{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YJ4Q74EBBXLG57D4EDIXCWV7RN","short_pith_number":"pith:YJ4Q74EB","canonical_record":{"source":{"id":"2502.08512","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T15:46:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5b7877f0f87efd1d8de316ba140204e399d56e8f2e3951a864d0f155b49ab349","abstract_canon_sha256":"5315d1823a2e1f2b988af94b6fd360330eb93fd0bd4c7de3fb9c763092ad8720"},"schema_version":"1.0"},"canonical_sha256":"c2790ff0810dd66efc7c20d1715abf8b77faccc58327e45b2fb3568c902ac989","source":{"kind":"arxiv","id":"2502.08512","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08512","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08512v3","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08512","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"pith_short_12","alias_value":"YJ4Q74EBBXLG","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"pith_short_16","alias_value":"YJ4Q74EBBXLG57D4","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"pith_short_8","alias_value":"YJ4Q74EB","created_at":"2026-07-05T11:53:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YJ4Q74EBBXLG57D4EDIXCWV7RN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08512","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T15:46:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5b7877f0f87efd1d8de316ba140204e399d56e8f2e3951a864d0f155b49ab349","abstract_canon_sha256":"5315d1823a2e1f2b988af94b6fd360330eb93fd0bd4c7de3fb9c763092ad8720"},"schema_version":"1.0"},"canonical_sha256":"c2790ff0810dd66efc7c20d1715abf8b77faccc58327e45b2fb3568c902ac989","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:44.064953Z","signature_b64":"VfL91Xn6Robdgv2QbOdLScts7vSDpmee+lnPak36pNJvymKVKuq65tIBa7ZchpFbfgOsciCAEyV8TYqqfkGtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2790ff0810dd66efc7c20d1715abf8b77faccc58327e45b2fb3568c902ac989","last_reissued_at":"2026-07-05T11:53:44.064546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:44.064546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08512","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4VaVsylnXB4H42m+8BBghmXo7CrcuidGOMh6AEdnzEkq5OlgUkYXZpcSWz2IlnqKBUyMSXbwIazuWhj+8CHHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:15:46.513851Z"},"content_sha256":"6e7b9ad6d3c7b4ac7197968c12911d20f3e283a6b38b2d56d0e45a872dc7e87c","schema_version":"1.0","event_id":"sha256:6e7b9ad6d3c7b4ac7197968c12911d20f3e283a6b38b2d56d0e45a872dc7e87c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YJ4Q74EBBXLG57D4EDIXCWV7RN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring Diversity in Synthetic Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bingzhe Wu, Huizhe Zhang, Jintang Li, Liang Chen, Peilin Zhao, Yatao Bian, Yuchang Zhu, Zibin Zheng","submitted_at":"2025-02-12T15:46:34Z","abstract_excerpt":"Large language models (LLMs) are widely adopted to generate synthetic datasets for various natural language processing (NLP) tasks, such as text classification and summarization. However, accurately measuring the diversity of these synthetic datasets-an aspect crucial for robust model performance-remains a significant challenge. In this paper, we introduce DCScore, a novel method for measuring synthetic dataset diversity from a classification perspective. Specifically, DCScore formulates diversity evaluation as a sample classification task, leveraging mutual relationships among samples. We fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08512","kind":"arxiv","version":3},"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/2502.08512/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":"2026-07-05T11:53:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4JsAWrGufYg7ajV3R+lUlAG5B2xBCNKBoKTmqq7AXrr/SCJA7K20ud6/ZYj/23JMbnf2yXJ1q2Bb9i9ZVVm+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:15:46.514753Z"},"content_sha256":"1d718d39c05aac2d201951238a40c30ec1cf161b18e4e168b0a726ae8c5a10b3","schema_version":"1.0","event_id":"sha256:1d718d39c05aac2d201951238a40c30ec1cf161b18e4e168b0a726ae8c5a10b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJ4Q74EBBXLG57D4EDIXCWV7RN/bundle.json","state_url":"https://pith.science/pith/YJ4Q74EBBXLG57D4EDIXCWV7RN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJ4Q74EBBXLG57D4EDIXCWV7RN/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":"2026-08-05T07:15:46Z","links":{"resolver":"https://pith.science/pith/YJ4Q74EBBXLG57D4EDIXCWV7RN","bundle":"https://pith.science/pith/YJ4Q74EBBXLG57D4EDIXCWV7RN/bundle.json","state":"https://pith.science/pith/YJ4Q74EBBXLG57D4EDIXCWV7RN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJ4Q74EBBXLG57D4EDIXCWV7RN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YJ4Q74EBBXLG57D4EDIXCWV7RN","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":"5315d1823a2e1f2b988af94b6fd360330eb93fd0bd4c7de3fb9c763092ad8720","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T15:46:34Z","title_canon_sha256":"5b7877f0f87efd1d8de316ba140204e399d56e8f2e3951a864d0f155b49ab349"},"schema_version":"1.0","source":{"id":"2502.08512","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08512","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08512v3","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08512","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"pith_short_12","alias_value":"YJ4Q74EBBXLG","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"pith_short_16","alias_value":"YJ4Q74EBBXLG57D4","created_at":"2026-07-05T11:53:44Z"},{"alias_kind":"pith_short_8","alias_value":"YJ4Q74EB","created_at":"2026-07-05T11:53:44Z"}],"graph_snapshots":[{"event_id":"sha256:1d718d39c05aac2d201951238a40c30ec1cf161b18e4e168b0a726ae8c5a10b3","target":"graph","created_at":"2026-07-05T11:53:44Z","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/2502.08512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are widely adopted to generate synthetic datasets for various natural language processing (NLP) tasks, such as text classification and summarization. However, accurately measuring the diversity of these synthetic datasets-an aspect crucial for robust model performance-remains a significant challenge. In this paper, we introduce DCScore, a novel method for measuring synthetic dataset diversity from a classification perspective. Specifically, DCScore formulates diversity evaluation as a sample classification task, leveraging mutual relationships among samples. We fur","authors_text":"Bingzhe Wu, Huizhe Zhang, Jintang Li, Liang Chen, Peilin Zhao, Yatao Bian, Yuchang Zhu, Zibin Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T15:46:34Z","title":"Measuring Diversity in Synthetic Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08512","kind":"arxiv","version":3},"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":"sha256:6e7b9ad6d3c7b4ac7197968c12911d20f3e283a6b38b2d56d0e45a872dc7e87c","target":"record","created_at":"2026-07-05T11:53:44Z","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":"5315d1823a2e1f2b988af94b6fd360330eb93fd0bd4c7de3fb9c763092ad8720","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T15:46:34Z","title_canon_sha256":"5b7877f0f87efd1d8de316ba140204e399d56e8f2e3951a864d0f155b49ab349"},"schema_version":"1.0","source":{"id":"2502.08512","kind":"arxiv","version":3}},"canonical_sha256":"c2790ff0810dd66efc7c20d1715abf8b77faccc58327e45b2fb3568c902ac989","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2790ff0810dd66efc7c20d1715abf8b77faccc58327e45b2fb3568c902ac989","first_computed_at":"2026-07-05T11:53:44.064546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:44.064546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VfL91Xn6Robdgv2QbOdLScts7vSDpmee+lnPak36pNJvymKVKuq65tIBa7ZchpFbfgOsciCAEyV8TYqqfkGtCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:44.064953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08512","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e7b9ad6d3c7b4ac7197968c12911d20f3e283a6b38b2d56d0e45a872dc7e87c","sha256:1d718d39c05aac2d201951238a40c30ec1cf161b18e4e168b0a726ae8c5a10b3"],"state_sha256":"30fdab5d2e543163fbeb32b38607f355a0761b939eff3b15d5a6f925f87cca5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rC8h+rXQhzYTbKiZv08xlawmA8Yszyb4w6LCg47RVafypZK79kbxngOe+2vuldPSkTjmcnvEEda1vP8IINhlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:15:46.521286Z","bundle_sha256":"6bdf11599b593dab93ecaf071df10d7a9f1259c421ed50d9ab4d2d54b68b8622"}}