{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UJCY3SCO4DJTVQGJ2COM6SIV26","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":"12c7e8f451aa767bbad4e46fc78411b62b5df7a8ec7c300401a1646383509058","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T01:35:47Z","title_canon_sha256":"d03ad83509ccc3f9612d6d282122f8d2953b4e6830df581c719b243682eb54ce"},"schema_version":"1.0","source":{"id":"2412.14436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14436","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14436v1","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14436","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"UJCY3SCO4DJT","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"UJCY3SCO4DJTVQGJ","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"UJCY3SCO","created_at":"2026-07-05T09:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:c55cc43eb4511a8811e467477b195f372df88d8161c2d74378d7d9624c4c81e5","target":"graph","created_at":"2026-07-05T09:51:47Z","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/2412.14436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language modeling demonstrate the need for high-quality domain-specific training data, especially for tasks that require specialized knowledge. General-purpose models, while versatile, often lack the depth needed for expert-level tasks because of limited domain-specific information. Domain adaptation training can enhance these models, but it demands substantial, high-quality data. To address this, we propose ORBIT, a cost-efficient methodology for curating massive, high-quality domain-specific datasets from noisy web sources, tailored for training specialist large language m","authors_text":"ChengXiang Zhai, Eric Modesitt, Ke Yang, Spencer Hulsey, Volodymyr Kindratenko","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T01:35:47Z","title":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14436","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":"sha256:6b65b06054e2cc416aea5282bf4b23100543d21dd88b9a189b0a5a45b904e315","target":"record","created_at":"2026-07-05T09:51:47Z","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":"12c7e8f451aa767bbad4e46fc78411b62b5df7a8ec7c300401a1646383509058","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T01:35:47Z","title_canon_sha256":"d03ad83509ccc3f9612d6d282122f8d2953b4e6830df581c719b243682eb54ce"},"schema_version":"1.0","source":{"id":"2412.14436","kind":"arxiv","version":1}},"canonical_sha256":"a2458dc84ee0d33ac0c9d09ccf4915d78c4555ab539f5f7399351f570351085b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2458dc84ee0d33ac0c9d09ccf4915d78c4555ab539f5f7399351f570351085b","first_computed_at":"2026-07-05T09:51:47.103155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:47.103155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uA4jPju//vCir/4u1dFNX3dR6zbSDoNxwWMc4XLxeADhbAJtrBBFtqrNJwmrX+mrDATy/hDN4N4vsE5xA2wyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:47.103696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b65b06054e2cc416aea5282bf4b23100543d21dd88b9a189b0a5a45b904e315","sha256:c55cc43eb4511a8811e467477b195f372df88d8161c2d74378d7d9624c4c81e5"],"state_sha256":"bbb0723448ef6b7db265c9572c5e7536acabc63cc30f907a57f152799e2ac8ae"}