{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L7BINUWKH2D5RQE5SMTZI4E2C3","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"39def3afc8142b226da28051edce956007e24e9435ca7e3472dc07775a16b76e","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T02:23:22Z","title_canon_sha256":"f904214cf8c509d8f0e7e02a6257e98a15a5470094990dbd39c4222adaff2233"},"schema_version":"1.0","source":{"id":"2607.18642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18642","created_at":"2026-07-22T00:22:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18642v1","created_at":"2026-07-22T00:22:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18642","created_at":"2026-07-22T00:22:58Z"},{"alias_kind":"pith_short_12","alias_value":"L7BINUWKH2D5","created_at":"2026-07-22T00:22:58Z"},{"alias_kind":"pith_short_16","alias_value":"L7BINUWKH2D5RQE5","created_at":"2026-07-22T00:22:58Z"},{"alias_kind":"pith_short_8","alias_value":"L7BINUWK","created_at":"2026-07-22T00:22:58Z"}],"graph_snapshots":[{"event_id":"sha256:323905a0003a18d36aeb12f2671a45ae4b89864cf9cde1c6d4d3a81c1cc9e339","target":"graph","created_at":"2026-07-22T00:22:58Z","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/2607.18642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Yuxiang Ji","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T02:23:22Z","title":"Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18642","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":"sha256:03618acf1f3264b11dd46ac7876b57ce6f5ddd3fd7f40d758bcc9ce4a461f5ef","target":"record","created_at":"2026-07-22T00:22:58Z","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":"39def3afc8142b226da28051edce956007e24e9435ca7e3472dc07775a16b76e","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T02:23:22Z","title_canon_sha256":"f904214cf8c509d8f0e7e02a6257e98a15a5470094990dbd39c4222adaff2233"},"schema_version":"1.0","source":{"id":"2607.18642","kind":"arxiv","version":1}},"canonical_sha256":"5fc286d2ca3e87d8c09d932794709a16c59bb51d315f793faeb1e820f4c646be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fc286d2ca3e87d8c09d932794709a16c59bb51d315f793faeb1e820f4c646be","first_computed_at":"2026-07-22T00:22:58.184279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:58.184279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FiODGE7yuU305hoMCsbHUqfNhklIaxqn1KxOM2qEv5opd4fqmLAHfgCySZAEnJZLhuRvY1cmhCofiZMbe7TEBg==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:58.185150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03618acf1f3264b11dd46ac7876b57ce6f5ddd3fd7f40d758bcc9ce4a461f5ef","sha256:323905a0003a18d36aeb12f2671a45ae4b89864cf9cde1c6d4d3a81c1cc9e339","sha256:2b98c71562a02bac8c204d9477e72fe6dca951a54d00efef50e0042d23e8bdcb"],"state_sha256":"2a87be956e9027aceb8e87ac4d9c7b20a7954f9271c4310f134cc7446feac49e"}