{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6RZG2KN2AQFJ4HQRLCBFVXVUZJ","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":"8f97690a19ba6998cc6efc054ee019ec016df9dcd82dbdb5744738a89906fcc0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:41:18Z","title_canon_sha256":"2d2a836881a11fc8fab7b710bbfd19329b589244f9f5cbb83c676defe418a2b1"},"schema_version":"1.0","source":{"id":"2309.05447","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05447","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05447v2","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05447","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"6RZG2KN2AQFJ","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"pith_short_16","alias_value":"6RZG2KN2AQFJ4HQR","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"pith_short_8","alias_value":"6RZG2KN2","created_at":"2026-07-05T08:23:11Z"}],"graph_snapshots":[{"event_id":"sha256:b92ddc1b4d0aab4af56a5fe5ebf2237d3aa449d532f3936e504a128c5f7a6e94","target":"graph","created_at":"2026-07-05T08:23:11Z","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/2309.05447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The improvement of LLMs' instruction-following capabilities relies heavily on the availability of high-quality instruction-response pairs. Unfortunately, the current methods used to collect the pairs suffer from either unaffordable labor costs or severe hallucinations in the self-generation of LLM. To tackle these challenges, this paper proposes a scalable solution. It involves training LLMs to generate instruction-response pairs based on human-written documents, rather than relying solely on self-generation without context. Our proposed method not only exploits the advantages of human-written","authors_text":"Guilin Qi, Haiyun Jiang, Shuming Shi, Xinting Huang, Yongrui Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:41:18Z","title":"DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05447","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":"sha256:3ba3febe0d747eacee4035efdb522cae41fb33bc71617a4456271642a2cf74a9","target":"record","created_at":"2026-07-05T08:23:11Z","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":"8f97690a19ba6998cc6efc054ee019ec016df9dcd82dbdb5744738a89906fcc0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:41:18Z","title_canon_sha256":"2d2a836881a11fc8fab7b710bbfd19329b589244f9f5cbb83c676defe418a2b1"},"schema_version":"1.0","source":{"id":"2309.05447","kind":"arxiv","version":2}},"canonical_sha256":"f4726d29ba040a9e1e1158825adeb4ca5d39a6a6a604fc15a4713b55cf560a14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4726d29ba040a9e1e1158825adeb4ca5d39a6a6a604fc15a4713b55cf560a14","first_computed_at":"2026-07-05T08:23:11.928047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:11.928047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gkIkLY6G760aCf9uwtS9bH+Xp+s/DC2DicLfPr9OqNHQ9RbFwspTL3tIT62+LuorV/OQ9p9rh+VciNb1M3VmAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:11.928538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05447","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ba3febe0d747eacee4035efdb522cae41fb33bc71617a4456271642a2cf74a9","sha256:b92ddc1b4d0aab4af56a5fe5ebf2237d3aa449d532f3936e504a128c5f7a6e94"],"state_sha256":"7ecdc1cec80248c2dc5dcd33324e14cccc70e2c64c81cffd64730e306c4593e1"}