{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BVH3UGGBICKJFZLMWYKNJ3ILR7","short_pith_number":"pith:BVH3UGGB","canonical_record":{"source":{"id":"2306.15895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-28T03:31:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9497560499de763059fa1176463cfce0743ddd5b458c8786f94f2ea05ad30d86","abstract_canon_sha256":"e13fdd12590dcc062b56142571e38c064430725e1687205091802a3903bf4ebe"},"schema_version":"1.0"},"canonical_sha256":"0d4fba18c1409492e56cb614d4ed0b8fff8513b596640bc92180c56de600a7ec","source":{"kind":"arxiv","id":"2306.15895","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15895","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15895v2","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15895","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"BVH3UGGBICKJ","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"pith_short_16","alias_value":"BVH3UGGBICKJFZLM","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"pith_short_8","alias_value":"BVH3UGGB","created_at":"2026-07-05T07:02:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BVH3UGGBICKJFZLMWYKNJ3ILR7","target":"record","payload":{"canonical_record":{"source":{"id":"2306.15895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-28T03:31:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9497560499de763059fa1176463cfce0743ddd5b458c8786f94f2ea05ad30d86","abstract_canon_sha256":"e13fdd12590dcc062b56142571e38c064430725e1687205091802a3903bf4ebe"},"schema_version":"1.0"},"canonical_sha256":"0d4fba18c1409492e56cb614d4ed0b8fff8513b596640bc92180c56de600a7ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:03.069356Z","signature_b64":"9s1H5KfYkztD1OoZXSHqGFvH4hMol/9q9pQ/kvDVUCQG9e7Q8Yji/q+dVj0JPWiz28ziivm3nlb4nwUxwZ3RAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d4fba18c1409492e56cb614d4ed0b8fff8513b596640bc92180c56de600a7ec","last_reissued_at":"2026-07-05T07:02:03.068843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:03.068843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.15895","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z2CfMJH3kP6onoSYuT+pBmdJ82UOdg7229bb5gwih3Sc12pU4x37eLvipwIKuWNBk2AZCMAGFV8C0mqkaPqiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:26:36.245979Z"},"content_sha256":"36c99d373c186724b99c73ca568b223e4bd85e865ae3e40ef852a1eb442d54de","schema_version":"1.0","event_id":"sha256:36c99d373c186724b99c73ca568b223e4bd85e865ae3e40ef852a1eb442d54de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BVH3UGGBICKJFZLMWYKNJ3ILR7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Ratner, Chao Zhang, Jiaming Shen, Jieyu Zhang, Ranjay Krishna, Yuchen Zhuang, Yue Yu, Yu Meng","submitted_at":"2023-06-28T03:31:31Z","abstract_excerpt":"Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally rely on simple class-conditional prompts, which may limit the diversity of the generated data and inherit systematic biases of LLM. Thus, we investigate training data generation with diversely attributed prompts (e.g., specifying attributes like length and style), which have the potential to yield diverse and attributed generated data. Our inves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15895","kind":"arxiv","version":2},"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/2306.15895/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":"2026-07-05T07:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWOZiFyUiSOti1uTwlj3QedOLVLPzxws8Lt9oTEV5ORXs7DsdHR2iAGpLVCy27h6nJHpiYiyAbj3Q04EBHuPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:26:36.246477Z"},"content_sha256":"5c6fe602fa6b6de47b64ead0dd163e322e8db88953d15452a33778f8feffc1a8","schema_version":"1.0","event_id":"sha256:5c6fe602fa6b6de47b64ead0dd163e322e8db88953d15452a33778f8feffc1a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVH3UGGBICKJFZLMWYKNJ3ILR7/bundle.json","state_url":"https://pith.science/pith/BVH3UGGBICKJFZLMWYKNJ3ILR7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVH3UGGBICKJFZLMWYKNJ3ILR7/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":"2026-08-09T03:26:36Z","links":{"resolver":"https://pith.science/pith/BVH3UGGBICKJFZLMWYKNJ3ILR7","bundle":"https://pith.science/pith/BVH3UGGBICKJFZLMWYKNJ3ILR7/bundle.json","state":"https://pith.science/pith/BVH3UGGBICKJFZLMWYKNJ3ILR7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVH3UGGBICKJFZLMWYKNJ3ILR7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BVH3UGGBICKJFZLMWYKNJ3ILR7","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":"e13fdd12590dcc062b56142571e38c064430725e1687205091802a3903bf4ebe","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-28T03:31:31Z","title_canon_sha256":"9497560499de763059fa1176463cfce0743ddd5b458c8786f94f2ea05ad30d86"},"schema_version":"1.0","source":{"id":"2306.15895","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15895","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15895v2","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15895","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"BVH3UGGBICKJ","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"pith_short_16","alias_value":"BVH3UGGBICKJFZLM","created_at":"2026-07-05T07:02:03Z"},{"alias_kind":"pith_short_8","alias_value":"BVH3UGGB","created_at":"2026-07-05T07:02:03Z"}],"graph_snapshots":[{"event_id":"sha256:5c6fe602fa6b6de47b64ead0dd163e322e8db88953d15452a33778f8feffc1a8","target":"graph","created_at":"2026-07-05T07:02:03Z","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/2306.15895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally rely on simple class-conditional prompts, which may limit the diversity of the generated data and inherit systematic biases of LLM. Thus, we investigate training data generation with diversely attributed prompts (e.g., specifying attributes like length and style), which have the potential to yield diverse and attributed generated data. Our inves","authors_text":"Alexander Ratner, Chao Zhang, Jiaming Shen, Jieyu Zhang, Ranjay Krishna, Yuchen Zhuang, Yue Yu, Yu Meng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-28T03:31:31Z","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15895","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":"sha256:36c99d373c186724b99c73ca568b223e4bd85e865ae3e40ef852a1eb442d54de","target":"record","created_at":"2026-07-05T07:02:03Z","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":"e13fdd12590dcc062b56142571e38c064430725e1687205091802a3903bf4ebe","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-28T03:31:31Z","title_canon_sha256":"9497560499de763059fa1176463cfce0743ddd5b458c8786f94f2ea05ad30d86"},"schema_version":"1.0","source":{"id":"2306.15895","kind":"arxiv","version":2}},"canonical_sha256":"0d4fba18c1409492e56cb614d4ed0b8fff8513b596640bc92180c56de600a7ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d4fba18c1409492e56cb614d4ed0b8fff8513b596640bc92180c56de600a7ec","first_computed_at":"2026-07-05T07:02:03.068843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:03.068843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9s1H5KfYkztD1OoZXSHqGFvH4hMol/9q9pQ/kvDVUCQG9e7Q8Yji/q+dVj0JPWiz28ziivm3nlb4nwUxwZ3RAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:03.069356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15895","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36c99d373c186724b99c73ca568b223e4bd85e865ae3e40ef852a1eb442d54de","sha256:5c6fe602fa6b6de47b64ead0dd163e322e8db88953d15452a33778f8feffc1a8"],"state_sha256":"686b45c440737a81054fa4daf62a533583ed3dd3f6126fec2b7325add297db88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPhnSU/roX17epGlS6tRINC5YhIPiL+ynY91MnnHPMPdCGDu+xK+sk23n+qs+h64aT52JEFIWzMCKzy7ozlQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:26:36.250863Z","bundle_sha256":"977a36765efa5acf20e9810cfac669fa36df9fd2a6e5202ca36447f3a8cffc64"}}