{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PTVABYERW6EMVCA7PAZMF5HARO","short_pith_number":"pith:PTVABYER","canonical_record":{"source":{"id":"2406.16694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T14:58:11Z","cross_cats_sorted":[],"title_canon_sha256":"b1ae898fbd85cdffe64d7888a4e37b7df9c86f0c0c7de88f3973a9650ac7a299","abstract_canon_sha256":"0c497d0ab55d017382ede6a645f8595106bcf01a6be1f2ac5ba403f88d093c0c"},"schema_version":"1.0"},"canonical_sha256":"7cea00e091b788ca881f7832c2f4e08b91324f3290cbe97fb539a2a49596ad0e","source":{"kind":"arxiv","id":"2406.16694","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PTVABYERW6EMVCA7PAZMF5HARO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T14:58:11Z","cross_cats_sorted":[],"title_canon_sha256":"b1ae898fbd85cdffe64d7888a4e37b7df9c86f0c0c7de88f3973a9650ac7a299","abstract_canon_sha256":"0c497d0ab55d017382ede6a645f8595106bcf01a6be1f2ac5ba403f88d093c0c"},"schema_version":"1.0"},"canonical_sha256":"7cea00e091b788ca881f7832c2f4e08b91324f3290cbe97fb539a2a49596ad0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:02.324464Z","signature_b64":"yMmZn/UXMWBqYXbGm34QLf3FFIA5L9flh43DqNtU3JyQQh15HaeFNot+cIgd1GnXRPEzGZ5biszBxcYOiDOlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cea00e091b788ca881f7832c2f4e08b91324f3290cbe97fb539a2a49596ad0e","last_reissued_at":"2026-07-05T08:36:02.323996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:02.323996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16694","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":"2026-07-05T08:36:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s9MT1oZHRagX75E91MPzu047i8Rg1RpTu/ey0YdAZ/n2S4Z5e45rvOeD94i42KPODt5pmS/pSgiRocOOvtubBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:05:58.775100Z"},"content_sha256":"a6b62890d88899651ac4e9646e24d0b6457b261838d0a4a63c7c18fd1ca57a16","schema_version":"1.0","event_id":"sha256:a6b62890d88899651ac4e9646e24d0b6457b261838d0a4a63c7c18fd1ca57a16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PTVABYERW6EMVCA7PAZMF5HARO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task Oriented In-Domain Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian Jiao, Qiang Lou, Shao-Lun Huang, Simiao Zuo, Xiao Liang, Xinyu Hu, Yeyun Gong, Yi Liu","submitted_at":"2024-06-24T14:58:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16694","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/2406.16694/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":"2026-07-05T08:36:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fbSTbCVlNNRszvdhZVOJLsODx6ned4DMYwRvg10Rgd20aoCx1F9qr2rdrLPJ+iyAhr3KGBPM0z2a9wDUSgWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:05:58.775480Z"},"content_sha256":"975a4bdc194503aeaca0139a69d6e0c51c5432a09219ecd565eb8272fb4a6b0d","schema_version":"1.0","event_id":"sha256:975a4bdc194503aeaca0139a69d6e0c51c5432a09219ecd565eb8272fb4a6b0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTVABYERW6EMVCA7PAZMF5HARO/bundle.json","state_url":"https://pith.science/pith/PTVABYERW6EMVCA7PAZMF5HARO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTVABYERW6EMVCA7PAZMF5HARO/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":"2026-08-03T17:05:58Z","links":{"resolver":"https://pith.science/pith/PTVABYERW6EMVCA7PAZMF5HARO","bundle":"https://pith.science/pith/PTVABYERW6EMVCA7PAZMF5HARO/bundle.json","state":"https://pith.science/pith/PTVABYERW6EMVCA7PAZMF5HARO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTVABYERW6EMVCA7PAZMF5HARO/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQ4W2qk/MXwzyLAS5Rpv7+Gt9TZE0k+O2BZq/djGWsYZpG+Ifeg2GtdBcR3Mso2tWijoT6cf8eniwlem/o5YDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:05:58.777693Z","bundle_sha256":"a11f4485c6d5ac89f20e100d411d59fbe99c89f559f51a9b18b6312b332b2971"}}