{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AGD3YZH3EI3EBD6CEXTI6C5ECN","short_pith_number":"pith:AGD3YZH3","schema_version":"1.0","canonical_sha256":"0187bc64fb2236408fc225e68f0ba4134780bb4d8c409db755d5b153811aa6df","source":{"kind":"arxiv","id":"2512.01089","version":2},"attestation_state":"computed","paper":{"title":"CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peter Jansen, Pragnya Narasimha, Samiah Hassan","submitted_at":"2025-11-30T21:19:10Z","abstract_excerpt":"Automated Scientific Discovery (ASD) systems can help automatically generate and run code-based experiments, but their capabilities are limited by the code they can reliably generate from parametric knowledge alone. As a result, current systems either mutate a small number of manually-crafted experiment examples, or operate solely from parametric knowledge, limiting quality and reach. We introduce CodeDistiller, a system that automatically distills large collections of scientific Github repositories into a vetted library of working domain-specific code examples, allowing ASD agents to expand t"},"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":"2512.01089","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-30T21:19:10Z","cross_cats_sorted":[],"title_canon_sha256":"61499d711f653d36ec2d874879430aec3501e38647220d5511794abec83811d9","abstract_canon_sha256":"645d815638bdd59748597209b73c2b2d4c0f42bfa1019be65377c87575cf226b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:29.177241Z","signature_b64":"zPRazzSOSnNR3xYsr+B6ciypfN2ZiFonhfi+zx8J2sSZCZGhU7B7FZAB0ywfFrZLDrSOKDQA0irN/n3KQ2NKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0187bc64fb2236408fc225e68f0ba4134780bb4d8c409db755d5b153811aa6df","last_reissued_at":"2026-05-20T00:00:29.176647Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:29.176647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peter Jansen, Pragnya Narasimha, Samiah Hassan","submitted_at":"2025-11-30T21:19:10Z","abstract_excerpt":"Automated Scientific Discovery (ASD) systems can help automatically generate and run code-based experiments, but their capabilities are limited by the code they can reliably generate from parametric knowledge alone. As a result, current systems either mutate a small number of manually-crafted experiment examples, or operate solely from parametric knowledge, limiting quality and reach. We introduce CodeDistiller, a system that automatically distills large collections of scientific Github repositories into a vetted library of working domain-specific code examples, allowing ASD agents to expand t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.01089","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/2512.01089/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":"2512.01089","created_at":"2026-05-20T00:00:29.176749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.01089v2","created_at":"2026-05-20T00:00:29.176749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.01089","created_at":"2026-05-20T00:00:29.176749+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGD3YZH3EI3E","created_at":"2026-05-20T00:00:29.176749+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGD3YZH3EI3EBD6C","created_at":"2026-05-20T00:00:29.176749+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGD3YZH3","created_at":"2026-05-20T00:00:29.176749+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/AGD3YZH3EI3EBD6CEXTI6C5ECN","json":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN.json","graph_json":"https://pith.science/api/pith-number/AGD3YZH3EI3EBD6CEXTI6C5ECN/graph.json","events_json":"https://pith.science/api/pith-number/AGD3YZH3EI3EBD6CEXTI6C5ECN/events.json","paper":"https://pith.science/paper/AGD3YZH3"},"agent_actions":{"view_html":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN","download_json":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN.json","view_paper":"https://pith.science/paper/AGD3YZH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.01089&json=true","fetch_graph":"https://pith.science/api/pith-number/AGD3YZH3EI3EBD6CEXTI6C5ECN/graph.json","fetch_events":"https://pith.science/api/pith-number/AGD3YZH3EI3EBD6CEXTI6C5ECN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN/action/storage_attestation","attest_author":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN/action/author_attestation","sign_citation":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN/action/citation_signature","submit_replication":"https://pith.science/pith/AGD3YZH3EI3EBD6CEXTI6C5ECN/action/replication_record"}},"created_at":"2026-05-20T00:00:29.176749+00:00","updated_at":"2026-05-20T00:00:29.176749+00:00"}