{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S7CCKD6SIIINLNHKRQB3ZP4BFG","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":"588f8f10ddd1e47e4ea3308e08b1a6e56873497c7d0be3dace8dcbd284f736d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T07:19:56Z","title_canon_sha256":"ab6d4e5e931e01fc81f2a6f628169585e2c56d64b43f6e02eae24aac24ea7f35"},"schema_version":"1.0","source":{"id":"2507.02378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02378","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02378v1","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02378","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"pith_short_12","alias_value":"S7CCKD6SIIIN","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"pith_short_16","alias_value":"S7CCKD6SIIINLNHK","created_at":"2026-07-05T11:31:17Z"},{"alias_kind":"pith_short_8","alias_value":"S7CCKD6S","created_at":"2026-07-05T11:31:17Z"}],"graph_snapshots":[{"event_id":"sha256:1c88390a59ba5890cdc9c86cbf2e9f90d390bcb2d09e7294ff26d619e1e3b6f4","target":"graph","created_at":"2026-07-05T11:31:17Z","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/2507.02378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have significantly improved code generation and program comprehension, accelerating the evolution of software engineering. Current methods primarily enhance model performance by leveraging vast amounts of data, focusing on data quantity while often overlooking data quality, thereby reducing training efficiency. To address this, we introduce an approach that utilizes a parametric model for code data selection, aimed at improving both training efficiency and model performance. Our method optimizes the parametric model to ensure distribution con","authors_text":"Sheng-Jun Huang, Weijie Lyu, Xuan Xia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T07:19:56Z","title":"Efficient Code LLM Training via Distribution-Consistent and Diversity-Aware Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02378","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":"sha256:843719a435c1076f4e289f8ba27a849b9792052d9120792cfdbb54eb2eea9986","target":"record","created_at":"2026-07-05T11:31:17Z","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":"588f8f10ddd1e47e4ea3308e08b1a6e56873497c7d0be3dace8dcbd284f736d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T07:19:56Z","title_canon_sha256":"ab6d4e5e931e01fc81f2a6f628169585e2c56d64b43f6e02eae24aac24ea7f35"},"schema_version":"1.0","source":{"id":"2507.02378","kind":"arxiv","version":1}},"canonical_sha256":"97c4250fd24210d5b4ea8c03bcbf81299f71b6b22a725f3ab9f7e5c13095ba16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97c4250fd24210d5b4ea8c03bcbf81299f71b6b22a725f3ab9f7e5c13095ba16","first_computed_at":"2026-07-05T11:31:17.119266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:17.119266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"13gJkFN1oQQoe+atlNtSSnsKVb0DTBslJ3FFsYkh0jh5IF+LwAxXvfNpAfxBerb8Jz6GLCDlBkUWrJXpELiJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:17.119839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:843719a435c1076f4e289f8ba27a849b9792052d9120792cfdbb54eb2eea9986","sha256:1c88390a59ba5890cdc9c86cbf2e9f90d390bcb2d09e7294ff26d619e1e3b6f4"],"state_sha256":"0a02c56b0e9918f94c4d92f31947c57abba8d2012c7e5a66d68fff0a9123d702"}