{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RZS6LB5VPEFTSDARPZGZQXJYJF","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":"9350abb51b6b4f813dcb541e8b23466f831c114432dd57d6ffeb33f128a3869b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T18:21:47Z","title_canon_sha256":"6c3ec579fa9bf5f54ff2b862399f79bfde1107dd7b25db5c59216667a3331ec5"},"schema_version":"1.0","source":{"id":"2505.04723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04723","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04723v1","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04723","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"pith_short_12","alias_value":"RZS6LB5VPEFT","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"pith_short_16","alias_value":"RZS6LB5VPEFTSDAR","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"pith_short_8","alias_value":"RZS6LB5V","created_at":"2026-07-05T11:00:12Z"}],"graph_snapshots":[{"event_id":"sha256:ff7e2bde6c11d15a642503de6dc830654536d6083594714f0f0538cbab1861ab","target":"graph","created_at":"2026-07-05T11:00:12Z","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/2505.04723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingyang Deng, Jinwen Ma, Jo-Ku Cheng, Ran Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04723","kind":"arxiv","version":1},"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":"sha256:61933356e0a5c85f98a55f5511317d38df5594ecf74573db8e2c578408bf2a4b","target":"record","created_at":"2026-07-05T11:00:12Z","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":"9350abb51b6b4f813dcb541e8b23466f831c114432dd57d6ffeb33f128a3869b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T18:21:47Z","title_canon_sha256":"6c3ec579fa9bf5f54ff2b862399f79bfde1107dd7b25db5c59216667a3331ec5"},"schema_version":"1.0","source":{"id":"2505.04723","kind":"arxiv","version":1}},"canonical_sha256":"8e65e587b5790b390c117e4d985d38496943fd618784db47e1b5e486a590d924","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e65e587b5790b390c117e4d985d38496943fd618784db47e1b5e486a590d924","first_computed_at":"2026-07-05T11:00:12.706233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:12.706233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jokrePEXL0hkYPxHMIZWJpMKYh23SXdCRauNnvmNiDpIVd/YHb9Gv7To26F616xjzX0ecRg9JBBWsvVIAqOVCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:12.706927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61933356e0a5c85f98a55f5511317d38df5594ecf74573db8e2c578408bf2a4b","sha256:ff7e2bde6c11d15a642503de6dc830654536d6083594714f0f0538cbab1861ab"],"state_sha256":"d06a33513639023f588f1f37c9ec2ac4ccee1ab78c6a839fa67e6374c62b6afa"}