{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VWIHSY4GN6BY6ZEKLEWBKRT4HQ","short_pith_number":"pith:VWIHSY4G","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"},"canonical_sha256":"ad907963866f838f648a592c15467c3c396aa5013417d5b2f9a3eaa6660d86ec","source":{"kind":"arxiv","id":"2407.10804","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VWIHSY4GN6BY6ZEKLEWBKRT4HQ","target":"record","payload":{"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"},"canonical_sha256":"ad907963866f838f648a592c15467c3c396aa5013417d5b2f9a3eaa6660d86ec","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"},"source_kind":"arxiv","source_id":"2407.10804","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BDu7EULycfpGsSQfIznk1lZ3h8gcrUs7gaIYnK95edskQLwD81j1TABEsDumb8mEm881zgEmt70m/0PmpSBtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:46:25.716098Z"},"content_sha256":"dc248382e265e92537aea9ce44715dd4d0004d7bfd6f2263b218695d45708943","schema_version":"1.0","event_id":"sha256:dc248382e265e92537aea9ce44715dd4d0004d7bfd6f2263b218695d45708943"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VWIHSY4GN6BY6ZEKLEWBKRT4HQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmLaiexyeKkbGpldlefGkxUvYwqpaNEf9sN1EFr5xDNtgBUtdwIgfjat9+6NUqE3rUJIMAVJCCP7sbhkqz/KAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:46:25.716612Z"},"content_sha256":"aff7e4df4cc1d35815494243bccb72f3c034f490b9e6cd352586fb172027cfcc","schema_version":"1.0","event_id":"sha256:aff7e4df4cc1d35815494243bccb72f3c034f490b9e6cd352586fb172027cfcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/bundle.json","state_url":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T05:46:25Z","links":{"resolver":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ","bundle":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/bundle.json","state":"https://pith.science/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWIHSY4GN6BY6ZEKLEWBKRT4HQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VmPXmC5yTiaKSrUq7QtQ2i4nOYkwlaha5jTiBo3Mvlab+tGZ/L0FGlntqvgrTzsI70kfiVqEiGWUzYQVYPHgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:46:25.721088Z","bundle_sha256":"28d5f89ef31100dd91b9dbffad1f50472794d38ce67064de97bed71284f48b1b"}}