{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YWS35UJNFQ4J2HMB7R5MT5WURW","short_pith_number":"pith:YWS35UJN","schema_version":"1.0","canonical_sha256":"c5a5bed12d2c389d1d81fc7ac9f6d48d9b34cd959d66ec04f27ed28d445af9e1","source":{"kind":"arxiv","id":"2508.01317","version":2},"attestation_state":"computed","paper":{"title":"LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Ren, Chengying Tu, Hongfei Yan, Jingang Wang, Rongxiang Weng, Xuemiao Zhang, Xunliang Cai","submitted_at":"2025-08-02T11:09:06Z","abstract_excerpt":"The advancement of large language models (LLMs) struggles with the scarcity of high-quality, diverse training data. To address this limitation, we propose LinkSyn, a novel knowledge point (KP) graph-based synthesis framework that enables flexible control over discipline and difficulty distributions while balancing KP coverage and popularity. LinkSyn extracts KPs from question-answering (QA) seed data and constructs a KP graph to synthesize diverse QA data from multiple seeds strongly linked by KPs and sampled from graph walks. Specifically, LinkSyn incorporates (1) a knowledge distribution val"},"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":"2508.01317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-02T11:09:06Z","cross_cats_sorted":[],"title_canon_sha256":"d4ee738da231ca5f6301ad16b199c87d10db404f939d7c5efa57bfb394eee93f","abstract_canon_sha256":"f57634c607d6e9003661a698c78883088a9986da8039b8496ab1c18dc027a194"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:12.414335Z","signature_b64":"G8dIoNez7bbOdUe7+EbRkNYF7n1Oo9tqZhiqHcAVUkRWWRnbxMktYUydgPiY1WzrUUeTk4WnBiY1Ea1YqFroCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5a5bed12d2c389d1d81fc7ac9f6d48d9b34cd959d66ec04f27ed28d445af9e1","last_reissued_at":"2026-07-05T11:49:12.413834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:12.413834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Ren, Chengying Tu, Hongfei Yan, Jingang Wang, Rongxiang Weng, Xuemiao Zhang, Xunliang Cai","submitted_at":"2025-08-02T11:09:06Z","abstract_excerpt":"The advancement of large language models (LLMs) struggles with the scarcity of high-quality, diverse training data. To address this limitation, we propose LinkSyn, a novel knowledge point (KP) graph-based synthesis framework that enables flexible control over discipline and difficulty distributions while balancing KP coverage and popularity. LinkSyn extracts KPs from question-answering (QA) seed data and constructs a KP graph to synthesize diverse QA data from multiple seeds strongly linked by KPs and sampled from graph walks. Specifically, LinkSyn incorporates (1) a knowledge distribution val"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01317","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/2508.01317/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":"2508.01317","created_at":"2026-07-05T11:49:12.413894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01317v2","created_at":"2026-07-05T11:49:12.413894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01317","created_at":"2026-07-05T11:49:12.413894+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWS35UJNFQ4J","created_at":"2026-07-05T11:49:12.413894+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWS35UJNFQ4J2HMB","created_at":"2026-07-05T11:49:12.413894+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWS35UJN","created_at":"2026-07-05T11:49:12.413894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW","json":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW.json","graph_json":"https://pith.science/api/pith-number/YWS35UJNFQ4J2HMB7R5MT5WURW/graph.json","events_json":"https://pith.science/api/pith-number/YWS35UJNFQ4J2HMB7R5MT5WURW/events.json","paper":"https://pith.science/paper/YWS35UJN"},"agent_actions":{"view_html":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW","download_json":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW.json","view_paper":"https://pith.science/paper/YWS35UJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01317&json=true","fetch_graph":"https://pith.science/api/pith-number/YWS35UJNFQ4J2HMB7R5MT5WURW/graph.json","fetch_events":"https://pith.science/api/pith-number/YWS35UJNFQ4J2HMB7R5MT5WURW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW/action/storage_attestation","attest_author":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW/action/author_attestation","sign_citation":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW/action/citation_signature","submit_replication":"https://pith.science/pith/YWS35UJNFQ4J2HMB7R5MT5WURW/action/replication_record"}},"created_at":"2026-07-05T11:49:12.413894+00:00","updated_at":"2026-07-05T11:49:12.413894+00:00"}