{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4BK5RD6T2TFI4Y2CDKMQM5HLXZ","short_pith_number":"pith:4BK5RD6T","canonical_record":{"source":{"id":"2412.03679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T19:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"1ccc7fc225e81860bde07511236df1bf7918a0b97df90d2dcd1824985a6a6a99","abstract_canon_sha256":"9a8cfe9edad02b0fd25083b384ac69766c7111b5521217d586d011cc73df98d2"},"schema_version":"1.0"},"canonical_sha256":"e055d88fd3d4ca8e63421a990674ebbe7ac205061f90ecebd8877a5c8f1b3a5b","source":{"kind":"arxiv","id":"2412.03679","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03679","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03679v2","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03679","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"4BK5RD6T2TFI","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"4BK5RD6T2TFI4Y2C","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"4BK5RD6T","created_at":"2026-07-05T12:02:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4BK5RD6T2TFI4Y2CDKMQM5HLXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T19:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"1ccc7fc225e81860bde07511236df1bf7918a0b97df90d2dcd1824985a6a6a99","abstract_canon_sha256":"9a8cfe9edad02b0fd25083b384ac69766c7111b5521217d586d011cc73df98d2"},"schema_version":"1.0"},"canonical_sha256":"e055d88fd3d4ca8e63421a990674ebbe7ac205061f90ecebd8877a5c8f1b3a5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:38.487272Z","signature_b64":"dqn95Df46IzZG1T6m3eEN7GLT5WpszjUjfvt7HxWi2sBmXZLuvZ7R4gfW18s+srdLB8x+IomubY6ORtdnrlUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e055d88fd3d4ca8e63421a990674ebbe7ac205061f90ecebd8877a5c8f1b3a5b","last_reissued_at":"2026-07-05T12:02:38.486679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:38.486679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03679","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":"2026-07-05T12:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o6fLV05TeTWcQGpsk8KOx2UF4ETA9Zp9MRJVpU9e7xcd/toV61a9szLU72uV7fWlysFoUWNv5VT4FA0i5FrYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:05:29.822183Z"},"content_sha256":"c409501c40933fed2f8c5dc940a4fa5b7127d0ca1d27c6922a6b1f9924465dfa","schema_version":"1.0","event_id":"sha256:c409501c40933fed2f8c5dc940a4fa5b7127d0ca1d27c6922a6b1f9924465dfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4BK5RD6T2TFI4Y2CDKMQM5HLXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Language Models as Synthetic Data Generators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Carolin Lawrence, Graham Neubig, Juyoung Suk, Kiril Gashteovski, Sean Welleck, Seongyun Lee, Seungone Kim, Vijay Viswanathan, Xiang Yue, Yizhong Wang","submitted_at":"2024-12-04T19:20:32Z","abstract_excerpt":"Given the increasing use of synthetic data in language model (LM) post-training, an LM's ability to generate high-quality data has become nearly as crucial as its ability to solve problems directly. While prior works have focused on developing effective data generation methods, they lack systematic comparison of different LMs as data generators in a unified setting. To address this gap, we propose AgoraBench, a benchmark that provides standardized settings and metrics to evaluate LMs' data generation abilities. Through synthesizing 1.26 million training instances using 6 LMs and training 99 st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03679","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/2412.03679/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":"2026-07-05T12:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZmO8eKFIQoWiFzSkyMRdPVWLzCd1OBHzm+Ng/W7zfhkEsbs8p1VGZvwZYWfl3DiD2AAc+1Y1WObnabUKE7xsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:05:29.822520Z"},"content_sha256":"a2c66ad810afed20b6b2b2bbfa2456f970497ad68a021627a0b541eba3affde6","schema_version":"1.0","event_id":"sha256:a2c66ad810afed20b6b2b2bbfa2456f970497ad68a021627a0b541eba3affde6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BK5RD6T2TFI4Y2CDKMQM5HLXZ/bundle.json","state_url":"https://pith.science/pith/4BK5RD6T2TFI4Y2CDKMQM5HLXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BK5RD6T2TFI4Y2CDKMQM5HLXZ/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":"2026-08-06T03:05:29Z","links":{"resolver":"https://pith.science/pith/4BK5RD6T2TFI4Y2CDKMQM5HLXZ","bundle":"https://pith.science/pith/4BK5RD6T2TFI4Y2CDKMQM5HLXZ/bundle.json","state":"https://pith.science/pith/4BK5RD6T2TFI4Y2CDKMQM5HLXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BK5RD6T2TFI4Y2CDKMQM5HLXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4BK5RD6T2TFI4Y2CDKMQM5HLXZ","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":"9a8cfe9edad02b0fd25083b384ac69766c7111b5521217d586d011cc73df98d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T19:20:32Z","title_canon_sha256":"1ccc7fc225e81860bde07511236df1bf7918a0b97df90d2dcd1824985a6a6a99"},"schema_version":"1.0","source":{"id":"2412.03679","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03679","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03679v2","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03679","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"4BK5RD6T2TFI","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"4BK5RD6T2TFI4Y2C","created_at":"2026-07-05T12:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"4BK5RD6T","created_at":"2026-07-05T12:02:38Z"}],"graph_snapshots":[{"event_id":"sha256:a2c66ad810afed20b6b2b2bbfa2456f970497ad68a021627a0b541eba3affde6","target":"graph","created_at":"2026-07-05T12:02:38Z","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/2412.03679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given the increasing use of synthetic data in language model (LM) post-training, an LM's ability to generate high-quality data has become nearly as crucial as its ability to solve problems directly. While prior works have focused on developing effective data generation methods, they lack systematic comparison of different LMs as data generators in a unified setting. To address this gap, we propose AgoraBench, a benchmark that provides standardized settings and metrics to evaluate LMs' data generation abilities. Through synthesizing 1.26 million training instances using 6 LMs and training 99 st","authors_text":"Carolin Lawrence, Graham Neubig, Juyoung Suk, Kiril Gashteovski, Sean Welleck, Seongyun Lee, Seungone Kim, Vijay Viswanathan, Xiang Yue, Yizhong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T19:20:32Z","title":"Evaluating Language Models as Synthetic Data Generators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03679","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:c409501c40933fed2f8c5dc940a4fa5b7127d0ca1d27c6922a6b1f9924465dfa","target":"record","created_at":"2026-07-05T12:02:38Z","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":"9a8cfe9edad02b0fd25083b384ac69766c7111b5521217d586d011cc73df98d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T19:20:32Z","title_canon_sha256":"1ccc7fc225e81860bde07511236df1bf7918a0b97df90d2dcd1824985a6a6a99"},"schema_version":"1.0","source":{"id":"2412.03679","kind":"arxiv","version":2}},"canonical_sha256":"e055d88fd3d4ca8e63421a990674ebbe7ac205061f90ecebd8877a5c8f1b3a5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e055d88fd3d4ca8e63421a990674ebbe7ac205061f90ecebd8877a5c8f1b3a5b","first_computed_at":"2026-07-05T12:02:38.486679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:38.486679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dqn95Df46IzZG1T6m3eEN7GLT5WpszjUjfvt7HxWi2sBmXZLuvZ7R4gfW18s+srdLB8x+IomubY6ORtdnrlUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:38.487272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03679","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c409501c40933fed2f8c5dc940a4fa5b7127d0ca1d27c6922a6b1f9924465dfa","sha256:a2c66ad810afed20b6b2b2bbfa2456f970497ad68a021627a0b541eba3affde6"],"state_sha256":"72373db4c21c1028e7518e7389a65b1a5a1a376ec7dcb713ea237d70f5c0b8e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Paj4jD9pUwduckQ7+FqsKzBgWWwkvJjRCSF6tuny2o9EhjHuPqqfoRcsC4OmEE1eNehk2aYEmXgr0s/RFe3IBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:05:29.832697Z","bundle_sha256":"b59d7d63c573ddb6d62d63373bf89f4cff788fdf20d3a02a777b920caceca362"}}