{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WDC5EEDHA4IVRPRZPI4IJLIFTX","short_pith_number":"pith:WDC5EEDH","schema_version":"1.0","canonical_sha256":"b0c5d21067071158be397a3884ad059ddfbd1f4605b677c3f603810cacbd1607","source":{"kind":"arxiv","id":"2412.02980","version":2},"attestation_state":"computed","paper":{"title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex Havrilla, Alon Albalak, Andrew Dai, Baber Abbasi, Chase Blagden, Dakota Mahan, Duy Phung, Elliot Meyerson, Fabrizio Milo, Giovanni Paolini, Kanishk Gandhi, Koen Oostermeijer, Laura O'Mahony, Maia Iyer, Mohammed Hamdy, Pawan Sasanka Ammanamanchi, Sharath Chandra Raparthy, Srishti Gureja, Vera Zisler, Wen-Ding Li","submitted_at":"2024-12-04T02:47:45Z","abstract_excerpt":"Synthetic data generation with Large Language Models is a promising paradigm for augmenting natural data over a nearly infinite range of tasks. Given this variety, direct comparisons among synthetic data generation algorithms are scarce, making it difficult to understand where improvement comes from and what bottlenecks exist. We propose to evaluate algorithms via the makeup of synthetic data generated by each algorithm in terms of data quality, diversity, and complexity. We choose these three characteristics for their significance in open-ended processes and the impact each has on the capabil"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.02980","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T02:47:45Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"03f3c7aee9bb0947ce938ef605be262385670dc8f67bff404c1c770ac561ed22","abstract_canon_sha256":"55d20a298938adbb0440df714d64f936b6a56f69f8e5e323b7a8fd9d32dce902"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:55.765683Z","signature_b64":"b07T1sPG0KJrm7wxn5553hepynjX2EmSmOyjWMDZ8V7pJmFhAokHcUnGkS4wpwlLPaGDLq7EOsmS/RK2TQJUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c5d21067071158be397a3884ad059ddfbd1f4605b677c3f603810cacbd1607","last_reissued_at":"2026-07-05T09:46:55.765156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:55.765156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex Havrilla, Alon Albalak, Andrew Dai, Baber Abbasi, Chase Blagden, Dakota Mahan, Duy Phung, Elliot Meyerson, Fabrizio Milo, Giovanni Paolini, Kanishk Gandhi, Koen Oostermeijer, Laura O'Mahony, Maia Iyer, Mohammed Hamdy, Pawan Sasanka Ammanamanchi, Sharath Chandra Raparthy, Srishti Gureja, Vera Zisler, Wen-Ding Li","submitted_at":"2024-12-04T02:47:45Z","abstract_excerpt":"Synthetic data generation with Large Language Models is a promising paradigm for augmenting natural data over a nearly infinite range of tasks. Given this variety, direct comparisons among synthetic data generation algorithms are scarce, making it difficult to understand where improvement comes from and what bottlenecks exist. We propose to evaluate algorithms via the makeup of synthetic data generated by each algorithm in terms of data quality, diversity, and complexity. We choose these three characteristics for their significance in open-ended processes and the impact each has on the capabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02980","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/2412.02980/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.02980","created_at":"2026-07-05T09:46:55.765220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02980v2","created_at":"2026-07-05T09:46:55.765220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02980","created_at":"2026-07-05T09:46:55.765220+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDC5EEDHA4IV","created_at":"2026-07-05T09:46:55.765220+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDC5EEDHA4IVRPRZ","created_at":"2026-07-05T09:46:55.765220+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDC5EEDH","created_at":"2026-07-05T09:46:55.765220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29721","citing_title":"Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13654","citing_title":"Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22551","citing_title":"QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX","json":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX.json","graph_json":"https://pith.science/api/pith-number/WDC5EEDHA4IVRPRZPI4IJLIFTX/graph.json","events_json":"https://pith.science/api/pith-number/WDC5EEDHA4IVRPRZPI4IJLIFTX/events.json","paper":"https://pith.science/paper/WDC5EEDH"},"agent_actions":{"view_html":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX","download_json":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX.json","view_paper":"https://pith.science/paper/WDC5EEDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02980&json=true","fetch_graph":"https://pith.science/api/pith-number/WDC5EEDHA4IVRPRZPI4IJLIFTX/graph.json","fetch_events":"https://pith.science/api/pith-number/WDC5EEDHA4IVRPRZPI4IJLIFTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX/action/storage_attestation","attest_author":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX/action/author_attestation","sign_citation":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX/action/citation_signature","submit_replication":"https://pith.science/pith/WDC5EEDHA4IVRPRZPI4IJLIFTX/action/replication_record"}},"created_at":"2026-07-05T09:46:55.765220+00:00","updated_at":"2026-07-05T09:46:55.765220+00:00"}