{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UJCY3SCO4DJTVQGJ2COM6SIV26","short_pith_number":"pith:UJCY3SCO","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"},"canonical_sha256":"a2458dc84ee0d33ac0c9d09ccf4915d78c4555ab539f5f7399351f570351085b","source":{"kind":"arxiv","id":"2412.14436","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UJCY3SCO4DJTVQGJ2COM6SIV26","target":"record","payload":{"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"},"canonical_sha256":"a2458dc84ee0d33ac0c9d09ccf4915d78c4555ab539f5f7399351f570351085b","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"},"source_kind":"arxiv","source_id":"2412.14436","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":"2026-07-05T09:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKWK12M9fhtVwC0Vsk2pujYgtPZ2CRb3tWtOCjAZVsFRoP2zo7/5Y0hTx0WaWP2D66clS0NAgUDoH2HX+vFEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:09:53.377920Z"},"content_sha256":"6b65b06054e2cc416aea5282bf4b23100543d21dd88b9a189b0a5a45b904e315","schema_version":"1.0","event_id":"sha256:6b65b06054e2cc416aea5282bf4b23100543d21dd88b9a189b0a5a45b904e315"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UJCY3SCO4DJTVQGJ2COM6SIV26","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7YucQWVyxGCW9gcHmyLMZJKo0QmNhViGjlScbgKw3klnlAlGAKHGYrMGt+i4GY5wMjLyNgwmDye49S0m6FplCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:09:53.378478Z"},"content_sha256":"c55cc43eb4511a8811e467477b195f372df88d8161c2d74378d7d9624c4c81e5","schema_version":"1.0","event_id":"sha256:c55cc43eb4511a8811e467477b195f372df88d8161c2d74378d7d9624c4c81e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/bundle.json","state_url":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/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":"2026-08-11T21:09:53Z","links":{"resolver":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26","bundle":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/bundle.json","state":"https://pith.science/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJCY3SCO4DJTVQGJ2COM6SIV26/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B3iS7y4QknhPiPlzGbWhbbk5YB7/wsHaX6veSdMz6SB2wLGK1rI4DT22oryYj60KziRfFYq5VqWQ/ioNuLeXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:09:53.383315Z","bundle_sha256":"b4bd680b6b033221c22641cdf68b1fb18e9537b52579dabfc913043874b029fa"}}