{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PTVABYERW6EMVCA7PAZMF5HARO","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":"0c497d0ab55d017382ede6a645f8595106bcf01a6be1f2ac5ba403f88d093c0c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T14:58:11Z","title_canon_sha256":"b1ae898fbd85cdffe64d7888a4e37b7df9c86f0c0c7de88f3973a9650ac7a299"},"schema_version":"1.0","source":{"id":"2406.16694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16694","created_at":"2026-07-05T08:36:02Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16694v1","created_at":"2026-07-05T08:36:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16694","created_at":"2026-07-05T08:36:02Z"},{"alias_kind":"pith_short_12","alias_value":"PTVABYERW6EM","created_at":"2026-07-05T08:36:02Z"},{"alias_kind":"pith_short_16","alias_value":"PTVABYERW6EMVCA7","created_at":"2026-07-05T08:36:02Z"},{"alias_kind":"pith_short_8","alias_value":"PTVABYER","created_at":"2026-07-05T08:36:02Z"}],"graph_snapshots":[{"event_id":"sha256:975a4bdc194503aeaca0139a69d6e0c51c5432a09219ecd565eb8272fb4a6b0d","target":"graph","created_at":"2026-07-05T08:36:02Z","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/2406.16694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown superior performance in various applications and fields. To achieve better performance on specialized domains such as law and advertisement, LLMs are often continue pre-trained on in-domain data. However, existing approaches suffer from two major issues. First, in-domain data are scarce compared with general domain-agnostic data. Second, data used for continual pre-training are not task-aware, such that they may not be helpful to downstream applications. We propose TRAIT, a task-oriented in-domain data augmentation framework. Our framework is divided int","authors_text":"Jian Jiao, Qiang Lou, Shao-Lun Huang, Simiao Zuo, Xiao Liang, Xinyu Hu, Yeyun Gong, Yi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T14:58:11Z","title":"Task Oriented In-Domain Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16694","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:a6b62890d88899651ac4e9646e24d0b6457b261838d0a4a63c7c18fd1ca57a16","target":"record","created_at":"2026-07-05T08:36:02Z","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":"0c497d0ab55d017382ede6a645f8595106bcf01a6be1f2ac5ba403f88d093c0c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T14:58:11Z","title_canon_sha256":"b1ae898fbd85cdffe64d7888a4e37b7df9c86f0c0c7de88f3973a9650ac7a299"},"schema_version":"1.0","source":{"id":"2406.16694","kind":"arxiv","version":1}},"canonical_sha256":"7cea00e091b788ca881f7832c2f4e08b91324f3290cbe97fb539a2a49596ad0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cea00e091b788ca881f7832c2f4e08b91324f3290cbe97fb539a2a49596ad0e","first_computed_at":"2026-07-05T08:36:02.323996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:02.323996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yMmZn/UXMWBqYXbGm34QLf3FFIA5L9flh43DqNtU3JyQQh15HaeFNot+cIgd1GnXRPEzGZ5biszBxcYOiDOlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:02.324464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6b62890d88899651ac4e9646e24d0b6457b261838d0a4a63c7c18fd1ca57a16","sha256:975a4bdc194503aeaca0139a69d6e0c51c5432a09219ecd565eb8272fb4a6b0d"],"state_sha256":"3a738dd704033fcc5c9f9c6c772bc030b349fe53a426026a8eee5efcc1767bb4"}