{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RP5TWVBDFBX43JG3XVYXVUJ5OK","short_pith_number":"pith:RP5TWVBD","canonical_record":{"source":{"id":"2503.20589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T14:41:38Z","cross_cats_sorted":[],"title_canon_sha256":"4f12d23836286dcbd6e91a3eed9e876c1768f18bf69bbec99bf24a5075bfe792","abstract_canon_sha256":"3857cdeb8341555f1f268ff536e5ecc3b4c43728537779713fe326624834b8b8"},"schema_version":"1.0"},"canonical_sha256":"8bfb3b5423286fcda4dbbd717ad13d72b93f269ed672c532a56257e7382620c4","source":{"kind":"arxiv","id":"2503.20589","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20589","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20589v1","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20589","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"pith_short_12","alias_value":"RP5TWVBDFBX4","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"pith_short_16","alias_value":"RP5TWVBDFBX43JG3","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"pith_short_8","alias_value":"RP5TWVBD","created_at":"2026-07-05T10:39:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RP5TWVBDFBX43JG3XVYXVUJ5OK","target":"record","payload":{"canonical_record":{"source":{"id":"2503.20589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T14:41:38Z","cross_cats_sorted":[],"title_canon_sha256":"4f12d23836286dcbd6e91a3eed9e876c1768f18bf69bbec99bf24a5075bfe792","abstract_canon_sha256":"3857cdeb8341555f1f268ff536e5ecc3b4c43728537779713fe326624834b8b8"},"schema_version":"1.0"},"canonical_sha256":"8bfb3b5423286fcda4dbbd717ad13d72b93f269ed672c532a56257e7382620c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:40.891824Z","signature_b64":"eZhLhLTO8MaXpNmCS0COfIRwLn/4asb/zyR1xcrDc64FHcF5VnaD4eUuLTR4NejtmV+nzWvRWxMwXbizPZ5ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bfb3b5423286fcda4dbbd717ad13d72b93f269ed672c532a56257e7382620c4","last_reissued_at":"2026-07-05T10:39:40.891302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:40.891302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.20589","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":"2026-07-05T10:39:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9IUpirJrsMF2Ji8meIWFGisUxvhoF+LHn/VPKPYSO/ogu4Kmd8wxvIt7T3LqQnn8eVRSEvvehCZJIdJv5rPbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:00:48.667588Z"},"content_sha256":"b490f2ba5971407dce07d778450019f4abb0528ce11e2998dca2bbb36ef04104","schema_version":"1.0","event_id":"sha256:b490f2ba5971407dce07d778450019f4abb0528ce11e2998dca2bbb36ef04104"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RP5TWVBDFBX43JG3XVYXVUJ5OK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Juntao Chen, Mingwei Liu, Tianyue Jiang, Wenchao Gu, Xilin Liu, Xingzhe Li, Yanlin Wang, Yuchi Ma, Zibin Zheng","submitted_at":"2025-03-26T14:41:38Z","abstract_excerpt":"Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted, the effectiveness of different retrieved information sources-contextual code, APIs, and similar snippets-has not been rigorously analyzed. Through an empirical study on two benchmarks, we demonstrate that in-context code and potential API information significantly enhance LLM performance, whereas retrieved similar code often introduces noise, degrading resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20589","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/2503.20589/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":"2026-07-05T10:39:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2m0HAvXE35woSCwjWaUtlRsxO/5lZrwNUeDVVExyFZdMDt38D8vG3sj+umExLPNRUdw+TtnL4GhwmWT5KVWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:00:48.668090Z"},"content_sha256":"380d65589bd33a5696009165059e77e8f6461acd27980e1a10742d0081336c47","schema_version":"1.0","event_id":"sha256:380d65589bd33a5696009165059e77e8f6461acd27980e1a10742d0081336c47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RP5TWVBDFBX43JG3XVYXVUJ5OK/bundle.json","state_url":"https://pith.science/pith/RP5TWVBDFBX43JG3XVYXVUJ5OK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RP5TWVBDFBX43JG3XVYXVUJ5OK/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":"2026-08-06T06:00:48Z","links":{"resolver":"https://pith.science/pith/RP5TWVBDFBX43JG3XVYXVUJ5OK","bundle":"https://pith.science/pith/RP5TWVBDFBX43JG3XVYXVUJ5OK/bundle.json","state":"https://pith.science/pith/RP5TWVBDFBX43JG3XVYXVUJ5OK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RP5TWVBDFBX43JG3XVYXVUJ5OK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RP5TWVBDFBX43JG3XVYXVUJ5OK","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":"3857cdeb8341555f1f268ff536e5ecc3b4c43728537779713fe326624834b8b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T14:41:38Z","title_canon_sha256":"4f12d23836286dcbd6e91a3eed9e876c1768f18bf69bbec99bf24a5075bfe792"},"schema_version":"1.0","source":{"id":"2503.20589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20589","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20589v1","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20589","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"pith_short_12","alias_value":"RP5TWVBDFBX4","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"pith_short_16","alias_value":"RP5TWVBDFBX43JG3","created_at":"2026-07-05T10:39:40Z"},{"alias_kind":"pith_short_8","alias_value":"RP5TWVBD","created_at":"2026-07-05T10:39:40Z"}],"graph_snapshots":[{"event_id":"sha256:380d65589bd33a5696009165059e77e8f6461acd27980e1a10742d0081336c47","target":"graph","created_at":"2026-07-05T10:39:40Z","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/2503.20589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted, the effectiveness of different retrieved information sources-contextual code, APIs, and similar snippets-has not been rigorously analyzed. Through an empirical study on two benchmarks, we demonstrate that in-context code and potential API information significantly enhance LLM performance, whereas retrieved similar code often introduces noise, degrading resu","authors_text":"Juntao Chen, Mingwei Liu, Tianyue Jiang, Wenchao Gu, Xilin Liu, Xingzhe Li, Yanlin Wang, Yuchi Ma, Zibin Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T14:41:38Z","title":"What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20589","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:b490f2ba5971407dce07d778450019f4abb0528ce11e2998dca2bbb36ef04104","target":"record","created_at":"2026-07-05T10:39:40Z","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":"3857cdeb8341555f1f268ff536e5ecc3b4c43728537779713fe326624834b8b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T14:41:38Z","title_canon_sha256":"4f12d23836286dcbd6e91a3eed9e876c1768f18bf69bbec99bf24a5075bfe792"},"schema_version":"1.0","source":{"id":"2503.20589","kind":"arxiv","version":1}},"canonical_sha256":"8bfb3b5423286fcda4dbbd717ad13d72b93f269ed672c532a56257e7382620c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bfb3b5423286fcda4dbbd717ad13d72b93f269ed672c532a56257e7382620c4","first_computed_at":"2026-07-05T10:39:40.891302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:40.891302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eZhLhLTO8MaXpNmCS0COfIRwLn/4asb/zyR1xcrDc64FHcF5VnaD4eUuLTR4NejtmV+nzWvRWxMwXbizPZ5ABA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:40.891824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b490f2ba5971407dce07d778450019f4abb0528ce11e2998dca2bbb36ef04104","sha256:380d65589bd33a5696009165059e77e8f6461acd27980e1a10742d0081336c47"],"state_sha256":"fce191b57a559cfeca8a383618a03b10158aa156d962f1cf61a05de053a9cd92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QvGbESpDd3hZeFjSPtC6T/Hp1MZNI4+F8xQdfGCgHG4pnLazgbsUy2Od0Fcd9mqiKRCdmBysyN06tzdXGYi8Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:00:48.671825Z","bundle_sha256":"df4095eea7df1819e4a6f4b5d9a49fa4530b059f76951971373b0264f3cd514e"}}