{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SI45DNWB3ZSRZMPXO64VIZATNO","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":"4f38c01f0b170062895243d708a47784afd9d44cd537a1142e60c80683f13901","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T10:31:24Z","title_canon_sha256":"c169074ebb67f2cb1bf50bb9c49bc60be35f83367719b8ecf8863ad5800c6bf7"},"schema_version":"1.0","source":{"id":"2508.05242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05242","created_at":"2026-07-05T11:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05242v1","created_at":"2026-07-05T11:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05242","created_at":"2026-07-05T11:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"SI45DNWB3ZSR","created_at":"2026-07-05T11:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"SI45DNWB3ZSRZMPX","created_at":"2026-07-05T11:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"SI45DNWB","created_at":"2026-07-05T11:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:d16f096d54ff77bc66596fd51a90002b99fd91fc3dbfa426a48ae8a4b4b63d84","target":"graph","created_at":"2026-07-05T11:50:09Z","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/2508.05242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines. Existing models are typically post-trained using reinforcement learning (RL) from general-purpose LLMs using \"human instruction-final answer\" pairs, where the instructions are usually from manual annotations. However, collecting high-quality coding instructions is both labor-intensive and difficult to scale. On the other hand, code snippets are abundantly available from various sources. This imbalance presents a major bottleneck in instruction-based post-training. We propose","authors_text":"Kai Zhao, Quanjiang Guo, Rui She, Shangshu Yu, Sijie Wang, Siqi Li, Wee Peng Tay, Xiang Li, Xin Li, Yawei Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T10:31:24Z","title":"CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05242","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:a55f8d36ec874e7a4acfa7783a95fa539596bbb552a888ab18012c9b42f17c60","target":"record","created_at":"2026-07-05T11:50:09Z","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":"4f38c01f0b170062895243d708a47784afd9d44cd537a1142e60c80683f13901","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T10:31:24Z","title_canon_sha256":"c169074ebb67f2cb1bf50bb9c49bc60be35f83367719b8ecf8863ad5800c6bf7"},"schema_version":"1.0","source":{"id":"2508.05242","kind":"arxiv","version":1}},"canonical_sha256":"9239d1b6c1de651cb1f777b95464136ba0ea5804fce6a55beb95dc5cbf8c76b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9239d1b6c1de651cb1f777b95464136ba0ea5804fce6a55beb95dc5cbf8c76b2","first_computed_at":"2026-07-05T11:50:09.674670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:09.674670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4gjjVWvK+sEvp4rdWwJY2fJSoKoCNs5ZMkwnnbk/C0ED08v9/8LFg8KYf6Ct3TMzSfrqX6oQo99uBgfCMYRRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:09.675256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a55f8d36ec874e7a4acfa7783a95fa539596bbb552a888ab18012c9b42f17c60","sha256:d16f096d54ff77bc66596fd51a90002b99fd91fc3dbfa426a48ae8a4b4b63d84"],"state_sha256":"cf28e65126da9e91fa22620768c489c4b56fb473dfe5216f16d0402b1a4279ad"}