{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7E45J63RBTWECNKSJB5O2K2YXR","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":"6df5a48ffe49477c5aab60c25359310de7943b20b7a3b1fa722d646842347ced","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:13Z","title_canon_sha256":"451fc7f8c38f533b2ae4a4ef47d0e7d9d178f502e5c9524e6bee9ce8f537ce3b"},"schema_version":"1.0","source":{"id":"2410.24198","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24198","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24198v2","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24198","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"7E45J63RBTWE","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"7E45J63RBTWECNKS","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"7E45J63R","created_at":"2026-07-05T09:29:36Z"}],"graph_snapshots":[{"event_id":"sha256:277a8e5b4e85c405f8bc349d762f79ae730690d1270fe7f6739a0545bbf86727","target":"graph","created_at":"2026-07-05T09:29:36Z","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/2410.24198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for self-aligning code LLMs without extensive human annotations or distillation. SelfCodeAlign employs the same base model for inference throughout the data generation process. It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks. It then samples multiple responses per task, pairs each with test cases, and validates the","authors_text":"Arjun Guha, Federico Cassano, Harm de Vries, Jiawei Liu, Leandro Von Werra, Lingming Zhang, Naman Jain, Yifeng Ding, Yuxiang Wei, Zachary Mueller","cross_cats":["cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:13Z","title":"SelfCodeAlign: Self-Alignment for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24198","kind":"arxiv","version":2},"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":"sha256:05cca7ba14711160a0743dfdb4ea33f9491248437eda9a9e5bbbe74c2814f87b","target":"record","created_at":"2026-07-05T09:29:36Z","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":"6df5a48ffe49477c5aab60c25359310de7943b20b7a3b1fa722d646842347ced","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:13Z","title_canon_sha256":"451fc7f8c38f533b2ae4a4ef47d0e7d9d178f502e5c9524e6bee9ce8f537ce3b"},"schema_version":"1.0","source":{"id":"2410.24198","kind":"arxiv","version":2}},"canonical_sha256":"f939d4fb710cec413552487aed2b58bc73b8f5112332b8f9737a3c19fef5ca62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f939d4fb710cec413552487aed2b58bc73b8f5112332b8f9737a3c19fef5ca62","first_computed_at":"2026-07-05T09:29:36.166226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:36.166226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0lRiZADLFJPpuNCGnXERxJY90YNWF+T8QdJw4YrhujGd+iPig+QNphYfj1QloblCBt3XDb79plFKM4h1FDsrDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:36.166764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.24198","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05cca7ba14711160a0743dfdb4ea33f9491248437eda9a9e5bbbe74c2814f87b","sha256:277a8e5b4e85c405f8bc349d762f79ae730690d1270fe7f6739a0545bbf86727"],"state_sha256":"5a363f8759613289c9b5d970312d1378f73d9209213a8256d31fea1c36a1dfec"}