{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WI6OAYJFOARK65U3Z7CTN62TW7","short_pith_number":"pith:WI6OAYJF","canonical_record":{"source":{"id":"2306.00176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T20:50:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0541c048c2a673be3da6649dc9ec8fe62c85bc0690f3908f7c207b0aa3692064","abstract_canon_sha256":"e1657b1a4eef428fdd2bc766295476545766184d6266a8de982b8ce3873a6551"},"schema_version":"1.0"},"canonical_sha256":"b23ce061257022af769bcfc536fb53b7dba3b0e383e137f8829b0e5f59444132","source":{"kind":"arxiv","id":"2306.00176","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00176","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00176v1","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00176","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"pith_short_12","alias_value":"WI6OAYJFOARK","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"pith_short_16","alias_value":"WI6OAYJFOARK65U3","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"pith_short_8","alias_value":"WI6OAYJF","created_at":"2026-07-05T06:16:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WI6OAYJFOARK65U3Z7CTN62TW7","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T20:50:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0541c048c2a673be3da6649dc9ec8fe62c85bc0690f3908f7c207b0aa3692064","abstract_canon_sha256":"e1657b1a4eef428fdd2bc766295476545766184d6266a8de982b8ce3873a6551"},"schema_version":"1.0"},"canonical_sha256":"b23ce061257022af769bcfc536fb53b7dba3b0e383e137f8829b0e5f59444132","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:23.031662Z","signature_b64":"HgDDq4lG7/dPRv2juLKdS9ClhhPUlFYNdxuAnVHFR2RTjsZXUow+lTpJNWqJ5748etJd8DITxNC5cwg8dK+TBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b23ce061257022af769bcfc536fb53b7dba3b0e383e137f8829b0e5f59444132","last_reissued_at":"2026-07-05T06:16:23.031235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:23.031235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00176","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":"2026-07-05T06:16:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8W9VIlGfmwdimuTUd0ThYSmN5/YSrZPKVcC7hm7P/qk5KSFkrGLJ+f10IeJ1hEDxhRzFTvHHiIOIbBwl2lHyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:26:56.782776Z"},"content_sha256":"ead372b1dc352e758642268c1f063df2cf73a9c68e038778ebb9bbf9d1cf91fb","schema_version":"1.0","event_id":"sha256:ead372b1dc352e758642268c1f063df2cf73a9c68e038778ebb9bbf9d1cf91fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WI6OAYJFOARK65U3Z7CTN62TW7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Annotation with Generative AI Requires Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Neil Fasching, Nicholas Pangakis, Samuel Wolken","submitted_at":"2023-05-31T20:50:45Z","abstract_excerpt":"Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty. Because these challenges will persist even as LLM technology improves, we argue that any automated annotation process using an LLM must validate the LLM's performance against labels generated by humans. To this end, we outline a workflow to harness the annotation potential of LLMs in a principled, efficient way. Using GPT-4, we validate this approach by replicati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00176","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/2306.00176/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":"2026-07-05T06:16:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QQNGPpsMloa6zdw1QNDHVZs+dETJb/U4DA4PgVTEnKlGiV41XI3G42kcLlhiPhmPcXIY9D4yO4h/9QKGvH4MCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:26:56.783339Z"},"content_sha256":"95c4149f046a385f6ad523c34b271999d32710824f5cfd157c72cfe5df7600d5","schema_version":"1.0","event_id":"sha256:95c4149f046a385f6ad523c34b271999d32710824f5cfd157c72cfe5df7600d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WI6OAYJFOARK65U3Z7CTN62TW7/bundle.json","state_url":"https://pith.science/pith/WI6OAYJFOARK65U3Z7CTN62TW7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WI6OAYJFOARK65U3Z7CTN62TW7/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":"2026-08-03T18:26:56Z","links":{"resolver":"https://pith.science/pith/WI6OAYJFOARK65U3Z7CTN62TW7","bundle":"https://pith.science/pith/WI6OAYJFOARK65U3Z7CTN62TW7/bundle.json","state":"https://pith.science/pith/WI6OAYJFOARK65U3Z7CTN62TW7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WI6OAYJFOARK65U3Z7CTN62TW7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WI6OAYJFOARK65U3Z7CTN62TW7","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":"e1657b1a4eef428fdd2bc766295476545766184d6266a8de982b8ce3873a6551","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T20:50:45Z","title_canon_sha256":"0541c048c2a673be3da6649dc9ec8fe62c85bc0690f3908f7c207b0aa3692064"},"schema_version":"1.0","source":{"id":"2306.00176","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00176","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00176v1","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00176","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"pith_short_12","alias_value":"WI6OAYJFOARK","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"pith_short_16","alias_value":"WI6OAYJFOARK65U3","created_at":"2026-07-05T06:16:23Z"},{"alias_kind":"pith_short_8","alias_value":"WI6OAYJF","created_at":"2026-07-05T06:16:23Z"}],"graph_snapshots":[{"event_id":"sha256:95c4149f046a385f6ad523c34b271999d32710824f5cfd157c72cfe5df7600d5","target":"graph","created_at":"2026-07-05T06:16:23Z","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/2306.00176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty. Because these challenges will persist even as LLM technology improves, we argue that any automated annotation process using an LLM must validate the LLM's performance against labels generated by humans. To this end, we outline a workflow to harness the annotation potential of LLMs in a principled, efficient way. Using GPT-4, we validate this approach by replicati","authors_text":"Neil Fasching, Nicholas Pangakis, Samuel Wolken","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T20:50:45Z","title":"Automated Annotation with Generative AI Requires Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00176","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:ead372b1dc352e758642268c1f063df2cf73a9c68e038778ebb9bbf9d1cf91fb","target":"record","created_at":"2026-07-05T06:16:23Z","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":"e1657b1a4eef428fdd2bc766295476545766184d6266a8de982b8ce3873a6551","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T20:50:45Z","title_canon_sha256":"0541c048c2a673be3da6649dc9ec8fe62c85bc0690f3908f7c207b0aa3692064"},"schema_version":"1.0","source":{"id":"2306.00176","kind":"arxiv","version":1}},"canonical_sha256":"b23ce061257022af769bcfc536fb53b7dba3b0e383e137f8829b0e5f59444132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b23ce061257022af769bcfc536fb53b7dba3b0e383e137f8829b0e5f59444132","first_computed_at":"2026-07-05T06:16:23.031235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:23.031235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HgDDq4lG7/dPRv2juLKdS9ClhhPUlFYNdxuAnVHFR2RTjsZXUow+lTpJNWqJ5748etJd8DITxNC5cwg8dK+TBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:23.031662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00176","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ead372b1dc352e758642268c1f063df2cf73a9c68e038778ebb9bbf9d1cf91fb","sha256:95c4149f046a385f6ad523c34b271999d32710824f5cfd157c72cfe5df7600d5"],"state_sha256":"5cfbdab418191d5739c0a1137e95a957651b4270d55d77acc086fe31ede944ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3BV0PDsedLk4jZqhxjS1d+W3zBx0bar09gZCMEm8Bn6lQV1cj7L12nir/hr36ocGeYdspdZ6oV08uWV4hpuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:26:56.786584Z","bundle_sha256":"ac8a20257d815a6b0bce985419e27bfdd3218625870cd3752d1a9802f57445d0"}}