrelevant tokens and providing a clearer unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22107","kind":"arxiv","version":4},"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/2505.22107/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":"2505.22107","created_at":"2026-07-05T11:53:47.184089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22107v4","created_at":"2026-07-05T11:53:47.184089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22107","created_at":"2026-07-05T11:53:47.184089+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJWBLHESSPQP","created_at":"2026-07-05T11:53:47.184089+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJWBLHESSPQPBF42","created_at":"2026-07-05T11:53:47.184089+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJWBLHES","created_at":"2026-07-05T11:53:47.184089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07183","citing_title":"Geometry of Semantic Space: Comparative Study of Discrete and Continuous Models","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ","json":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ.json","graph_json":"https://pith.science/api/pith-number/PJWBLHESSPQPBF427ELZS3L2IJ/graph.json","events_json":"https://pith.science/api/pith-number/PJWBLHESSPQPBF427ELZS3L2IJ/events.json","paper":"https://pith.science/paper/PJWBLHES"},"agent_actions":{"view_html":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ","download_json":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ.json","view_paper":"https://pith.science/paper/PJWBLHES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22107&json=true","fetch_graph":"https://pith.science/api/pith-number/PJWBLHESSPQPBF427ELZS3L2IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PJWBLHESSPQPBF427ELZS3L2IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ/action/storage_attestation","attest_author":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ/action/author_attestation","sign_citation":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ/action/citation_signature","submit_replication":"https://pith.science/pith/PJWBLHESSPQPBF427ELZS3L2IJ/action/replication_record"}},"created_at":"2026-07-05T11:53:47.184089+00:00","updated_at":"2026-07-05T11:53:47.184089+00:00"}