{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M2BSHJ2HZI7GE5FXA2IIYFYDCH","short_pith_number":"pith:M2BSHJ2H","schema_version":"1.0","canonical_sha256":"668323a747ca3e6274b706908c170311ec84ef310c0921d901c0fb0318dd605d","source":{"kind":"arxiv","id":"2605.30039","version":1},"attestation_state":"computed","paper":{"title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hang Yu, Jianguo Li, Jianwei Yin, Peiyu Liu, Peng Di, Tengfei Ma, Tong Ye, Wenhai Wang, Xuhong Zhang","submitted_at":"2026-05-28T14:57:02Z","abstract_excerpt":"Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can achieve strong performance in specific domains through fine-tuning on domain-specific data. However, acquiring high-quality data for target domains remains a significant challenge. Existing data synthesis approaches follow a deductive paradigm, heavily relying on explicit domain descriptions expressed in natural language and careful prompt engineering, limiting their applicability in real-world scenarios where domains are difficult to describe or formally articulate. In this work, we tackle the "},"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":"2605.30039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T14:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"cf581d4c56731511d241328cd332144eadd01b78593c43b86c51258f97673df2","abstract_canon_sha256":"7d938a4c3a8f1d76587d9564d5e37d17dc7498a99c8a9d26edeca15580807b84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:08.071608Z","signature_b64":"saIGv+SalZjkjmD1+wcTb8o5wq9l7ca9C7AYmuBm7RAQZDQ7ttbvRorrIaKH3bJkbPx5RJifZFZZ3+NeuJk0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"668323a747ca3e6274b706908c170311ec84ef310c0921d901c0fb0318dd605d","last_reissued_at":"2026-05-29T02:06:08.071115Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:08.071115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hang Yu, Jianguo Li, Jianwei Yin, Peiyu Liu, Peng Di, Tengfei Ma, Tong Ye, Wenhai Wang, Xuhong Zhang","submitted_at":"2026-05-28T14:57:02Z","abstract_excerpt":"Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can achieve strong performance in specific domains through fine-tuning on domain-specific data. However, acquiring high-quality data for target domains remains a significant challenge. Existing data synthesis approaches follow a deductive paradigm, heavily relying on explicit domain descriptions expressed in natural language and careful prompt engineering, limiting their applicability in real-world scenarios where domains are difficult to describe or formally articulate. In this work, we tackle the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30039","kind":"arxiv","version":1},"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/2605.30039/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":"2605.30039","created_at":"2026-05-29T02:06:08.071183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30039v1","created_at":"2026-05-29T02:06:08.071183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30039","created_at":"2026-05-29T02:06:08.071183+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2BSHJ2HZI7G","created_at":"2026-05-29T02:06:08.071183+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2BSHJ2HZI7GE5FX","created_at":"2026-05-29T02:06:08.071183+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2BSHJ2H","created_at":"2026-05-29T02:06:08.071183+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/M2BSHJ2HZI7GE5FXA2IIYFYDCH","json":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH.json","graph_json":"https://pith.science/api/pith-number/M2BSHJ2HZI7GE5FXA2IIYFYDCH/graph.json","events_json":"https://pith.science/api/pith-number/M2BSHJ2HZI7GE5FXA2IIYFYDCH/events.json","paper":"https://pith.science/paper/M2BSHJ2H"},"agent_actions":{"view_html":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH","download_json":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH.json","view_paper":"https://pith.science/paper/M2BSHJ2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30039&json=true","fetch_graph":"https://pith.science/api/pith-number/M2BSHJ2HZI7GE5FXA2IIYFYDCH/graph.json","fetch_events":"https://pith.science/api/pith-number/M2BSHJ2HZI7GE5FXA2IIYFYDCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/action/storage_attestation","attest_author":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/action/author_attestation","sign_citation":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/action/citation_signature","submit_replication":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/action/replication_record"}},"created_at":"2026-05-29T02:06:08.071183+00:00","updated_at":"2026-05-29T02:06:08.071183+00:00"}