{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2HHPWRQASU5D2P4NCOEMCJ5DMP","short_pith_number":"pith:2HHPWRQA","canonical_record":{"source":{"id":"2310.20111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T01:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"9279feaf735a8ac8515a748b50797e3d6ca8e2311ef4c6b634d5bd7ab32c1d17","abstract_canon_sha256":"c8f91745a1764ad3a99e9a63d9ab6744672f1a32eaab63da3e60a7f480e63f52"},"schema_version":"1.0"},"canonical_sha256":"d1cefb4600953a3d3f8d1388c127a363e595aa6327ad5417056302aa52f61341","source":{"kind":"arxiv","id":"2310.20111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20111","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20111v1","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20111","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"2HHPWRQASU5D","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"2HHPWRQASU5D2P4N","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"2HHPWRQA","created_at":"2026-07-05T07:07:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2HHPWRQASU5D2P4NCOEMCJ5DMP","target":"record","payload":{"canonical_record":{"source":{"id":"2310.20111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T01:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"9279feaf735a8ac8515a748b50797e3d6ca8e2311ef4c6b634d5bd7ab32c1d17","abstract_canon_sha256":"c8f91745a1764ad3a99e9a63d9ab6744672f1a32eaab63da3e60a7f480e63f52"},"schema_version":"1.0"},"canonical_sha256":"d1cefb4600953a3d3f8d1388c127a363e595aa6327ad5417056302aa52f61341","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:24.187711Z","signature_b64":"V/n1ThQ77NUtt/Aeq7amHtq9KZRFSzNHSxHxqqek6ZlmFoG6MRZsKjI0C5ZpdVvzo8H082s3RmfS/+kYvHSYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1cefb4600953a3d3f8d1388c127a363e595aa6327ad5417056302aa52f61341","last_reissued_at":"2026-07-05T07:07:24.187223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:24.187223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.20111","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":"2026-07-05T07:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMKv8ogHUzyJZxtrnsczlpVtNC8vUFIuw1zcSoQszDUn4ub0z2lpVEygjffg7rJtsDE0oKDfhl9si7TSb7y0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:20:24.534975Z"},"content_sha256":"a43e92642258d1b99a80cd4674ef1eb39a85da398560339485edea8685eeac70","schema_version":"1.0","event_id":"sha256:a43e92642258d1b99a80cd4674ef1eb39a85da398560339485edea8685eeac70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2HHPWRQASU5D2P4NCOEMCJ5DMP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making Large Language Models Better Data Creators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong-Ho Lee, Jay Pujara, Mohit Sewak, Ryen W. White, Sujay Kumar Jauhar","submitted_at":"2023-10-31T01:08:34Z","abstract_excerpt":"Although large language models (LLMs) have advanced the state-of-the-art in NLP significantly, deploying them for downstream applications is still challenging due to cost, responsiveness, control, or concerns around privacy and security. As such, trainable models are still the preferred option in some cases. However, these models still require human-labeled data for optimal performance, which is expensive and time-consuming to obtain. In order to address this issue, several techniques to reduce human effort involve labeling or generating data using LLMs. Although these methods are effective fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20111","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/2310.20111/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":"2026-07-05T07:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbemcYinggRdtg956jIW3B+UwR8jF04qYhoC+fQqDKVHtpXXZQ//8OsBmTYSF6maoG485mwAWjU1kDq6g9JjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:20:24.535551Z"},"content_sha256":"c422bc1dc51c024e001db016f1741a1d44d474025de0491cd0590b6b4ce3fbeb","schema_version":"1.0","event_id":"sha256:c422bc1dc51c024e001db016f1741a1d44d474025de0491cd0590b6b4ce3fbeb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2HHPWRQASU5D2P4NCOEMCJ5DMP/bundle.json","state_url":"https://pith.science/pith/2HHPWRQASU5D2P4NCOEMCJ5DMP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2HHPWRQASU5D2P4NCOEMCJ5DMP/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":"2026-08-07T13:20:24Z","links":{"resolver":"https://pith.science/pith/2HHPWRQASU5D2P4NCOEMCJ5DMP","bundle":"https://pith.science/pith/2HHPWRQASU5D2P4NCOEMCJ5DMP/bundle.json","state":"https://pith.science/pith/2HHPWRQASU5D2P4NCOEMCJ5DMP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2HHPWRQASU5D2P4NCOEMCJ5DMP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2HHPWRQASU5D2P4NCOEMCJ5DMP","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":"c8f91745a1764ad3a99e9a63d9ab6744672f1a32eaab63da3e60a7f480e63f52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T01:08:34Z","title_canon_sha256":"9279feaf735a8ac8515a748b50797e3d6ca8e2311ef4c6b634d5bd7ab32c1d17"},"schema_version":"1.0","source":{"id":"2310.20111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20111","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20111v1","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20111","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"2HHPWRQASU5D","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"2HHPWRQASU5D2P4N","created_at":"2026-07-05T07:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"2HHPWRQA","created_at":"2026-07-05T07:07:24Z"}],"graph_snapshots":[{"event_id":"sha256:c422bc1dc51c024e001db016f1741a1d44d474025de0491cd0590b6b4ce3fbeb","target":"graph","created_at":"2026-07-05T07:07:24Z","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/2310.20111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) have advanced the state-of-the-art in NLP significantly, deploying them for downstream applications is still challenging due to cost, responsiveness, control, or concerns around privacy and security. As such, trainable models are still the preferred option in some cases. However, these models still require human-labeled data for optimal performance, which is expensive and time-consuming to obtain. In order to address this issue, several techniques to reduce human effort involve labeling or generating data using LLMs. Although these methods are effective fo","authors_text":"Dong-Ho Lee, Jay Pujara, Mohit Sewak, Ryen W. White, Sujay Kumar Jauhar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T01:08:34Z","title":"Making Large Language Models Better Data Creators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20111","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:a43e92642258d1b99a80cd4674ef1eb39a85da398560339485edea8685eeac70","target":"record","created_at":"2026-07-05T07:07:24Z","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":"c8f91745a1764ad3a99e9a63d9ab6744672f1a32eaab63da3e60a7f480e63f52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T01:08:34Z","title_canon_sha256":"9279feaf735a8ac8515a748b50797e3d6ca8e2311ef4c6b634d5bd7ab32c1d17"},"schema_version":"1.0","source":{"id":"2310.20111","kind":"arxiv","version":1}},"canonical_sha256":"d1cefb4600953a3d3f8d1388c127a363e595aa6327ad5417056302aa52f61341","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1cefb4600953a3d3f8d1388c127a363e595aa6327ad5417056302aa52f61341","first_computed_at":"2026-07-05T07:07:24.187223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:24.187223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/n1ThQ77NUtt/Aeq7amHtq9KZRFSzNHSxHxqqek6ZlmFoG6MRZsKjI0C5ZpdVvzo8H082s3RmfS/+kYvHSYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:24.187711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.20111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a43e92642258d1b99a80cd4674ef1eb39a85da398560339485edea8685eeac70","sha256:c422bc1dc51c024e001db016f1741a1d44d474025de0491cd0590b6b4ce3fbeb"],"state_sha256":"f86bd77ffccd7bc8276043ab013a0b031ff166cf7e500def20901e61f108ab03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mq3wfN5+67rRpx6yBbS/3iww8rjYDeikDhun79zQG6LZr33/UuzOUVoh0nsReMR7vKV1yXvKlKO0rbqORIV7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T13:20:24.539108Z","bundle_sha256":"1c1919eb4d10740aefe670b5803cd69bafdf39839bc218953004209d57fd7f53"}}