{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CHCPCTCKALBDOR532DTPRS3TYW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2b34abb91e61247f0ade0168a34c80797aa54b6207f2b42fab7756afd0167f45","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T01:19:30Z","title_canon_sha256":"1ced3217f9c55243c9a48710310d072834294a329b73545003a1d4825acfac2e"},"schema_version":"1.0","source":{"id":"2312.02418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02418","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02418v1","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02418","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"CHCPCTCKALBD","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"CHCPCTCKALBDOR53","created_at":"2026-07-05T07:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"CHCPCTCK","created_at":"2026-07-05T07:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:5c3f97b10f0103af776b51c61122df4489080dc1f76614554d1aec39455f0c8c","target":"graph","created_at":"2026-07-05T07:20:17Z","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/2312.02418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code datasets, often collected from diverse and uncontrolled sources such as GitHub, potentially suffer from quality issues, thereby affecting the performance and training efficiency of Large Language Models (LLMs) optimized for code generation. Previous studies demonstrated the benefit of using embedding spaces for data pruning, but they mainly focused on duplicate removal or increasing variety, and in other modalities, such as images. Our work focuses on using embeddings to identify and remove \"low-quality\" code data. First, we explore features of \"low-quality\" code in embedding space, throu","authors_text":"Aaditya K. Singh, Anas Mahmoud, Ari S. Morcos, Baptiste Rozi\\`ere, Carole-Jean Wu, Fabian Gloeckle, Kushal Tirumala, Mostafa Elhoushi, Newsha Ardalani, Yu Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T01:19:30Z","title":"Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02418","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":"sha256:492b2ead2f44cde9316a1fb32f19117926aeb6d3894795de5a53954b49c4af1e","target":"record","created_at":"2026-07-05T07:20:17Z","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":"2b34abb91e61247f0ade0168a34c80797aa54b6207f2b42fab7756afd0167f45","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T01:19:30Z","title_canon_sha256":"1ced3217f9c55243c9a48710310d072834294a329b73545003a1d4825acfac2e"},"schema_version":"1.0","source":{"id":"2312.02418","kind":"arxiv","version":1}},"canonical_sha256":"11c4f14c4a02c23747bbd0e6f8cb73c5b7f34069359e833580de8ec84266a9d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11c4f14c4a02c23747bbd0e6f8cb73c5b7f34069359e833580de8ec84266a9d6","first_computed_at":"2026-07-05T07:20:17.811495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:17.811495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F0BRhCoFNvMygnqGDkES9zZURuEKLa84hOxyM6v306friqn11GtTpJTiPjX2Wq+/8Ck6J4DwZ28nvw46XwRDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:17.811976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:492b2ead2f44cde9316a1fb32f19117926aeb6d3894795de5a53954b49c4af1e","sha256:5c3f97b10f0103af776b51c61122df4489080dc1f76614554d1aec39455f0c8c"],"state_sha256":"16edb8ee15782d897694b606a8ab6b8485affa3ca0b0fc535aee6b48b801c0f3"}