{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:COLZ2L7Q77PNIAA2TUIW7J77VX","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":"aa21f715ccf769d12fdfaff1d407629ff3fd92b5030ffac32005aae1292bc2a8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T15:20:25Z","title_canon_sha256":"3362d356fb9f49250e88fa5ec2c6b5d42b4a6e5bc88ad38f1446cad82412e2f1"},"schema_version":"1.0","source":{"id":"2406.17633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17633","created_at":"2026-07-05T08:36:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17633v1","created_at":"2026-07-05T08:36:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17633","created_at":"2026-07-05T08:36:38Z"},{"alias_kind":"pith_short_12","alias_value":"COLZ2L7Q77PN","created_at":"2026-07-05T08:36:38Z"},{"alias_kind":"pith_short_16","alias_value":"COLZ2L7Q77PNIAA2","created_at":"2026-07-05T08:36:38Z"},{"alias_kind":"pith_short_8","alias_value":"COLZ2L7Q","created_at":"2026-07-05T08:36:38Z"}],"graph_snapshots":[{"event_id":"sha256:a603a02935cfcf80f77f017aff601478d5685c0475ba28b7ff4fb8d01108d21e","target":"graph","created_at":"2026-07-05T08:36:38Z","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/2406.17633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computational social science (CSS) practitioners often rely on human-labeled data to fine-tune supervised text classifiers. We assess the potential for researchers to augment or replace human-generated training data with surrogate training labels from generative large language models (LLMs). We introduce a recommended workflow and test this LLM application by replicating 14 classification tasks and measuring performance. We employ a novel corpus of English-language text classification data sets from recent CSS articles in high-impact journals. Because these data sets are stored in password-pro","authors_text":"Nicholas Pangakis, Samuel Wolken","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T15:20:25Z","title":"Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17633","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:a88213578bf7ec1fff13235269796f8f565401bf81e0b4b9a798126552c81cb9","target":"record","created_at":"2026-07-05T08:36:38Z","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":"aa21f715ccf769d12fdfaff1d407629ff3fd92b5030ffac32005aae1292bc2a8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T15:20:25Z","title_canon_sha256":"3362d356fb9f49250e88fa5ec2c6b5d42b4a6e5bc88ad38f1446cad82412e2f1"},"schema_version":"1.0","source":{"id":"2406.17633","kind":"arxiv","version":1}},"canonical_sha256":"13979d2ff0ffded4001a9d116fa7ffade05db12f561a1f1e22123491301afca9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13979d2ff0ffded4001a9d116fa7ffade05db12f561a1f1e22123491301afca9","first_computed_at":"2026-07-05T08:36:38.072022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:38.072022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5F7KG+VDObVGOe7oZK4SoOqZAHiTJtEjB5pPn2VpFl0/dht0yLcPSwG0NN+oZpIGUNAvAwieIotamqyYam2oDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:38.072513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a88213578bf7ec1fff13235269796f8f565401bf81e0b4b9a798126552c81cb9","sha256:a603a02935cfcf80f77f017aff601478d5685c0475ba28b7ff4fb8d01108d21e"],"state_sha256":"818fc3ba5d7568e06fa59be8a483b714cafde154d12e5349dfd25d2e9d016cf2"}