{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PGG73MZSPWNZKTCGC6ZZB76JEP","short_pith_number":"pith:PGG73MZS","canonical_record":{"source":{"id":"2407.21077","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T20:42:59Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"542ac42fc35681f9eb5bb3dfb21faa8a85596cae212a81fb3be1b57fb4b94ced","abstract_canon_sha256":"b9192af0af3e82f4b5f40ed1c999561ed0cbcadcdaa9f1120cdff1e5a9bd2387"},"schema_version":"1.0"},"canonical_sha256":"798dfdb3327d9b954c4617b390ffc923d549192692d1bb42fe64f7e34ae4a369","source":{"kind":"arxiv","id":"2407.21077","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21077","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21077v3","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21077","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"pith_short_12","alias_value":"PGG73MZSPWNZ","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"pith_short_16","alias_value":"PGG73MZSPWNZKTCG","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"pith_short_8","alias_value":"PGG73MZS","created_at":"2026-07-05T11:07:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PGG73MZSPWNZKTCGC6ZZB76JEP","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21077","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T20:42:59Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"542ac42fc35681f9eb5bb3dfb21faa8a85596cae212a81fb3be1b57fb4b94ced","abstract_canon_sha256":"b9192af0af3e82f4b5f40ed1c999561ed0cbcadcdaa9f1120cdff1e5a9bd2387"},"schema_version":"1.0"},"canonical_sha256":"798dfdb3327d9b954c4617b390ffc923d549192692d1bb42fe64f7e34ae4a369","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:59.679340Z","signature_b64":"fo/xuVf2fEXeCBS27lST6HLHKJ2iqJB/gsrEMmCYhSFGTaLZbrUQFZ+6TqcRAYMXMGJxchj0Ks726/JUNxWlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"798dfdb3327d9b954c4617b390ffc923d549192692d1bb42fe64f7e34ae4a369","last_reissued_at":"2026-07-05T11:07:59.678820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:59.678820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21077","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ji4lYrkvphnPn1g/SujQl3HovFFJFk5CYA+pTqYluWbSWV1saM0STBHzHkVAODIn1Rlwl7/MzEreoH1tz4feBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:18:59.000872Z"},"content_sha256":"730fc36f03a605bc021f5bd0312de561bc5aa5910efa08795d785ffea37f49ad","schema_version":"1.0","event_id":"sha256:730fc36f03a605bc021f5bd0312de561bc5aa5910efa08795d785ffea37f49ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PGG73MZSPWNZKTCGC6ZZB76JEP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Aleksander Ficek, Boris Ginsburg, Jagadeesh Balam, Jocelyn Huang, Mehrzad Samadi, Sean Narenthiran, Somshubra Majumdar, Vahid Noroozi, Wasi Uddin Ahmad","submitted_at":"2024-07-29T20:42:59Z","abstract_excerpt":"Large Language Models (LLMs) require high quality instruction data for effective alignment, particularly in code generation tasks where expert curated datasets are expensive to produce. We present Genetic-Instruct, a scalable algorithm for synthesizing large-scale, high quality coding instructions using evolutionary principles. Starting from a small set of seed instructions, Genetic-Instruct generates diverse and challenging instruction-code pairs by leveraging an Instructor-LLM for generation, a Coder-LLM for code synthesis, and a Judge-LLM for automatic quality evaluation. Our proposed appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21077","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.21077/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCTQnIhJmIsh3OQ9F2DGY7jZ7uq6F0CHBAq3tXR/KIgK38GVuTgR0pld86cQyNiJBwqLzRx+4/p+stK0phaDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:18:59.001242Z"},"content_sha256":"355d35f7568c96e0939dea3a44f21a912c2770da8c23694ff13e8cf76a4e4d43","schema_version":"1.0","event_id":"sha256:355d35f7568c96e0939dea3a44f21a912c2770da8c23694ff13e8cf76a4e4d43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PGG73MZSPWNZKTCGC6ZZB76JEP/bundle.json","state_url":"https://pith.science/pith/PGG73MZSPWNZKTCGC6ZZB76JEP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PGG73MZSPWNZKTCGC6ZZB76JEP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T04:18:59Z","links":{"resolver":"https://pith.science/pith/PGG73MZSPWNZKTCGC6ZZB76JEP","bundle":"https://pith.science/pith/PGG73MZSPWNZKTCGC6ZZB76JEP/bundle.json","state":"https://pith.science/pith/PGG73MZSPWNZKTCGC6ZZB76JEP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PGG73MZSPWNZKTCGC6ZZB76JEP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PGG73MZSPWNZKTCGC6ZZB76JEP","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":"b9192af0af3e82f4b5f40ed1c999561ed0cbcadcdaa9f1120cdff1e5a9bd2387","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T20:42:59Z","title_canon_sha256":"542ac42fc35681f9eb5bb3dfb21faa8a85596cae212a81fb3be1b57fb4b94ced"},"schema_version":"1.0","source":{"id":"2407.21077","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21077","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21077v3","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21077","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"pith_short_12","alias_value":"PGG73MZSPWNZ","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"pith_short_16","alias_value":"PGG73MZSPWNZKTCG","created_at":"2026-07-05T11:07:59Z"},{"alias_kind":"pith_short_8","alias_value":"PGG73MZS","created_at":"2026-07-05T11:07:59Z"}],"graph_snapshots":[{"event_id":"sha256:355d35f7568c96e0939dea3a44f21a912c2770da8c23694ff13e8cf76a4e4d43","target":"graph","created_at":"2026-07-05T11:07:59Z","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/2407.21077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) require high quality instruction data for effective alignment, particularly in code generation tasks where expert curated datasets are expensive to produce. We present Genetic-Instruct, a scalable algorithm for synthesizing large-scale, high quality coding instructions using evolutionary principles. Starting from a small set of seed instructions, Genetic-Instruct generates diverse and challenging instruction-code pairs by leveraging an Instructor-LLM for generation, a Coder-LLM for code synthesis, and a Judge-LLM for automatic quality evaluation. Our proposed appro","authors_text":"Aleksander Ficek, Boris Ginsburg, Jagadeesh Balam, Jocelyn Huang, Mehrzad Samadi, Sean Narenthiran, Somshubra Majumdar, Vahid Noroozi, Wasi Uddin Ahmad","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T20:42:59Z","title":"Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21077","kind":"arxiv","version":3},"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":"sha256:730fc36f03a605bc021f5bd0312de561bc5aa5910efa08795d785ffea37f49ad","target":"record","created_at":"2026-07-05T11:07:59Z","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":"b9192af0af3e82f4b5f40ed1c999561ed0cbcadcdaa9f1120cdff1e5a9bd2387","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T20:42:59Z","title_canon_sha256":"542ac42fc35681f9eb5bb3dfb21faa8a85596cae212a81fb3be1b57fb4b94ced"},"schema_version":"1.0","source":{"id":"2407.21077","kind":"arxiv","version":3}},"canonical_sha256":"798dfdb3327d9b954c4617b390ffc923d549192692d1bb42fe64f7e34ae4a369","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"798dfdb3327d9b954c4617b390ffc923d549192692d1bb42fe64f7e34ae4a369","first_computed_at":"2026-07-05T11:07:59.678820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:59.678820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fo/xuVf2fEXeCBS27lST6HLHKJ2iqJB/gsrEMmCYhSFGTaLZbrUQFZ+6TqcRAYMXMGJxchj0Ks726/JUNxWlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:59.679340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21077","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:730fc36f03a605bc021f5bd0312de561bc5aa5910efa08795d785ffea37f49ad","sha256:355d35f7568c96e0939dea3a44f21a912c2770da8c23694ff13e8cf76a4e4d43"],"state_sha256":"56f6c8bddb2cd9abf71fe5e32ad0b73a8c3a4b83f40038f03d12fa32b0d8d052"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oOlhyiu0nG+XsZviLu4gcR/KoV0xpcyDV6BxAibFc5yv5cLsYB0bngRCh+BUn0k6KdteAgr387eLVDn2y8rDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:18:59.003497Z","bundle_sha256":"a084b0ce0f004b5aa4c2b5feff13cbaa4b16794acebd42556fc998f76d6b4330"}}