{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VWIHSY4GN6BY6ZEKLEWBKRT4HQ","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":"fe1162026bc9647c01d65eccdea2ab40e64382587181f02b6d24b7d68d6c6e06","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:20:13Z","title_canon_sha256":"de4828c1ae062aed10582383496bbb61620eca4a7cdba936e19a3fbfdfbaa8d2"},"schema_version":"1.0","source":{"id":"2407.10804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10804","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10804v1","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10804","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"VWIHSY4GN6BY","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"VWIHSY4GN6BY6ZEK","created_at":"2026-07-05T08:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"VWIHSY4G","created_at":"2026-07-05T08:44:04Z"}],"graph_snapshots":[{"event_id":"sha256:aff7e4df4cc1d35815494243bccb72f3c034f490b9e6cd352586fb172027cfcc","target":"graph","created_at":"2026-07-05T08:44:04Z","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/2407.10804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jinhao Jiang, Ji-Rong Wen, Junyi Li, Tao Zhang, Wayne Xin Zhao, Yang Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:20:13Z","title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10804","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:dc248382e265e92537aea9ce44715dd4d0004d7bfd6f2263b218695d45708943","target":"record","created_at":"2026-07-05T08:44:04Z","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":"fe1162026bc9647c01d65eccdea2ab40e64382587181f02b6d24b7d68d6c6e06","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T15:20:13Z","title_canon_sha256":"de4828c1ae062aed10582383496bbb61620eca4a7cdba936e19a3fbfdfbaa8d2"},"schema_version":"1.0","source":{"id":"2407.10804","kind":"arxiv","version":1}},"canonical_sha256":"ad907963866f838f648a592c15467c3c396aa5013417d5b2f9a3eaa6660d86ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad907963866f838f648a592c15467c3c396aa5013417d5b2f9a3eaa6660d86ec","first_computed_at":"2026-07-05T08:44:04.409759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:04.409759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9XIcqEu5HAglPxxjcrKLKdnUW3EcJXb/Yr0ujCgXHtfijtcgwFZNBaq4RbK4oHD+4SUtHs7KE/UaHt3/OJhpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:04.410235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc248382e265e92537aea9ce44715dd4d0004d7bfd6f2263b218695d45708943","sha256:aff7e4df4cc1d35815494243bccb72f3c034f490b9e6cd352586fb172027cfcc"],"state_sha256":"5063c9e4247d9274294f45012c2d4d010d267ff7bc93e9f01f4acb6b49f3a489"}