{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BW6SUXM5TZRSYTJM3TXY7LDCQF","short_pith_number":"pith:BW6SUXM5","canonical_record":{"source":{"id":"2409.11968","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T13:20:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"28ddb36a206ecc8485f650c4b6e0fa05d50cf51010bb7d208bbfcea92da4c657","abstract_canon_sha256":"858926fdfa886b4caa9f0652fdeef50da4bdfaff1cc433d0195ee0ffada51b1f"},"schema_version":"1.0"},"canonical_sha256":"0dbd2a5d9d9e632c4d2cdcef8fac62816671c81d569ba93ce789571281361d4f","source":{"kind":"arxiv","id":"2409.11968","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11968","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11968v1","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11968","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"pith_short_12","alias_value":"BW6SUXM5TZRS","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"pith_short_16","alias_value":"BW6SUXM5TZRSYTJM","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"pith_short_8","alias_value":"BW6SUXM5","created_at":"2026-07-05T09:08:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BW6SUXM5TZRSYTJM3TXY7LDCQF","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11968","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T13:20:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"28ddb36a206ecc8485f650c4b6e0fa05d50cf51010bb7d208bbfcea92da4c657","abstract_canon_sha256":"858926fdfa886b4caa9f0652fdeef50da4bdfaff1cc433d0195ee0ffada51b1f"},"schema_version":"1.0"},"canonical_sha256":"0dbd2a5d9d9e632c4d2cdcef8fac62816671c81d569ba93ce789571281361d4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:40.335436Z","signature_b64":"ZvWyzqeR003g+oc8fHXgYd1A8zfETCwUCTOBrD3eLpSAfRVjMxNoC3nFpoPnBWGhEfH5DeGulbbvJb6sBCYFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dbd2a5d9d9e632c4d2cdcef8fac62816671c81d569ba93ce789571281361d4f","last_reissued_at":"2026-07-05T09:08:40.334942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:40.334942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11968","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":"2026-07-05T09:08:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Owq+NrAqnqNLU0CnFQ/mw0JO8lfLs4KgUL7VNyo5jOLSJzH+koHJK57YVKWSG2vhwJVCDSAEKQ6KJcsiSWJoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:58:42.539343Z"},"content_sha256":"152e9f2d42f604bbbbfeb741ca7384436ae8cf1fd3cf0db7ad880c6e716dc015","schema_version":"1.0","event_id":"sha256:152e9f2d42f604bbbbfeb741ca7384436ae8cf1fd3cf0db7ad880c6e716dc015"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BW6SUXM5TZRSYTJM3TXY7LDCQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficacy of Synthetic Data as a Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dmitry Ivanov, Gaurav Maheshwari, Kevin El Haddad","submitted_at":"2024-09-18T13:20:23Z","abstract_excerpt":"Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is essential to understand how representative they are of real-world data. We investigate this by assessing the effectiveness of generating synthetic data through LLM and using it as a benchmark for various NLP tasks. Our experiments across six datasets, and three different tasks, show that while synthetic data can effectively capture performance of various me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11968","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/2409.11968/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":"2026-07-05T09:08:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NWSQHOHTrLQwQZv7lXbK2uShjEsKMI3iB8pmmaU8SEEesbMuyp39A9d2hRdBDm1EYiEYZ+IcIU1jZdcdg9tEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:58:42.539852Z"},"content_sha256":"7455ff67c9c74fee73ab50c19aa0d5091ff33dab80ceae82398630e3d01d6e73","schema_version":"1.0","event_id":"sha256:7455ff67c9c74fee73ab50c19aa0d5091ff33dab80ceae82398630e3d01d6e73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BW6SUXM5TZRSYTJM3TXY7LDCQF/bundle.json","state_url":"https://pith.science/pith/BW6SUXM5TZRSYTJM3TXY7LDCQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BW6SUXM5TZRSYTJM3TXY7LDCQF/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":"2026-08-06T18:58:42Z","links":{"resolver":"https://pith.science/pith/BW6SUXM5TZRSYTJM3TXY7LDCQF","bundle":"https://pith.science/pith/BW6SUXM5TZRSYTJM3TXY7LDCQF/bundle.json","state":"https://pith.science/pith/BW6SUXM5TZRSYTJM3TXY7LDCQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BW6SUXM5TZRSYTJM3TXY7LDCQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BW6SUXM5TZRSYTJM3TXY7LDCQF","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":"858926fdfa886b4caa9f0652fdeef50da4bdfaff1cc433d0195ee0ffada51b1f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T13:20:23Z","title_canon_sha256":"28ddb36a206ecc8485f650c4b6e0fa05d50cf51010bb7d208bbfcea92da4c657"},"schema_version":"1.0","source":{"id":"2409.11968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11968","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11968v1","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11968","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"pith_short_12","alias_value":"BW6SUXM5TZRS","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"pith_short_16","alias_value":"BW6SUXM5TZRSYTJM","created_at":"2026-07-05T09:08:40Z"},{"alias_kind":"pith_short_8","alias_value":"BW6SUXM5","created_at":"2026-07-05T09:08:40Z"}],"graph_snapshots":[{"event_id":"sha256:7455ff67c9c74fee73ab50c19aa0d5091ff33dab80ceae82398630e3d01d6e73","target":"graph","created_at":"2026-07-05T09:08:40Z","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/2409.11968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is essential to understand how representative they are of real-world data. We investigate this by assessing the effectiveness of generating synthetic data through LLM and using it as a benchmark for various NLP tasks. Our experiments across six datasets, and three different tasks, show that while synthetic data can effectively capture performance of various me","authors_text":"Dmitry Ivanov, Gaurav Maheshwari, Kevin El Haddad","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T13:20:23Z","title":"Efficacy of Synthetic Data as a Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11968","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":"sha256:152e9f2d42f604bbbbfeb741ca7384436ae8cf1fd3cf0db7ad880c6e716dc015","target":"record","created_at":"2026-07-05T09:08:40Z","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":"858926fdfa886b4caa9f0652fdeef50da4bdfaff1cc433d0195ee0ffada51b1f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T13:20:23Z","title_canon_sha256":"28ddb36a206ecc8485f650c4b6e0fa05d50cf51010bb7d208bbfcea92da4c657"},"schema_version":"1.0","source":{"id":"2409.11968","kind":"arxiv","version":1}},"canonical_sha256":"0dbd2a5d9d9e632c4d2cdcef8fac62816671c81d569ba93ce789571281361d4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dbd2a5d9d9e632c4d2cdcef8fac62816671c81d569ba93ce789571281361d4f","first_computed_at":"2026-07-05T09:08:40.334942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:40.334942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZvWyzqeR003g+oc8fHXgYd1A8zfETCwUCTOBrD3eLpSAfRVjMxNoC3nFpoPnBWGhEfH5DeGulbbvJb6sBCYFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:40.335436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:152e9f2d42f604bbbbfeb741ca7384436ae8cf1fd3cf0db7ad880c6e716dc015","sha256:7455ff67c9c74fee73ab50c19aa0d5091ff33dab80ceae82398630e3d01d6e73"],"state_sha256":"8ef51286b49ee6543cac067a27970833b00279b7d68f95fe8e2633ba228047b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29cGn8HApLTEnu75v5HjzDg9pUT9m/egi+RpA/x7o5KECgE4IRKGpUEZlSUq8t1GNBY6944pP2VTRnpo71iBCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:58:42.544890Z","bundle_sha256":"3f226992fb14ac1b3bef3dd2f9c0d0209ef79b12966975c73484e3b72b9408ae"}}