{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L42VFWM4V4EUS2DSA7RSQFOZQR","short_pith_number":"pith:L42VFWM4","schema_version":"1.0","canonical_sha256":"5f3552d99caf0949687207e32815d98468c0e8487c20c50287d9a251282f0268","source":{"kind":"arxiv","id":"2309.06126","version":1},"attestation_state":"computed","paper":{"title":"AstroLLaMA: Towards Specialized Foundation Models in Astronomy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["astro-ph.CO","astro-ph.GA","astro-ph.HE","cs.CL","cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Alberto Accomazzi, Alyssa Goodman, Charlie O'Neill, David Brodrick, Ernest Perkowski, Ioana Ciuc\\u{a}, Jack Miller, Jason Li, Jesse Cranney, Jill Naiman, Josh Peek, Kartheik Iyer, Kevin Schawinski, Maja Jab{\\l}o\\'nska, Pranav Khetarpal, Sandor Kruk, Sergio J. Rodr\\'iguez M\\'endez, Sharaf Zaman, Thang Bui, Tomasz R\\'o\\.za\\'nski, Tuan Dung Nguyen, UniverseTBD, Yuan-Sen Ting, Ze-Chang Sun","submitted_at":"2023-09-12T11:02:27Z","abstract_excerpt":"Large language models excel in many human-language tasks but often falter in highly specialized domains like scholarly astronomy. To bridge this gap, we introduce AstroLLaMA, a 7-billion-parameter model fine-tuned from LLaMA-2 using over 300,000 astronomy abstracts from arXiv. Optimized for traditional causal language modeling, AstroLLaMA achieves a 30% lower perplexity than Llama-2, showing marked domain adaptation. Our model generates more insightful and scientifically relevant text completions and embedding extraction than state-of-the-arts foundation models despite having significantly few"},"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":"2309.06126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"astro-ph.IM","submitted_at":"2023-09-12T11:02:27Z","cross_cats_sorted":["astro-ph.CO","astro-ph.GA","astro-ph.HE","cs.CL","cs.LG"],"title_canon_sha256":"cad78b40a94b90849063612c3fe877623619b6d1bafc871fe3213524cb0f5c33","abstract_canon_sha256":"03f5bf90b1ea8c780bc4cf347c2f1f8093158d4f54fa68542ffbf5ec324bdc90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:03.870630Z","signature_b64":"NCQ0hymJlVeO8p/G6I+3aAx9grjOIyCC+aVcsC0drSS+l3AZrNBv+NXjcGxlTsyOEdiSbhVzcZ7R4lYAb1kJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f3552d99caf0949687207e32815d98468c0e8487c20c50287d9a251282f0268","last_reissued_at":"2026-07-05T06:50:03.870132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:03.870132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AstroLLaMA: Towards Specialized Foundation Models in Astronomy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["astro-ph.CO","astro-ph.GA","astro-ph.HE","cs.CL","cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Alberto Accomazzi, Alyssa Goodman, Charlie O'Neill, David Brodrick, Ernest Perkowski, Ioana Ciuc\\u{a}, Jack Miller, Jason Li, Jesse Cranney, Jill Naiman, Josh Peek, Kartheik Iyer, Kevin Schawinski, Maja Jab{\\l}o\\'nska, Pranav Khetarpal, Sandor Kruk, Sergio J. Rodr\\'iguez M\\'endez, Sharaf Zaman, Thang Bui, Tomasz R\\'o\\.za\\'nski, Tuan Dung Nguyen, UniverseTBD, Yuan-Sen Ting, Ze-Chang Sun","submitted_at":"2023-09-12T11:02:27Z","abstract_excerpt":"Large language models excel in many human-language tasks but often falter in highly specialized domains like scholarly astronomy. To bridge this gap, we introduce AstroLLaMA, a 7-billion-parameter model fine-tuned from LLaMA-2 using over 300,000 astronomy abstracts from arXiv. Optimized for traditional causal language modeling, AstroLLaMA achieves a 30% lower perplexity than Llama-2, showing marked domain adaptation. Our model generates more insightful and scientifically relevant text completions and embedding extraction than state-of-the-arts foundation models despite having significantly few"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06126","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/2309.06126/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":"2309.06126","created_at":"2026-07-05T06:50:03.870191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06126v1","created_at":"2026-07-05T06:50:03.870191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06126","created_at":"2026-07-05T06:50:03.870191+00:00"},{"alias_kind":"pith_short_12","alias_value":"L42VFWM4V4EU","created_at":"2026-07-05T06:50:03.870191+00:00"},{"alias_kind":"pith_short_16","alias_value":"L42VFWM4V4EUS2DS","created_at":"2026-07-05T06:50:03.870191+00:00"},{"alias_kind":"pith_short_8","alias_value":"L42VFWM4","created_at":"2026-07-05T06:50:03.870191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25039","citing_title":"AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11280","citing_title":"Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR","json":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR.json","graph_json":"https://pith.science/api/pith-number/L42VFWM4V4EUS2DSA7RSQFOZQR/graph.json","events_json":"https://pith.science/api/pith-number/L42VFWM4V4EUS2DSA7RSQFOZQR/events.json","paper":"https://pith.science/paper/L42VFWM4"},"agent_actions":{"view_html":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR","download_json":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR.json","view_paper":"https://pith.science/paper/L42VFWM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06126&json=true","fetch_graph":"https://pith.science/api/pith-number/L42VFWM4V4EUS2DSA7RSQFOZQR/graph.json","fetch_events":"https://pith.science/api/pith-number/L42VFWM4V4EUS2DSA7RSQFOZQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR/action/storage_attestation","attest_author":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR/action/author_attestation","sign_citation":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR/action/citation_signature","submit_replication":"https://pith.science/pith/L42VFWM4V4EUS2DSA7RSQFOZQR/action/replication_record"}},"created_at":"2026-07-05T06:50:03.870191+00:00","updated_at":"2026-07-05T06:50:03.870191+00:00"}