{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YVEK4FRALJJGBBMCX4HYKXZQSR","short_pith_number":"pith:YVEK4FRA","canonical_record":{"source":{"id":"2306.04140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T04:27:09Z","cross_cats_sorted":[],"title_canon_sha256":"d655582b230a8605a32169ba4c6a386aebfc319e2329686526da178b072dfe7a","abstract_canon_sha256":"a4405b2e9e481fbcb90788d044f1bf9b9043173d49305c92af234ceed7b636b0"},"schema_version":"1.0"},"canonical_sha256":"c548ae16205a52608582bf0f855f309471318bdb717a82df83a8870956d50082","source":{"kind":"arxiv","id":"2306.04140","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04140","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04140v1","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04140","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"YVEK4FRALJJG","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"YVEK4FRALJJGBBMC","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"YVEK4FRA","created_at":"2026-07-05T06:39:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YVEK4FRALJJGBBMCX4HYKXZQSR","target":"record","payload":{"canonical_record":{"source":{"id":"2306.04140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T04:27:09Z","cross_cats_sorted":[],"title_canon_sha256":"d655582b230a8605a32169ba4c6a386aebfc319e2329686526da178b072dfe7a","abstract_canon_sha256":"a4405b2e9e481fbcb90788d044f1bf9b9043173d49305c92af234ceed7b636b0"},"schema_version":"1.0"},"canonical_sha256":"c548ae16205a52608582bf0f855f309471318bdb717a82df83a8870956d50082","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:54.069283Z","signature_b64":"mtPzzExv+1tgEPgsvaDCblyty90qV7Uk30bsjWd47YoZnMe4xh4jZ/CnTS5Pxpm6LIs0vCWcrdzjfuyXQCujAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c548ae16205a52608582bf0f855f309471318bdb717a82df83a8870956d50082","last_reissued_at":"2026-07-05T06:39:54.068914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:54.068914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.04140","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":"2026-07-05T06:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RVFflndihSm0Sx5zs/uZah9q8PU1aJrf1yyUcqW+gzKgAoWqFD4UX+BQVpPyptjYSUqmd/sFrRU2DgImr7bDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:23:22.945559Z"},"content_sha256":"e1272cf2e965f25cb6b90dcdec21dbdef0ccd944376efa00dd1b2093edebfe55","schema_version":"1.0","event_id":"sha256:e1272cf2e965f25cb6b90dcdec21dbdef0ccd944376efa00dd1b2093edebfe55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YVEK4FRALJJGBBMCX4HYKXZQSR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ece Kamar, John Joon Young Chung, Saleema Amershi","submitted_at":"2023-06-07T04:27:09Z","abstract_excerpt":"Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we explore human-AI partnerships to facilitate high diversity and accuracy in LLM-based text data generation. We first examine two approaches to diversify text generation: 1) logit suppression, which minimizes the generation of languages that have already been frequently generated, and 2) temperature sampling, which flattens the token sampling probability. We found that diversification approaches can increas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04140","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/2306.04140/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":"2026-07-05T06:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YqoXokqwzzwU3wsWRyp2hkhBrd2pslNPtRJf5hz17rX5EBNPiKtWE+r+kjdzGm8wUJLLMNaItesrXytHVBeNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:23:22.946308Z"},"content_sha256":"ff68a79703b564630ae2a563d424d3dc4acd7a82f8d3dab0ccae72ac2a721631","schema_version":"1.0","event_id":"sha256:ff68a79703b564630ae2a563d424d3dc4acd7a82f8d3dab0ccae72ac2a721631"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVEK4FRALJJGBBMCX4HYKXZQSR/bundle.json","state_url":"https://pith.science/pith/YVEK4FRALJJGBBMCX4HYKXZQSR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVEK4FRALJJGBBMCX4HYKXZQSR/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":"2026-08-19T18:23:22Z","links":{"resolver":"https://pith.science/pith/YVEK4FRALJJGBBMCX4HYKXZQSR","bundle":"https://pith.science/pith/YVEK4FRALJJGBBMCX4HYKXZQSR/bundle.json","state":"https://pith.science/pith/YVEK4FRALJJGBBMCX4HYKXZQSR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVEK4FRALJJGBBMCX4HYKXZQSR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YVEK4FRALJJGBBMCX4HYKXZQSR","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":"a4405b2e9e481fbcb90788d044f1bf9b9043173d49305c92af234ceed7b636b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T04:27:09Z","title_canon_sha256":"d655582b230a8605a32169ba4c6a386aebfc319e2329686526da178b072dfe7a"},"schema_version":"1.0","source":{"id":"2306.04140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04140","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04140v1","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04140","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"YVEK4FRALJJG","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"YVEK4FRALJJGBBMC","created_at":"2026-07-05T06:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"YVEK4FRA","created_at":"2026-07-05T06:39:54Z"}],"graph_snapshots":[{"event_id":"sha256:ff68a79703b564630ae2a563d424d3dc4acd7a82f8d3dab0ccae72ac2a721631","target":"graph","created_at":"2026-07-05T06:39:54Z","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/2306.04140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we explore human-AI partnerships to facilitate high diversity and accuracy in LLM-based text data generation. We first examine two approaches to diversify text generation: 1) logit suppression, which minimizes the generation of languages that have already been frequently generated, and 2) temperature sampling, which flattens the token sampling probability. We found that diversification approaches can increas","authors_text":"Ece Kamar, John Joon Young Chung, Saleema Amershi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T04:27:09Z","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04140","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:e1272cf2e965f25cb6b90dcdec21dbdef0ccd944376efa00dd1b2093edebfe55","target":"record","created_at":"2026-07-05T06:39:54Z","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":"a4405b2e9e481fbcb90788d044f1bf9b9043173d49305c92af234ceed7b636b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T04:27:09Z","title_canon_sha256":"d655582b230a8605a32169ba4c6a386aebfc319e2329686526da178b072dfe7a"},"schema_version":"1.0","source":{"id":"2306.04140","kind":"arxiv","version":1}},"canonical_sha256":"c548ae16205a52608582bf0f855f309471318bdb717a82df83a8870956d50082","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c548ae16205a52608582bf0f855f309471318bdb717a82df83a8870956d50082","first_computed_at":"2026-07-05T06:39:54.068914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:54.068914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mtPzzExv+1tgEPgsvaDCblyty90qV7Uk30bsjWd47YoZnMe4xh4jZ/CnTS5Pxpm6LIs0vCWcrdzjfuyXQCujAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:54.069283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1272cf2e965f25cb6b90dcdec21dbdef0ccd944376efa00dd1b2093edebfe55","sha256:ff68a79703b564630ae2a563d424d3dc4acd7a82f8d3dab0ccae72ac2a721631"],"state_sha256":"53a7bd0a897fdd6f381ebc152dac9648713df1efdd3e7c35750efd7f139ae8c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IIXWgA31MdemZuwPWvdnfo91bwgZJy4Fu5u9KgoZvtH6x8Vbvx33MN7ODEPdYR1HEADQi1xJUgm0O9a3A2ueAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T18:23:22.950888Z","bundle_sha256":"cc867aa455b61eddb8ba40b9d76806632aae0eb0eecdf855801ca096bfdad5a6"}}