{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QLIGREK3KJN7NT4SFOBJRDR5RJ","short_pith_number":"pith:QLIGREK3","schema_version":"1.0","canonical_sha256":"82d068915b525bf6cf922b82988e3d8a5405a8b434070908a1a4be7a14fd0458","source":{"kind":"arxiv","id":"2605.24784","version":1},"attestation_state":"computed","paper":{"title":"GRAIL: AI translation for scientists application workflow on satellite data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ahmed ElDawy, Zhuocheng Shang","submitted_at":"2026-05-23T23:58:27Z","abstract_excerpt":"Domain scientists increasingly develop Python scripts to analyze satellite imagery but they lack scalability to large-scale data. This paper demonstrates GRAIL, an agentic translation system that converts Python geospatial workflows into executable Spark-based programs without requiring scientists to learn a new framework. Rather than fine-tuning a specialized LLM model, GRAIL adapts RDPro, a Scala library for satellite data analysis, to make it LLM-ready using structured documentation, API alias functions, and repair-oriented error logs. Translation is structured as a LangGraph pipeline that "},"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":"2605.24784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T23:58:27Z","cross_cats_sorted":[],"title_canon_sha256":"e7cbb93c6d134700005ea0e2c574f6f14dfcd1bade24f6e740a3405871b14a28","abstract_canon_sha256":"1186cd8d91bc2a5e02dddab0d5ae213501857d409c7aa171b2a5fae12499a35a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:57.965628Z","signature_b64":"rILZnaoBBZokwSlXC8dm/YeaSDUVTqzQsQalFXwWCVZGCj0xVnFU3jnM342lfhRygSQF4RW28bgWHuxAvhHSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82d068915b525bf6cf922b82988e3d8a5405a8b434070908a1a4be7a14fd0458","last_reissued_at":"2026-05-26T01:03:57.964992Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:57.964992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRAIL: AI translation for scientists application workflow on satellite data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ahmed ElDawy, Zhuocheng Shang","submitted_at":"2026-05-23T23:58:27Z","abstract_excerpt":"Domain scientists increasingly develop Python scripts to analyze satellite imagery but they lack scalability to large-scale data. This paper demonstrates GRAIL, an agentic translation system that converts Python geospatial workflows into executable Spark-based programs without requiring scientists to learn a new framework. Rather than fine-tuning a specialized LLM model, GRAIL adapts RDPro, a Scala library for satellite data analysis, to make it LLM-ready using structured documentation, API alias functions, and repair-oriented error logs. Translation is structured as a LangGraph pipeline that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24784","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/2605.24784/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":"2605.24784","created_at":"2026-05-26T01:03:57.965072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24784v1","created_at":"2026-05-26T01:03:57.965072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24784","created_at":"2026-05-26T01:03:57.965072+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLIGREK3KJN7","created_at":"2026-05-26T01:03:57.965072+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLIGREK3KJN7NT4S","created_at":"2026-05-26T01:03:57.965072+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLIGREK3","created_at":"2026-05-26T01:03:57.965072+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/QLIGREK3KJN7NT4SFOBJRDR5RJ","json":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ.json","graph_json":"https://pith.science/api/pith-number/QLIGREK3KJN7NT4SFOBJRDR5RJ/graph.json","events_json":"https://pith.science/api/pith-number/QLIGREK3KJN7NT4SFOBJRDR5RJ/events.json","paper":"https://pith.science/paper/QLIGREK3"},"agent_actions":{"view_html":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ","download_json":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ.json","view_paper":"https://pith.science/paper/QLIGREK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24784&json=true","fetch_graph":"https://pith.science/api/pith-number/QLIGREK3KJN7NT4SFOBJRDR5RJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QLIGREK3KJN7NT4SFOBJRDR5RJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ/action/storage_attestation","attest_author":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ/action/author_attestation","sign_citation":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ/action/citation_signature","submit_replication":"https://pith.science/pith/QLIGREK3KJN7NT4SFOBJRDR5RJ/action/replication_record"}},"created_at":"2026-05-26T01:03:57.965072+00:00","updated_at":"2026-05-26T01:03:57.965072+00:00"}