{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WXXM7A2ROCTJ37TL75EWPI67RM","short_pith_number":"pith:WXXM7A2R","schema_version":"1.0","canonical_sha256":"b5eecf835170a69dfe6bff4967a3df8b35aa29d35612e038b6780b85ba12a478","source":{"kind":"arxiv","id":"2407.21049","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Long Range Dependency Handling in Code Generation LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Donghao Ren, Yannick Assogba","submitted_at":"2024-07-23T02:45:22Z","abstract_excerpt":"As language models support larger and larger context sizes, evaluating their ability to make effective use of that context becomes increasingly important. We analyze the ability of several code generation models to handle long range dependencies using a suite of multi-step key retrieval tasks in context windows up to 8k tokens in length. The tasks progressively increase in difficulty and allow more nuanced evaluation of model capabilities than tests like the popular needle-in-the-haystack test. We find that performance degrades significantly for many models (up to 2x) when a function reference"},"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":"2407.21049","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T02:45:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"459167f5f2f24357192634e2ac8abd7eb9050169d80e1192c38cfc4e00c47da4","abstract_canon_sha256":"7a8b8d6baede64822de14f70bef50da54d742a23c127dbc17e9103369a3ebe2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:43.249907Z","signature_b64":"bqnQHZtjyjXMzgXc/blcxDVcE96rSFTkd5F0YIYEoi3N8bhP3r3CX7nz4ggbtROXn02FMDrWPHXfcIJsBFQyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5eecf835170a69dfe6bff4967a3df8b35aa29d35612e038b6780b85ba12a478","last_reissued_at":"2026-07-05T11:26:43.249406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:43.249406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Long Range Dependency Handling in Code Generation LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Donghao Ren, Yannick Assogba","submitted_at":"2024-07-23T02:45:22Z","abstract_excerpt":"As language models support larger and larger context sizes, evaluating their ability to make effective use of that context becomes increasingly important. We analyze the ability of several code generation models to handle long range dependencies using a suite of multi-step key retrieval tasks in context windows up to 8k tokens in length. The tasks progressively increase in difficulty and allow more nuanced evaluation of model capabilities than tests like the popular needle-in-the-haystack test. We find that performance degrades significantly for many models (up to 2x) when a function reference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21049","kind":"arxiv","version":2},"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/2407.21049/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":"2407.21049","created_at":"2026-07-05T11:26:43.249462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21049v2","created_at":"2026-07-05T11:26:43.249462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21049","created_at":"2026-07-05T11:26:43.249462+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXXM7A2ROCTJ","created_at":"2026-07-05T11:26:43.249462+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXXM7A2ROCTJ37TL","created_at":"2026-07-05T11:26:43.249462+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXXM7A2R","created_at":"2026-07-05T11:26:43.249462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02962","citing_title":"Robot builds a robot's brain: AI generated drone command and control station hosted in the sky","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM","json":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM.json","graph_json":"https://pith.science/api/pith-number/WXXM7A2ROCTJ37TL75EWPI67RM/graph.json","events_json":"https://pith.science/api/pith-number/WXXM7A2ROCTJ37TL75EWPI67RM/events.json","paper":"https://pith.science/paper/WXXM7A2R"},"agent_actions":{"view_html":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM","download_json":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM.json","view_paper":"https://pith.science/paper/WXXM7A2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21049&json=true","fetch_graph":"https://pith.science/api/pith-number/WXXM7A2ROCTJ37TL75EWPI67RM/graph.json","fetch_events":"https://pith.science/api/pith-number/WXXM7A2ROCTJ37TL75EWPI67RM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM/action/storage_attestation","attest_author":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM/action/author_attestation","sign_citation":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM/action/citation_signature","submit_replication":"https://pith.science/pith/WXXM7A2ROCTJ37TL75EWPI67RM/action/replication_record"}},"created_at":"2026-07-05T11:26:43.249462+00:00","updated_at":"2026-07-05T11:26:43.249462+00:00"}