{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VWIHSY4GN6BY6ZEKLEWBKRT4HQ","short_pith_number":"pith:VWIHSY4G","schema_version":"1.0","canonical_sha256":"ad907963866f838f648a592c15467c3c396aa5013417d5b2f9a3eaa6660d86ec","source":{"kind":"arxiv","id":"2407.10804","version":1},"attestation_state":"computed","paper":{"title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinhao Jiang, Ji-Rong Wen, Junyi Li, Tao Zhang, Wayne Xin Zhao, Yang Song","submitted_at":"2024-07-15T15:20:13Z","abstract_excerpt":"Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate knowledge memorization, followed by training to apply this knowledge following human instructions and preferences. However, this method may result in inefficient knowledge memorization due to a lack of awareness of knowledge utilization and imposes substantial demands on LLMs to simultaneously learn knowledge utilization and format alignment with limited trainin"},"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":"2407.10804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:20:13Z","cross_cats_sorted":[],"title_canon_sha256":"de4828c1ae062aed10582383496bbb61620eca4a7cdba936e19a3fbfdfbaa8d2","abstract_canon_sha256":"fe1162026bc9647c01d65eccdea2ab40e64382587181f02b6d24b7d68d6c6e06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:04.410235Z","signature_b64":"9XIcqEu5HAglPxxjcrKLKdnUW3EcJXb/Yr0ujCgXHtfijtcgwFZNBaq4RbK4oHD+4SUtHs7KE/UaHt3/OJhpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad907963866f838f648a592c15467c3c396aa5013417d5b2f9a3eaa6660d86ec","last_reissued_at":"2026-07-05T08:44:04.409759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:04.409759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinhao Jiang, Ji-Rong Wen, Junyi Li, Tao Zhang, Wayne Xin Zhao, Yang Song","submitted_at":"2024-07-15T15:20:13Z","abstract_excerpt":"Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate knowledge memorization, followed by training to apply this knowledge following human instructions and preferences. However, this method may result in inefficient knowledge memorization due to a lack of awareness of knowledge utilization and imposes substantial demands on LLMs to simultaneously learn knowledge utilization and format alignment with limited trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10804","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/2407.10804/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":"2407.10804","created_at":"2026-07-05T08:44:04.409818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10804v1","created_at":"2026-07-05T08:44:04.409818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10804","created_at":"2026-07-05T08:44:04.409818+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWIHSY4GN6BY","created_at":"2026-07-05T08:44:04.409818+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWIHSY4GN6BY6ZEK","created_at":"2026-07-05T08:44:04.409818+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWIHSY4G","created_at":"2026-07-05T08:44:04.409818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07365","citing_title":"LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ","json":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ.json","graph_json":"https://pith.science/api/pith-number/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/graph.json","events_json":"https://pith.science/api/pith-number/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/events.json","paper":"https://pith.science/paper/VWIHSY4G"},"agent_actions":{"view_html":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ","download_json":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ.json","view_paper":"https://pith.science/paper/VWIHSY4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10804&json=true","fetch_graph":"https://pith.science/api/pith-number/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/action/storage_attestation","attest_author":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/action/author_attestation","sign_citation":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/action/citation_signature","submit_replication":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/action/replication_record"}},"created_at":"2026-07-05T08:44:04.409818+00:00","updated_at":"2026-07-05T08:44:04.409818+00:00"}