{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UJCY3SCO4DJTVQGJ2COM6SIV26","short_pith_number":"pith:UJCY3SCO","schema_version":"1.0","canonical_sha256":"a2458dc84ee0d33ac0c9d09ccf4915d78c4555ab539f5f7399351f570351085b","source":{"kind":"arxiv","id":"2412.14436","version":1},"attestation_state":"computed","paper":{"title":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"ChengXiang Zhai, Eric Modesitt, Ke Yang, Spencer Hulsey, Volodymyr Kindratenko","submitted_at":"2024-12-19T01:35:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.14436","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T01:35:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d03ad83509ccc3f9612d6d282122f8d2953b4e6830df581c719b243682eb54ce","abstract_canon_sha256":"12c7e8f451aa767bbad4e46fc78411b62b5df7a8ec7c300401a1646383509058"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:47.103696Z","signature_b64":"uA4jPju//vCir/4u1dFNX3dR6zbSDoNxwWMc4XLxeADhbAJtrBBFtqrNJwmrX+mrDATy/hDN4N4vsE5xA2wyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2458dc84ee0d33ac0c9d09ccf4915d78c4555ab539f5f7399351f570351085b","last_reissued_at":"2026-07-05T09:51:47.103155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:47.103155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"ChengXiang Zhai, Eric Modesitt, Ke Yang, Spencer Hulsey, Volodymyr Kindratenko","submitted_at":"2024-12-19T01:35:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14436","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/2412.14436/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.14436","created_at":"2026-07-05T09:51:47.103226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14436v1","created_at":"2026-07-05T09:51:47.103226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14436","created_at":"2026-07-05T09:51:47.103226+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJCY3SCO4DJT","created_at":"2026-07-05T09:51:47.103226+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJCY3SCO4DJTVQGJ","created_at":"2026-07-05T09:51:47.103226+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJCY3SCO","created_at":"2026-07-05T09:51:47.103226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26","json":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26.json","graph_json":"https://pith.science/api/pith-number/UJCY3SCO4DJTVQGJ2COM6SIV26/graph.json","events_json":"https://pith.science/api/pith-number/UJCY3SCO4DJTVQGJ2COM6SIV26/events.json","paper":"https://pith.science/paper/UJCY3SCO"},"agent_actions":{"view_html":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26","download_json":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26.json","view_paper":"https://pith.science/paper/UJCY3SCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14436&json=true","fetch_graph":"https://pith.science/api/pith-number/UJCY3SCO4DJTVQGJ2COM6SIV26/graph.json","fetch_events":"https://pith.science/api/pith-number/UJCY3SCO4DJTVQGJ2COM6SIV26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/action/storage_attestation","attest_author":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/action/author_attestation","sign_citation":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/action/citation_signature","submit_replication":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/action/replication_record"}},"created_at":"2026-07-05T09:51:47.103226+00:00","updated_at":"2026-07-05T09:51:47.103226+00:00"}