{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:COLZ2L7Q77PNIAA2TUIW7J77VX","short_pith_number":"pith:COLZ2L7Q","canonical_record":{"source":{"id":"2406.17633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T15:20:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3362d356fb9f49250e88fa5ec2c6b5d42b4a6e5bc88ad38f1446cad82412e2f1","abstract_canon_sha256":"aa21f715ccf769d12fdfaff1d407629ff3fd92b5030ffac32005aae1292bc2a8"},"schema_version":"1.0"},"canonical_sha256":"13979d2ff0ffded4001a9d116fa7ffade05db12f561a1f1e22123491301afca9","source":{"kind":"arxiv","id":"2406.17633","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:COLZ2L7Q77PNIAA2TUIW7J77VX","target":"record","payload":{"canonical_record":{"source":{"id":"2406.17633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T15:20:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3362d356fb9f49250e88fa5ec2c6b5d42b4a6e5bc88ad38f1446cad82412e2f1","abstract_canon_sha256":"aa21f715ccf769d12fdfaff1d407629ff3fd92b5030ffac32005aae1292bc2a8"},"schema_version":"1.0"},"canonical_sha256":"13979d2ff0ffded4001a9d116fa7ffade05db12f561a1f1e22123491301afca9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:38.072513Z","signature_b64":"5F7KG+VDObVGOe7oZK4SoOqZAHiTJtEjB5pPn2VpFl0/dht0yLcPSwG0NN+oZpIGUNAvAwieIotamqyYam2oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13979d2ff0ffded4001a9d116fa7ffade05db12f561a1f1e22123491301afca9","last_reissued_at":"2026-07-05T08:36:38.072022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:38.072022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.17633","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ImI/4vti8xVirWOfs7yTZNYnQMeM/gpwYhIXLaaFJfPXtXcHvDE/KtkvyZJ1WtZQDv2jRVBKqlu2ttlBBHeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:01:46.913526Z"},"content_sha256":"a88213578bf7ec1fff13235269796f8f565401bf81e0b4b9a798126552c81cb9","schema_version":"1.0","event_id":"sha256:a88213578bf7ec1fff13235269796f8f565401bf81e0b4b9a798126552c81cb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:COLZ2L7Q77PNIAA2TUIW7J77VX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Nicholas Pangakis, Samuel Wolken","submitted_at":"2024-06-25T15:20:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17633","kind":"arxiv","version":1},"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/2406.17633/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":"2026-07-05T08:36:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZMt0JPvulxDv/Hy7jYHu7JRFg07i2QZqsOthNwP3mAoP6TOlQ/+4zK7JgvJFuxi3kt+4QLMsxfw4EFSDzM5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:01:46.914109Z"},"content_sha256":"a603a02935cfcf80f77f017aff601478d5685c0475ba28b7ff4fb8d01108d21e","schema_version":"1.0","event_id":"sha256:a603a02935cfcf80f77f017aff601478d5685c0475ba28b7ff4fb8d01108d21e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/COLZ2L7Q77PNIAA2TUIW7J77VX/bundle.json","state_url":"https://pith.science/pith/COLZ2L7Q77PNIAA2TUIW7J77VX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/COLZ2L7Q77PNIAA2TUIW7J77VX/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":"2026-08-06T13:01:46Z","links":{"resolver":"https://pith.science/pith/COLZ2L7Q77PNIAA2TUIW7J77VX","bundle":"https://pith.science/pith/COLZ2L7Q77PNIAA2TUIW7J77VX/bundle.json","state":"https://pith.science/pith/COLZ2L7Q77PNIAA2TUIW7J77VX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/COLZ2L7Q77PNIAA2TUIW7J77VX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A0ybKroY4kgral/jV5OQ3FpmZNrZJTVD4CL00AtMbo32PbAmz0NmLe69G8X4w7QCg0G0xT12O6SSq7DuBCJOCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:01:46.919318Z","bundle_sha256":"d28eb769115ea853cbc6299c6b850d66f860df4a7c8b3934d7027061416b00c8"}}