{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VPPO6YWLZFJABP5J6MG5YSRWTA","short_pith_number":"pith:VPPO6YWL","schema_version":"1.0","canonical_sha256":"abdeef62cbc95200bfa9f30ddc4a36983821fcb25ad4ae23dc5f95a631a282db","source":{"kind":"arxiv","id":"2306.14893","version":1},"attestation_state":"computed","paper":{"title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Canwen Xu, Daya Guo, Jian Yin, Julian McAuley, Nan Duan","submitted_at":"2023-06-26T17:59:24Z","abstract_excerpt":"In this paper, we introduce a new task for code completion that focuses on handling long code input and propose a sparse Transformer model, called LongCoder, to address this task. LongCoder employs a sliding window mechanism for self-attention and introduces two types of globally accessible tokens - bridge tokens and memory tokens - to improve performance and efficiency. Bridge tokens are inserted throughout the input sequence to aggregate local information and facilitate global interaction, while memory tokens are included to highlight important statements that may be invoked later and need t"},"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":"2306.14893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-06-26T17:59:24Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"259e61623eb7bf7ad694ed6e43e8bf10334945b22833b1a16d0ca0f24fb3534d","abstract_canon_sha256":"b6b2d831cd48c81acbf122dce0efa822ea5cbf5fd8c31bf100a12e4b4573a650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:41.843429Z","signature_b64":"HzS64NIaPbwsuYYX/dqZKZYXdJFR+crd1RVXJo5tuA0yImjmKqWSkFBHPvjkPjSTkBMLWmmAgWh+aWp+pE6MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abdeef62cbc95200bfa9f30ddc4a36983821fcb25ad4ae23dc5f95a631a282db","last_reissued_at":"2026-07-05T06:24:41.842988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:41.842988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Canwen Xu, Daya Guo, Jian Yin, Julian McAuley, Nan Duan","submitted_at":"2023-06-26T17:59:24Z","abstract_excerpt":"In this paper, we introduce a new task for code completion that focuses on handling long code input and propose a sparse Transformer model, called LongCoder, to address this task. LongCoder employs a sliding window mechanism for self-attention and introduces two types of globally accessible tokens - bridge tokens and memory tokens - to improve performance and efficiency. Bridge tokens are inserted throughout the input sequence to aggregate local information and facilitate global interaction, while memory tokens are included to highlight important statements that may be invoked later and need t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14893","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/2306.14893/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":"2306.14893","created_at":"2026-07-05T06:24:41.843042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14893v1","created_at":"2026-07-05T06:24:41.843042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14893","created_at":"2026-07-05T06:24:41.843042+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPPO6YWLZFJA","created_at":"2026-07-05T06:24:41.843042+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPPO6YWLZFJABP5J","created_at":"2026-07-05T06:24:41.843042+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPPO6YWL","created_at":"2026-07-05T06:24:41.843042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29563","citing_title":"Coverage-Driven KV Cache Eviction for Efficient and Improved Inference of LLM","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20173","citing_title":"Qiskit Code Migration with LLMs","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2407.11550","citing_title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2308.14508","citing_title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02069","citing_title":"PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA","json":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA.json","graph_json":"https://pith.science/api/pith-number/VPPO6YWLZFJABP5J6MG5YSRWTA/graph.json","events_json":"https://pith.science/api/pith-number/VPPO6YWLZFJABP5J6MG5YSRWTA/events.json","paper":"https://pith.science/paper/VPPO6YWL"},"agent_actions":{"view_html":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA","download_json":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA.json","view_paper":"https://pith.science/paper/VPPO6YWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14893&json=true","fetch_graph":"https://pith.science/api/pith-number/VPPO6YWLZFJABP5J6MG5YSRWTA/graph.json","fetch_events":"https://pith.science/api/pith-number/VPPO6YWLZFJABP5J6MG5YSRWTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA/action/storage_attestation","attest_author":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA/action/author_attestation","sign_citation":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA/action/citation_signature","submit_replication":"https://pith.science/pith/VPPO6YWLZFJABP5J6MG5YSRWTA/action/replication_record"}},"created_at":"2026-07-05T06:24:41.843042+00:00","updated_at":"2026-07-05T06:24:41.843042+00:00"}