{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7BINUWKH2D5RQE5SMTZI4E2C3","short_pith_number":"pith:L7BINUWK","schema_version":"1.0","canonical_sha256":"5fc286d2ca3e87d8c09d932794709a16c59bb51d315f793faeb1e820f4c646be","source":{"kind":"arxiv","id":"2607.18642","version":1},"attestation_state":"computed","paper":{"title":"Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Yuxiang Ji","submitted_at":"2026-07-21T02:23:22Z","abstract_excerpt":"Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface \"messiness,\" and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set. We present Spaghetti Architect, a tool that mints code datasets with the control such corpora lack. An anti-optimization transpiler maps a clean, language-agnostic JSON intermediate representation to deliberately redundant, fully-flattened programs in five languages (Python, JavaScript, Go, Java, C++); every program is compiled, run, and"},"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":"2607.18642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T02:23:22Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"f904214cf8c509d8f0e7e02a6257e98a15a5470094990dbd39c4222adaff2233","abstract_canon_sha256":"39def3afc8142b226da28051edce956007e24e9435ca7e3472dc07775a16b76e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:58.185150Z","signature_b64":"FiODGE7yuU305hoMCsbHUqfNhklIaxqn1KxOM2qEv5opd4fqmLAHfgCySZAEnJZLhuRvY1cmhCofiZMbe7TEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fc286d2ca3e87d8c09d932794709a16c59bb51d315f793faeb1e820f4c646be","last_reissued_at":"2026-07-22T00:22:58.184279Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:58.184279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Yuxiang Ji","submitted_at":"2026-07-21T02:23:22Z","abstract_excerpt":"Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface \"messiness,\" and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set. We present Spaghetti Architect, a tool that mints code datasets with the control such corpora lack. An anti-optimization transpiler maps a clean, language-agnostic JSON intermediate representation to deliberately redundant, fully-flattened programs in five languages (Python, JavaScript, Go, Java, C++); every program is compiled, run, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18642","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/2607.18642/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":"2607.18642","created_at":"2026-07-22T00:22:58.184741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18642v1","created_at":"2026-07-22T00:22:58.184741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18642","created_at":"2026-07-22T00:22:58.184741+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7BINUWKH2D5","created_at":"2026-07-22T00:22:58.184741+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7BINUWKH2D5RQE5","created_at":"2026-07-22T00:22:58.184741+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7BINUWK","created_at":"2026-07-22T00:22:58.184741+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/L7BINUWKH2D5RQE5SMTZI4E2C3","json":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3.json","graph_json":"https://pith.science/api/pith-number/L7BINUWKH2D5RQE5SMTZI4E2C3/graph.json","events_json":"https://pith.science/api/pith-number/L7BINUWKH2D5RQE5SMTZI4E2C3/events.json","paper":"https://pith.science/paper/L7BINUWK"},"agent_actions":{"view_html":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3","download_json":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3.json","view_paper":"https://pith.science/paper/L7BINUWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18642&json=true","fetch_graph":"https://pith.science/api/pith-number/L7BINUWKH2D5RQE5SMTZI4E2C3/graph.json","fetch_events":"https://pith.science/api/pith-number/L7BINUWKH2D5RQE5SMTZI4E2C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/action/storage_attestation","attest_author":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/action/author_attestation","sign_citation":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/action/citation_signature","submit_replication":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/action/replication_record"}},"created_at":"2026-07-22T00:22:58.184741+00:00","updated_at":"2026-07-22T00:22:58.184741+00:00"}