{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RZS6LB5VPEFTSDARPZGZQXJYJF","short_pith_number":"pith:RZS6LB5V","schema_version":"1.0","canonical_sha256":"8e65e587b5790b390c117e4d985d38496943fd618784db47e1b5e486a590d924","source":{"kind":"arxiv","id":"2505.04723","version":1},"attestation_state":"computed","paper":{"title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingyang Deng, Jinwen Ma, Jo-Ku Cheng, Ran Chen","submitted_at":"2025-05-07T18:21:47Z","abstract_excerpt":"This study addresses key challenges in developing domain-specific large language models (LLMs) for Chinese state-owned assets and enterprises (SOAEs), where current approaches face three limitations: 1) constrained model capacity that limits knowledge integration and cross-task adaptability; 2) excessive reliance on domain-specific supervised fine-tuning (SFT) data, which neglects the broader applicability of general language patterns; and 3) inefficient inference acceleration for large models processing long contexts. In this work, we propose SOAEsV2-7B/72B, a specialized LLM series developed"},"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":"2505.04723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T18:21:47Z","cross_cats_sorted":[],"title_canon_sha256":"6c3ec579fa9bf5f54ff2b862399f79bfde1107dd7b25db5c59216667a3331ec5","abstract_canon_sha256":"9350abb51b6b4f813dcb541e8b23466f831c114432dd57d6ffeb33f128a3869b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:12.706927Z","signature_b64":"jokrePEXL0hkYPxHMIZWJpMKYh23SXdCRauNnvmNiDpIVd/YHb9Gv7To26F616xjzX0ecRg9JBBWsvVIAqOVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e65e587b5790b390c117e4d985d38496943fd618784db47e1b5e486a590d924","last_reissued_at":"2026-07-05T11:00:12.706233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:12.706233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingyang Deng, Jinwen Ma, Jo-Ku Cheng, Ran Chen","submitted_at":"2025-05-07T18:21:47Z","abstract_excerpt":"This study addresses key challenges in developing domain-specific large language models (LLMs) for Chinese state-owned assets and enterprises (SOAEs), where current approaches face three limitations: 1) constrained model capacity that limits knowledge integration and cross-task adaptability; 2) excessive reliance on domain-specific supervised fine-tuning (SFT) data, which neglects the broader applicability of general language patterns; and 3) inefficient inference acceleration for large models processing long contexts. In this work, we propose SOAEsV2-7B/72B, a specialized LLM series developed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04723","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/2505.04723/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":"2505.04723","created_at":"2026-07-05T11:00:12.706394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04723v1","created_at":"2026-07-05T11:00:12.706394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04723","created_at":"2026-07-05T11:00:12.706394+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZS6LB5VPEFT","created_at":"2026-07-05T11:00:12.706394+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZS6LB5VPEFTSDAR","created_at":"2026-07-05T11:00:12.706394+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZS6LB5V","created_at":"2026-07-05T11:00:12.706394+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/RZS6LB5VPEFTSDARPZGZQXJYJF","json":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF.json","graph_json":"https://pith.science/api/pith-number/RZS6LB5VPEFTSDARPZGZQXJYJF/graph.json","events_json":"https://pith.science/api/pith-number/RZS6LB5VPEFTSDARPZGZQXJYJF/events.json","paper":"https://pith.science/paper/RZS6LB5V"},"agent_actions":{"view_html":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF","download_json":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF.json","view_paper":"https://pith.science/paper/RZS6LB5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04723&json=true","fetch_graph":"https://pith.science/api/pith-number/RZS6LB5VPEFTSDARPZGZQXJYJF/graph.json","fetch_events":"https://pith.science/api/pith-number/RZS6LB5VPEFTSDARPZGZQXJYJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF/action/storage_attestation","attest_author":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF/action/author_attestation","sign_citation":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF/action/citation_signature","submit_replication":"https://pith.science/pith/RZS6LB5VPEFTSDARPZGZQXJYJF/action/replication_record"}},"created_at":"2026-07-05T11:00:12.706394+00:00","updated_at":"2026-07-05T11:00:12.706394+00:00"}