{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CW7LPWCDV2RQNJ3LTAP3VW5RFR","short_pith_number":"pith:CW7LPWCD","schema_version":"1.0","canonical_sha256":"15beb7d843aea306a76b981fbadbb12c50be238bd4e78fccd86b7633edb76f1d","source":{"kind":"arxiv","id":"2409.19750","version":1},"attestation_state":"computed","paper":{"title":"AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"astro-ph.IM","authors_text":"Alberto Accomazzi, Hardik Arora, Rui Pan, Tirthankar Ghosal, Tuan Dung Nguyen, Yuan-Sen Ting","submitted_at":"2024-09-29T16:02:22Z","abstract_excerpt":"Continual pretraining of large language models on domain-specific data has been proposed to enhance performance on downstream tasks. In astronomy, the previous absence of astronomy-focused benchmarks has hindered objective evaluation of these specialized LLM models. Leveraging a recent initiative to curate high-quality astronomical MCQs, this study aims to quantitatively assess specialized LLMs in astronomy. We find that the previously released AstroLLaMA series, based on LLaMA-2-7B, underperforms compared to the base model. We demonstrate that this performance degradation can be partially mit"},"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":"2409.19750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2024-09-29T16:02:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f9f5d8fef5c2e1c499a7c1b6f0c696adfa694982f42ecae6503a3113ce6e55ab","abstract_canon_sha256":"b608fbfe9a1620cef995e951b3222c37aa771a8674be39d5ea88fd033fbf1da5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:21.957418Z","signature_b64":"R69ulzfBe3rwEZtpa3+KvNzILu6eNWIvNBEHLYKNlMJAhIFjYzANLXGD0uPGRjvNQ59mg+S12/RcoqvjZJOxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15beb7d843aea306a76b981fbadbb12c50be238bd4e78fccd86b7633edb76f1d","last_reissued_at":"2026-07-05T09:13:21.956938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:21.956938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"astro-ph.IM","authors_text":"Alberto Accomazzi, Hardik Arora, Rui Pan, Tirthankar Ghosal, Tuan Dung Nguyen, Yuan-Sen Ting","submitted_at":"2024-09-29T16:02:22Z","abstract_excerpt":"Continual pretraining of large language models on domain-specific data has been proposed to enhance performance on downstream tasks. In astronomy, the previous absence of astronomy-focused benchmarks has hindered objective evaluation of these specialized LLM models. Leveraging a recent initiative to curate high-quality astronomical MCQs, this study aims to quantitatively assess specialized LLMs in astronomy. We find that the previously released AstroLLaMA series, based on LLaMA-2-7B, underperforms compared to the base model. We demonstrate that this performance degradation can be partially mit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19750","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/2409.19750/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":"2409.19750","created_at":"2026-07-05T09:13:21.956995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19750v1","created_at":"2026-07-05T09:13:21.956995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19750","created_at":"2026-07-05T09:13:21.956995+00:00"},{"alias_kind":"pith_short_12","alias_value":"CW7LPWCDV2RQ","created_at":"2026-07-05T09:13:21.956995+00:00"},{"alias_kind":"pith_short_16","alias_value":"CW7LPWCDV2RQNJ3L","created_at":"2026-07-05T09:13:21.956995+00:00"},{"alias_kind":"pith_short_8","alias_value":"CW7LPWCD","created_at":"2026-07-05T09:13:21.956995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.06921","citing_title":"Teaching Astronomy with Large Language Models","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR","json":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR.json","graph_json":"https://pith.science/api/pith-number/CW7LPWCDV2RQNJ3LTAP3VW5RFR/graph.json","events_json":"https://pith.science/api/pith-number/CW7LPWCDV2RQNJ3LTAP3VW5RFR/events.json","paper":"https://pith.science/paper/CW7LPWCD"},"agent_actions":{"view_html":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR","download_json":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR.json","view_paper":"https://pith.science/paper/CW7LPWCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19750&json=true","fetch_graph":"https://pith.science/api/pith-number/CW7LPWCDV2RQNJ3LTAP3VW5RFR/graph.json","fetch_events":"https://pith.science/api/pith-number/CW7LPWCDV2RQNJ3LTAP3VW5RFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR/action/storage_attestation","attest_author":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR/action/author_attestation","sign_citation":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR/action/citation_signature","submit_replication":"https://pith.science/pith/CW7LPWCDV2RQNJ3LTAP3VW5RFR/action/replication_record"}},"created_at":"2026-07-05T09:13:21.956995+00:00","updated_at":"2026-07-05T09:13:21.956995+00:00"}