{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3CWB2SR7ELIQP4JSU7OC7TV7HB","short_pith_number":"pith:3CWB2SR7","canonical_record":{"source":{"id":"2305.15041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:27:59Z","cross_cats_sorted":[],"title_canon_sha256":"26b8ee02df91a05277c50d782f4c0c7128d3ab793223b88b3a84eb6b6023d244","abstract_canon_sha256":"935b68cdcbefb02969a26897de33811cc946351bf62579f572b13b59d6d6aa67"},"schema_version":"1.0"},"canonical_sha256":"d8ac1d4a3f22d107f132a7dc2fcebf3860dce95ff13cec53a90e1af8ab8ab596","source":{"kind":"arxiv","id":"2305.15041","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15041","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15041v1","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15041","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"pith_short_12","alias_value":"3CWB2SR7ELIQ","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"pith_short_16","alias_value":"3CWB2SR7ELIQP4JS","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"pith_short_8","alias_value":"3CWB2SR7","created_at":"2026-07-05T06:13:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3CWB2SR7ELIQP4JSU7OC7TV7HB","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:27:59Z","cross_cats_sorted":[],"title_canon_sha256":"26b8ee02df91a05277c50d782f4c0c7128d3ab793223b88b3a84eb6b6023d244","abstract_canon_sha256":"935b68cdcbefb02969a26897de33811cc946351bf62579f572b13b59d6d6aa67"},"schema_version":"1.0"},"canonical_sha256":"d8ac1d4a3f22d107f132a7dc2fcebf3860dce95ff13cec53a90e1af8ab8ab596","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:30.351365Z","signature_b64":"wFC51w/ElDPzTwNxwhT7pQQ1tvmTI6VNl+hsqMRjEEa710FQeyP7Pj/oxtUeJXlk8EnRqPhqqigP+UMT+18LBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8ac1d4a3f22d107f132a7dc2fcebf3860dce95ff13cec53a90e1af8ab8ab596","last_reissued_at":"2026-07-05T06:13:30.350901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:30.350901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15041","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":"2026-07-05T06:13:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uxdXDwwbrTwAmB1p+ixI3ami/dezvtcysJLjTjgtsyy3BhU82V8BQHX1a+gyBXZxIutvIAObIL0j4b2/pY5PAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:12:11.123178Z"},"content_sha256":"3eaf3b1e70495b7ce17bbf0a6d1b25bfa6adde3638007e8388b76d315e22f392","schema_version":"1.0","event_id":"sha256:3eaf3b1e70495b7ce17bbf0a6d1b25bfa6adde3638007e8388b76d315e22f392"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3CWB2SR7ELIQP4JSU7OC7TV7HB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akhil Arora, Ashton Anderson, Manoel Horta Ribeiro, Martin Josifoski, Robert West, Veniamin Veselovsky","submitted_at":"2023-05-24T11:27:59Z","abstract_excerpt":"Large Language Models (LLMs) have democratized synthetic data generation, which in turn has the potential to simplify and broaden a wide gamut of NLP tasks. Here, we tackle a pervasive problem in synthetic data generation: its generative distribution often differs from the distribution of real-world data researchers care about (in other words, it is unfaithful). In a case study on sarcasm detection, we study three strategies to increase the faithfulness of synthetic data: grounding, filtering, and taxonomy-based generation. We evaluate these strategies using the performance of classifiers trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15041","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/2305.15041/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":"2026-07-05T06:13:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQ/6OOhaPXo6SvXQdME7iuTTMhJnZ+2WfWN/FEh1ZfZ1Vk7dUegsGqy+GbR1BQ8NqT2HzrTbc9vF9XbfRLlIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:12:11.124135Z"},"content_sha256":"78673366d85f860b473b0d5ebb65e407ba03884c67d918b1b8db1508d6193abc","schema_version":"1.0","event_id":"sha256:78673366d85f860b473b0d5ebb65e407ba03884c67d918b1b8db1508d6193abc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CWB2SR7ELIQP4JSU7OC7TV7HB/bundle.json","state_url":"https://pith.science/pith/3CWB2SR7ELIQP4JSU7OC7TV7HB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CWB2SR7ELIQP4JSU7OC7TV7HB/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":"2026-08-16T20:12:11Z","links":{"resolver":"https://pith.science/pith/3CWB2SR7ELIQP4JSU7OC7TV7HB","bundle":"https://pith.science/pith/3CWB2SR7ELIQP4JSU7OC7TV7HB/bundle.json","state":"https://pith.science/pith/3CWB2SR7ELIQP4JSU7OC7TV7HB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CWB2SR7ELIQP4JSU7OC7TV7HB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3CWB2SR7ELIQP4JSU7OC7TV7HB","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":"935b68cdcbefb02969a26897de33811cc946351bf62579f572b13b59d6d6aa67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:27:59Z","title_canon_sha256":"26b8ee02df91a05277c50d782f4c0c7128d3ab793223b88b3a84eb6b6023d244"},"schema_version":"1.0","source":{"id":"2305.15041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15041","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15041v1","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15041","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"pith_short_12","alias_value":"3CWB2SR7ELIQ","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"pith_short_16","alias_value":"3CWB2SR7ELIQP4JS","created_at":"2026-07-05T06:13:30Z"},{"alias_kind":"pith_short_8","alias_value":"3CWB2SR7","created_at":"2026-07-05T06:13:30Z"}],"graph_snapshots":[{"event_id":"sha256:78673366d85f860b473b0d5ebb65e407ba03884c67d918b1b8db1508d6193abc","target":"graph","created_at":"2026-07-05T06:13:30Z","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/2305.15041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have democratized synthetic data generation, which in turn has the potential to simplify and broaden a wide gamut of NLP tasks. Here, we tackle a pervasive problem in synthetic data generation: its generative distribution often differs from the distribution of real-world data researchers care about (in other words, it is unfaithful). In a case study on sarcasm detection, we study three strategies to increase the faithfulness of synthetic data: grounding, filtering, and taxonomy-based generation. We evaluate these strategies using the performance of classifiers trai","authors_text":"Akhil Arora, Ashton Anderson, Manoel Horta Ribeiro, Martin Josifoski, Robert West, Veniamin Veselovsky","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:27:59Z","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15041","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":"sha256:3eaf3b1e70495b7ce17bbf0a6d1b25bfa6adde3638007e8388b76d315e22f392","target":"record","created_at":"2026-07-05T06:13:30Z","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":"935b68cdcbefb02969a26897de33811cc946351bf62579f572b13b59d6d6aa67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:27:59Z","title_canon_sha256":"26b8ee02df91a05277c50d782f4c0c7128d3ab793223b88b3a84eb6b6023d244"},"schema_version":"1.0","source":{"id":"2305.15041","kind":"arxiv","version":1}},"canonical_sha256":"d8ac1d4a3f22d107f132a7dc2fcebf3860dce95ff13cec53a90e1af8ab8ab596","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8ac1d4a3f22d107f132a7dc2fcebf3860dce95ff13cec53a90e1af8ab8ab596","first_computed_at":"2026-07-05T06:13:30.350901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:30.350901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wFC51w/ElDPzTwNxwhT7pQQ1tvmTI6VNl+hsqMRjEEa710FQeyP7Pj/oxtUeJXlk8EnRqPhqqigP+UMT+18LBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:30.351365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eaf3b1e70495b7ce17bbf0a6d1b25bfa6adde3638007e8388b76d315e22f392","sha256:78673366d85f860b473b0d5ebb65e407ba03884c67d918b1b8db1508d6193abc"],"state_sha256":"0440367b087b286f391e0e916f43a5d1acde81d777c12fb8f88fc3ef7fe94aa9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UqczCB/x4h26ysYRRorlmTilSfQAVctohPS2Ei21MWDUAVrE7+DG1HaZHCQvk3HTOGmlUk2tK/grip3ysULnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:12:11.129728Z","bundle_sha256":"31103895c256340031dac5daf7057af791f80e0a077843b8d1558f3cd068634e"}}