{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SJ2WH5IBIOEHH5SX33PTYYKCD3","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":"c90a28844f1c738a4aa72bf1965c928fcccd9af5070776bc11469f3efe820d42","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T21:15:36Z","title_canon_sha256":"921d4428591f37fabb206b099c6f10e45da8b4a1180cbd49d52ed90bdcb03bda"},"schema_version":"1.0","source":{"id":"2404.05875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05875","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05875v1","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05875","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"SJ2WH5IBIOEH","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"SJ2WH5IBIOEHH5SX","created_at":"2026-07-05T08:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"SJ2WH5IB","created_at":"2026-07-05T08:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:2844cd403ecd22fbc6b92e8447ad2a6ef4b6ee1045fafa3d8641d0fb27a33bcb","target":"graph","created_at":"2026-07-05T08:06:00Z","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/2404.05875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor and time cost to collect or annotate data by humans, researchers start to explore the use of LLMs to generate instruction-aligned synthetic data. Recent works focus on generating diverse instructions and applying LLM to increase instruction complexity, often neglecting downstream use cases. It remains unclear how to tailor high-quality data to elicit better ","authors_text":"Chen-Yu Lee, Chun-Liang Li, Jin Miao, Long T. Le, Tomas Pfister, Vincent Perot, Zifeng Wang, Zizhao Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T21:15:36Z","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05875","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:e9b7d8baa05d0a7bebd06f0a456f95d07cf2da26c5a8db4c0b0141b058453d80","target":"record","created_at":"2026-07-05T08:06:00Z","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":"c90a28844f1c738a4aa72bf1965c928fcccd9af5070776bc11469f3efe820d42","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T21:15:36Z","title_canon_sha256":"921d4428591f37fabb206b099c6f10e45da8b4a1180cbd49d52ed90bdcb03bda"},"schema_version":"1.0","source":{"id":"2404.05875","kind":"arxiv","version":1}},"canonical_sha256":"927563f501438873f657dedf3c61421edcc2be6f054936ef7601c010134a3529","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"927563f501438873f657dedf3c61421edcc2be6f054936ef7601c010134a3529","first_computed_at":"2026-07-05T08:06:00.589777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:00.589777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EE/ZppiZiKXUTmLJMh5o/XiKtZnBZn4dgKoz4T2ep80nxhtWGxY4mthS2MWORaUVneYxmFmwUPN8OeU1IWxQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:00.590302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9b7d8baa05d0a7bebd06f0a456f95d07cf2da26c5a8db4c0b0141b058453d80","sha256:2844cd403ecd22fbc6b92e8447ad2a6ef4b6ee1045fafa3d8641d0fb27a33bcb"],"state_sha256":"d1e5d934b936c59901c758810a2d172d2c3051c93a7306580920504567b1d42c"}