{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:L7BINUWKH2D5RQE5SMTZI4E2C3","short_pith_number":"pith:L7BINUWK","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"},"canonical_sha256":"5fc286d2ca3e87d8c09d932794709a16c59bb51d315f793faeb1e820f4c646be","source":{"kind":"arxiv","id":"2607.18642","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:L7BINUWKH2D5RQE5SMTZI4E2C3","target":"record","payload":{"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"},"canonical_sha256":"5fc286d2ca3e87d8c09d932794709a16c59bb51d315f793faeb1e820f4c646be","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"},"source_kind":"arxiv","source_id":"2607.18642","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T00:22:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buFBGsIystbEDDxCpFuGUzh9td7LtWojifglBbXPCs45JY26BcylJfNLJhnc3mlRLThRxS/G9nZa5vlkLTUKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:56:36.303611Z"},"content_sha256":"03618acf1f3264b11dd46ac7876b57ce6f5ddd3fd7f40d758bcc9ce4a461f5ef","schema_version":"1.0","event_id":"sha256:03618acf1f3264b11dd46ac7876b57ce6f5ddd3fd7f40d758bcc9ce4a461f5ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:L7BINUWKH2D5RQE5SMTZI4E2C3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T00:22:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gWucszkgLjyyvSzwql4tDDT+EP2Q907Efk/QO/r/uM4cvZJrIavoYkNmDZ7/FB7GVRsmB8JyV4ANSIlhM+sPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:56:36.304520Z"},"content_sha256":"323905a0003a18d36aeb12f2671a45ae4b89864cf9cde1c6d4d3a81c1cc9e339","schema_version":"1.0","event_id":"sha256:323905a0003a18d36aeb12f2671a45ae4b89864cf9cde1c6d4d3a81c1cc9e339"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:L7BINUWKH2D5RQE5SMTZI4E2C3","target":"integrity","payload":{"note":"Identifier '10.5281/zenodo.21033174always' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"A persistent Zenodo DOI is assigned to the tagged release; the concept DOIhttps://doi.org/10.5281/zenodo.21033174always resolves to the latest version. Maintenance.The dataset is maintained by the author via the GitHub repository (issues / ","arxiv_id":"2607.18642","detector":"doi_compliance","evidence":{"doi":"10.5281/zenodo.21033174always","arxiv_id":null,"ref_index":6,"raw_excerpt":"A persistent Zenodo DOI is assigned to the tagged release; the concept DOIhttps://doi.org/10.5281/zenodo.21033174always resolves to the latest version. Maintenance.The dataset is maintained by the author via the GitHub repository (issues / pull requests); contact is the corresponding author inCITATION.cff. It is versioned (dataset_versionin the manifest; current2.0) and is fully regenerable withpy","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":6,"audited_at":"2026-08-01T14:58:43.187466Z","event_type":"pith.integrity.v1","detected_doi":"10.5281/zenodo.21033174always","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"f0eac5e4da231a381e66dd1dc84979e634f770586df01cf40a20495d8a7ae962","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":16006,"payload_sha256":"8a4e9a91b2ae72fe9f752bb38e54c4517f3bb68a6c93a2d104edc7821ccd73f6","signature_b64":"5C73BdnD4h87op7l5WYJNGrX92XhGPtsTGVjhYMVwaWCguTd7qV3b7rAK1sXCD9tsR+mC6HpoPrQe9qdX5FqAg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T15:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBEyeXMCRydLZuPhFabe8oGGOtBCVH3gpcosnCM37yHvpFVTe/VBbao4p1IUUiWPjpOL9d64ZLyges57kuUlAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:56:36.307333Z"},"content_sha256":"2b98c71562a02bac8c204d9477e72fe6dca951a54d00efef50e0042d23e8bdcb","schema_version":"1.0","event_id":"sha256:2b98c71562a02bac8c204d9477e72fe6dca951a54d00efef50e0042d23e8bdcb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/bundle.json","state_url":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T14:56:36Z","links":{"resolver":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3","bundle":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/bundle.json","state":"https://pith.science/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7BINUWKH2D5RQE5SMTZI4E2C3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IyB1flgi+K3qI5J2W2A7hdrUHQ4kHkOA3hPKiP9ZTUshQWvgvk/51UXbR/U9CmIMgaam1wd1afUvRe3TPYxDBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:56:36.311260Z","bundle_sha256":"e04a41e1b21d763627d1fec6ee0af063f76322e5203fc55d01f8f5f580b8165e"}}