{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MF76GHFSMZ26FFW6FQEEEFMDP7","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":"e2048e1a358ec9f03f7b3780f7f5ae8fb69868ef535478dd81b58ee164184558","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-09T15:38:44Z","title_canon_sha256":"6a318263668384c5c94fa652bef04f2be45aff107f0d58f69ccc1b320cd0dd16"},"schema_version":"1.0","source":{"id":"2509.07858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07858","created_at":"2026-07-05T12:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07858v1","created_at":"2026-07-05T12:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07858","created_at":"2026-07-05T12:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"MF76GHFSMZ26","created_at":"2026-07-05T12:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"MF76GHFSMZ26FFW6","created_at":"2026-07-05T12:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"MF76GHFS","created_at":"2026-07-05T12:07:41Z"}],"graph_snapshots":[{"event_id":"sha256:0bd2931272d8a4142198eeef02ed95823280d1e342d19c0d1a55dd21e613fd7b","target":"graph","created_at":"2026-07-05T12:07:41Z","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/2509.07858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing code large language models (LLMs) often rely on large-scale instruction data distilled from proprietary LLMs for fine-tuning, which typically incurs high costs. In this paper, we explore the potential of small-scale open-source LLMs (e.g., 7B) as synthesizers for high-quality code instruction data construction. We first observe that the data synthesis capability of small-scale LLMs can be enhanced by training on a few superior data synthesis samples from proprietary LLMs. Building on this, we propose a novel iterative self-distillation approach to bootstrap small-scale LLMs, transform","authors_text":"Changzhi Zhou, Haomin Fu, Linmei Hu, Luhao Zhang, Mengdi Zhang, Xiancai Chen, Xinyu Zhang, Yang Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-09T15:38:44Z","title":"SCoder: Iterative Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07858","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":"sha256:1ffa4e308ae7ef5d8da9f6edeb5661a27ed1bb34d89654e40ce5697908a95969","target":"record","created_at":"2026-07-05T12:07:41Z","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":"e2048e1a358ec9f03f7b3780f7f5ae8fb69868ef535478dd81b58ee164184558","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-09T15:38:44Z","title_canon_sha256":"6a318263668384c5c94fa652bef04f2be45aff107f0d58f69ccc1b320cd0dd16"},"schema_version":"1.0","source":{"id":"2509.07858","kind":"arxiv","version":1}},"canonical_sha256":"617fe31cb26675e296de2c084215837ff236442d99e14949e9b901fc88b52e3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"617fe31cb26675e296de2c084215837ff236442d99e14949e9b901fc88b52e3c","first_computed_at":"2026-07-05T12:07:41.215612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:41.215612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"evT/tjqYGxXWLstiPsaeRHTaW61FhdXQ4uWxrRYNGMZp4ohMa/OmvwVMZ3/lhuBf8W8JNhCh3RL41YOnZFPZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:41.216137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.07858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ffa4e308ae7ef5d8da9f6edeb5661a27ed1bb34d89654e40ce5697908a95969","sha256:0bd2931272d8a4142198eeef02ed95823280d1e342d19c0d1a55dd21e613fd7b"],"state_sha256":"0c1bc4dbf0ea6f23275f4a3065003ddcc7a33f59862fb6e25f136e399d283942"}