{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZM42HKS527LOTCPWLNHW46O57V","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":"91115ae5cada3fa7bee03f02ec3b35c374fc536cefa49f3f2514b672cef5e2a1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T19:15:27Z","title_canon_sha256":"42bff3d137bb1712bf3b526907a69a119819b9f0c7b8ca3415de39787aa0ff9d"},"schema_version":"1.0","source":{"id":"2606.10087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10087","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10087v1","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10087","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZM42HKS527LO","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZM42HKS527LOTCPW","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZM42HKS5","created_at":"2026-06-10T00:08:48Z"}],"graph_snapshots":[{"event_id":"sha256:147fe6f29c0942ea905a1128fa62668ddb78b88f99f689f1247fcbab995ab513","target":"graph","created_at":"2026-06-10T00:08:48Z","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/2606.10087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats. While synthetic data has proven transformative for language models, code remains largely unexplored beyond limited quality improvements. We present CodeAlchemy, a synthetic data generation framework that transforms publicly sourced code into semantically-rich training data through 5 strategies: CodeEnhance (quality-aware rewriting), CodeQA (template-based problems), CodeDev (developer tasks), CodeDialogue (multi-turn conversations), and CodeTrace (execution traces). We process 3 corpora acro","authors_text":"Aditya Prasad, Ankit Gupta, Rameswar Panda","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T19:15:27Z","title":"CodeAlchemy: Synthetic Code Rewriting at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10087","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":"sha256:5c2522f8aaa5dfebcc593154131ada9008ebd3cd0f71792312d8724fc7f749f3","target":"record","created_at":"2026-06-10T00:08:48Z","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":"91115ae5cada3fa7bee03f02ec3b35c374fc536cefa49f3f2514b672cef5e2a1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T19:15:27Z","title_canon_sha256":"42bff3d137bb1712bf3b526907a69a119819b9f0c7b8ca3415de39787aa0ff9d"},"schema_version":"1.0","source":{"id":"2606.10087","kind":"arxiv","version":1}},"canonical_sha256":"cb39a3aa5dd7d6e989f65b4f6e79ddfd447b73f8ace3f0975bcf44711ab87f95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb39a3aa5dd7d6e989f65b4f6e79ddfd447b73f8ace3f0975bcf44711ab87f95","first_computed_at":"2026-06-10T00:08:48.589164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:48.589164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9RKZSEQfuyMXTfVq+RjlHMXtuGlv6F/ZYokX2LTPxwrwWqOLi7MIzWO5zoRAVke7IcZDkIq0t4u8sR+DrO/eCA==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:48.590028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c2522f8aaa5dfebcc593154131ada9008ebd3cd0f71792312d8724fc7f749f3","sha256:147fe6f29c0942ea905a1128fa62668ddb78b88f99f689f1247fcbab995ab513"],"state_sha256":"57fa3393e662f83dafb84b03218241ad952c6664871591213e30d5a56ff2ce2c"}