{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLYHGDRGKKH66JSP7QB7PB6IFM","short_pith_number":"pith:KLYHGDRG","schema_version":"1.0","canonical_sha256":"52f0730e26528fef264ffc03f787c82b3ccb62daadd9f8173f37fe589d437885","source":{"kind":"arxiv","id":"2407.21669","version":2},"attestation_state":"computed","paper":{"title":"Synth-Empathy: Towards High-Quality Synthetic Empathy Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Conghui He, Hao Liang, Jingxuan Wei, Linkun Sun, Linzhuang Sun, Wentao Zhang, Xijie Huang","submitted_at":"2024-07-31T15:12:24Z","abstract_excerpt":"In recent years, with the rapid advancements in large language models (LLMs), achieving excellent empathetic response capabilities has become a crucial prerequisite. Consequently, managing and understanding empathetic datasets have gained increasing significance. However, empathetic data are typically human-labeled, leading to insufficient datasets and wasted human labor. In this work, we present Synth-Empathy, an LLM-based data generation and quality and diversity selection pipeline that automatically generates high-quality empathetic data while discarding low-quality data. With the data gene"},"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":"2407.21669","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-31T15:12:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d826d2ff6d55351e6a9c60014c253cc4893365ab8932454376c7328f4458e66b","abstract_canon_sha256":"dbf7e8c7b22b48140ad7a9029fa13d3ba19635db033e3716fad78bea57ae6a8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:16.386934Z","signature_b64":"7kvN/wJt9Pr2cEfRn8r2SzSNqPV9ip3pVMXSHiJ7jcClp2nZx58YOiyKq/ngg79RLd7VbMC6bfaWH57weN9uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52f0730e26528fef264ffc03f787c82b3ccb62daadd9f8173f37fe589d437885","last_reissued_at":"2026-07-05T08:54:16.386465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:16.386465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synth-Empathy: Towards High-Quality Synthetic Empathy Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Conghui He, Hao Liang, Jingxuan Wei, Linkun Sun, Linzhuang Sun, Wentao Zhang, Xijie Huang","submitted_at":"2024-07-31T15:12:24Z","abstract_excerpt":"In recent years, with the rapid advancements in large language models (LLMs), achieving excellent empathetic response capabilities has become a crucial prerequisite. Consequently, managing and understanding empathetic datasets have gained increasing significance. However, empathetic data are typically human-labeled, leading to insufficient datasets and wasted human labor. In this work, we present Synth-Empathy, an LLM-based data generation and quality and diversity selection pipeline that automatically generates high-quality empathetic data while discarding low-quality data. With the data gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21669","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/2407.21669/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":"2407.21669","created_at":"2026-07-05T08:54:16.386524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21669v2","created_at":"2026-07-05T08:54:16.386524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21669","created_at":"2026-07-05T08:54:16.386524+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLYHGDRGKKH6","created_at":"2026-07-05T08:54:16.386524+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLYHGDRGKKH66JSP","created_at":"2026-07-05T08:54:16.386524+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLYHGDRG","created_at":"2026-07-05T08:54:16.386524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM","json":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM.json","graph_json":"https://pith.science/api/pith-number/KLYHGDRGKKH66JSP7QB7PB6IFM/graph.json","events_json":"https://pith.science/api/pith-number/KLYHGDRGKKH66JSP7QB7PB6IFM/events.json","paper":"https://pith.science/paper/KLYHGDRG"},"agent_actions":{"view_html":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM","download_json":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM.json","view_paper":"https://pith.science/paper/KLYHGDRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21669&json=true","fetch_graph":"https://pith.science/api/pith-number/KLYHGDRGKKH66JSP7QB7PB6IFM/graph.json","fetch_events":"https://pith.science/api/pith-number/KLYHGDRGKKH66JSP7QB7PB6IFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM/action/storage_attestation","attest_author":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM/action/author_attestation","sign_citation":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM/action/citation_signature","submit_replication":"https://pith.science/pith/KLYHGDRGKKH66JSP7QB7PB6IFM/action/replication_record"}},"created_at":"2026-07-05T08:54:16.386524+00:00","updated_at":"2026-07-05T08:54:16.386524+00:00"}