{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IEXJWL5P72J5FWE5RSGCO5YIKX","short_pith_number":"pith:IEXJWL5P","schema_version":"1.0","canonical_sha256":"412e9b2faffe93d2d89d8c8c27770855fd2188c372452d3c4d7982c68524cb2b","source":{"kind":"arxiv","id":"2403.15747","version":1},"attestation_state":"computed","paper":{"title":"CodeShell Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chang Gao, Rui Xie, Shikun Zhang, Wei Ye, Zhengran Zeng, Zhuohao Yu","submitted_at":"2024-03-23T07:29:41Z","abstract_excerpt":"Code large language models mark a pivotal breakthrough in artificial intelligence. They are specifically crafted to understand and generate programming languages, significantly boosting the efficiency of coding development workflows. In this technical report, we present CodeShell-Base, a seven billion-parameter foundation model with 8K context length, showcasing exceptional proficiency in code comprehension. By incorporating Grouped-Query Attention and Rotary Positional Embedding into GPT-2, CodeShell-Base integrates the structural merits of StarCoder and CodeLlama and forms its unique archite"},"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":"2403.15747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-23T07:29:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e28f0abf0690609597799aea6b4a19766246d9ed7c96d08e98084e42a14fdd68","abstract_canon_sha256":"3448419a1a8ff51091dcf0bf140e4474e1081e7aa8f7a19eb31ea84ee0bbdecc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:05.688134Z","signature_b64":"+5Q3XrriqEqXpiN84ULX3cIxw11cEGMbI+QVRODNO2fiz9zcsm1RAaPVikud/NJTC1/DmeWhzfPCXNMh0tZuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"412e9b2faffe93d2d89d8c8c27770855fd2188c372452d3c4d7982c68524cb2b","last_reissued_at":"2026-07-05T08:00:05.687725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:05.687725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeShell Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chang Gao, Rui Xie, Shikun Zhang, Wei Ye, Zhengran Zeng, Zhuohao Yu","submitted_at":"2024-03-23T07:29:41Z","abstract_excerpt":"Code large language models mark a pivotal breakthrough in artificial intelligence. They are specifically crafted to understand and generate programming languages, significantly boosting the efficiency of coding development workflows. In this technical report, we present CodeShell-Base, a seven billion-parameter foundation model with 8K context length, showcasing exceptional proficiency in code comprehension. By incorporating Grouped-Query Attention and Rotary Positional Embedding into GPT-2, CodeShell-Base integrates the structural merits of StarCoder and CodeLlama and forms its unique archite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15747","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/2403.15747/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":"2403.15747","created_at":"2026-07-05T08:00:05.687780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15747v1","created_at":"2026-07-05T08:00:05.687780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15747","created_at":"2026-07-05T08:00:05.687780+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEXJWL5P72J5","created_at":"2026-07-05T08:00:05.687780+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEXJWL5P72J5FWE5","created_at":"2026-07-05T08:00:05.687780+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEXJWL5P","created_at":"2026-07-05T08:00:05.687780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":292,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX","json":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX.json","graph_json":"https://pith.science/api/pith-number/IEXJWL5P72J5FWE5RSGCO5YIKX/graph.json","events_json":"https://pith.science/api/pith-number/IEXJWL5P72J5FWE5RSGCO5YIKX/events.json","paper":"https://pith.science/paper/IEXJWL5P"},"agent_actions":{"view_html":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX","download_json":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX.json","view_paper":"https://pith.science/paper/IEXJWL5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15747&json=true","fetch_graph":"https://pith.science/api/pith-number/IEXJWL5P72J5FWE5RSGCO5YIKX/graph.json","fetch_events":"https://pith.science/api/pith-number/IEXJWL5P72J5FWE5RSGCO5YIKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX/action/storage_attestation","attest_author":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX/action/author_attestation","sign_citation":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX/action/citation_signature","submit_replication":"https://pith.science/pith/IEXJWL5P72J5FWE5RSGCO5YIKX/action/replication_record"}},"created_at":"2026-07-05T08:00:05.687780+00:00","updated_at":"2026-07-05T08:00:05.687780+00:00"}