{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G434RH5W7CEAB4QA4M5UIGN6FA","short_pith_number":"pith:G434RH5W","schema_version":"1.0","canonical_sha256":"3737c89fb6f88800f200e33b4419be282bddccc92a2ed2f74727e3b8739706de","source":{"kind":"arxiv","id":"2506.22742","version":1},"attestation_state":"computed","paper":{"title":"RAILS: Retrieval-Augmented Intelligence for Learning Software Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Baidya Saha, Devraj Parmar, Happy Hasmukhbhai Patel, Md. Morshedul Islam, Sindhuja Prabhakaran, Wali Mohammad Abdullah","submitted_at":"2025-06-28T03:30:04Z","abstract_excerpt":"Large Language Models (LLMs) like GPT-3.5-Turbo are increasingly used to assist software development, yet they often produce incomplete code or incorrect imports, especially when lacking access to external or project-specific documentation. We introduce RAILS (Retrieval-Augmented Intelligence for Learning Software Development), a framework that augments LLM prompts with semantically retrieved context from curated Java resources using FAISS and OpenAI embeddings. RAILS incorporates an iterative validation loop guided by compiler feedback to refine suggestions. We evaluated RAILS on 78 real-worl"},"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":"2506.22742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-28T03:30:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f12c432273df5f6228a8ac5fd932717060d7faa21f452c5dcea722ac51f386b3","abstract_canon_sha256":"1434ad5ff2b90e18c1b4514e5e7514cf67a94f83ae1585e3fb8f77da9636c546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:44.527210Z","signature_b64":"84bw4IfqjCouVVl40aQhB7OuWWKvBWUrnzAEcjb4Pq86UAzWyTLi6l+mGpk8oxRi6ist7j9O7CKhcJn5GumGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3737c89fb6f88800f200e33b4419be282bddccc92a2ed2f74727e3b8739706de","last_reissued_at":"2026-07-05T11:28:44.526822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:44.526822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAILS: Retrieval-Augmented Intelligence for Learning Software Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Baidya Saha, Devraj Parmar, Happy Hasmukhbhai Patel, Md. Morshedul Islam, Sindhuja Prabhakaran, Wali Mohammad Abdullah","submitted_at":"2025-06-28T03:30:04Z","abstract_excerpt":"Large Language Models (LLMs) like GPT-3.5-Turbo are increasingly used to assist software development, yet they often produce incomplete code or incorrect imports, especially when lacking access to external or project-specific documentation. We introduce RAILS (Retrieval-Augmented Intelligence for Learning Software Development), a framework that augments LLM prompts with semantically retrieved context from curated Java resources using FAISS and OpenAI embeddings. RAILS incorporates an iterative validation loop guided by compiler feedback to refine suggestions. We evaluated RAILS on 78 real-worl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22742","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/2506.22742/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":"2506.22742","created_at":"2026-07-05T11:28:44.526883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22742v1","created_at":"2026-07-05T11:28:44.526883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22742","created_at":"2026-07-05T11:28:44.526883+00:00"},{"alias_kind":"pith_short_12","alias_value":"G434RH5W7CEA","created_at":"2026-07-05T11:28:44.526883+00:00"},{"alias_kind":"pith_short_16","alias_value":"G434RH5W7CEAB4QA","created_at":"2026-07-05T11:28:44.526883+00:00"},{"alias_kind":"pith_short_8","alias_value":"G434RH5W","created_at":"2026-07-05T11:28:44.526883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA","json":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA.json","graph_json":"https://pith.science/api/pith-number/G434RH5W7CEAB4QA4M5UIGN6FA/graph.json","events_json":"https://pith.science/api/pith-number/G434RH5W7CEAB4QA4M5UIGN6FA/events.json","paper":"https://pith.science/paper/G434RH5W"},"agent_actions":{"view_html":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA","download_json":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA.json","view_paper":"https://pith.science/paper/G434RH5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22742&json=true","fetch_graph":"https://pith.science/api/pith-number/G434RH5W7CEAB4QA4M5UIGN6FA/graph.json","fetch_events":"https://pith.science/api/pith-number/G434RH5W7CEAB4QA4M5UIGN6FA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA/action/storage_attestation","attest_author":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA/action/author_attestation","sign_citation":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA/action/citation_signature","submit_replication":"https://pith.science/pith/G434RH5W7CEAB4QA4M5UIGN6FA/action/replication_record"}},"created_at":"2026-07-05T11:28:44.526883+00:00","updated_at":"2026-07-05T11:28:44.526883+00:00"}