{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LS7GBZ5OO7IB26NEZNOGFXJDOD","short_pith_number":"pith:LS7GBZ5O","schema_version":"1.0","canonical_sha256":"5cbe60e7ae77d01d79a4cb5c62dd2370ce31a6b4f4a8b5091a6458d57f5a800a","source":{"kind":"arxiv","id":"2503.17604","version":4},"attestation_state":"computed","paper":{"title":"OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aastha Jhunjhunwala, Adam Atanas, Joah Han, Kai Liu, Kang Xu, Md Amirul Islam, Robert Clark, Rucha Apte, Vignesh Prabhakar, Yao-Ting Wang, Zihan Wang","submitted_at":"2025-03-22T01:18:59Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable potential in advancing scientific knowledge and addressing complex challenges. In this work, we introduce OmniScience, a specialized large reasoning model for general science, developed through three key components: (1) domain adaptive pretraining on a carefully curated corpus of scientific literature, (2) instruction tuning on a specialized dataset to guide the model in following domain-specific tasks, and (3) reasoning-based knowledge distillation through fine-tuning to significantly enhance its ability to generate contextually releva"},"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":"2503.17604","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-22T01:18:59Z","cross_cats_sorted":[],"title_canon_sha256":"d57bee0757fbac5bb3637893df3b75b77f9b69a8a94f5738555be7ccc3081545","abstract_canon_sha256":"71602ea0d347d44f83b6f5965345e0e0dbe4784727d1357114dd600437b25176"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:40.031224Z","signature_b64":"TXYa8Sg4EYbj6WzHzL1Q4Y3uyZ8WwHtkT8saiwRPfKqfRk+0cyq7UQAbw5Yz4NkKGlLOja9AFS6uGbG31O3WBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cbe60e7ae77d01d79a4cb5c62dd2370ce31a6b4f4a8b5091a6458d57f5a800a","last_reissued_at":"2026-07-05T10:52:40.030735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:40.030735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aastha Jhunjhunwala, Adam Atanas, Joah Han, Kai Liu, Kang Xu, Md Amirul Islam, Robert Clark, Rucha Apte, Vignesh Prabhakar, Yao-Ting Wang, Zihan Wang","submitted_at":"2025-03-22T01:18:59Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable potential in advancing scientific knowledge and addressing complex challenges. In this work, we introduce OmniScience, a specialized large reasoning model for general science, developed through three key components: (1) domain adaptive pretraining on a carefully curated corpus of scientific literature, (2) instruction tuning on a specialized dataset to guide the model in following domain-specific tasks, and (3) reasoning-based knowledge distillation through fine-tuning to significantly enhance its ability to generate contextually releva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17604","kind":"arxiv","version":4},"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/2503.17604/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":"2503.17604","created_at":"2026-07-05T10:52:40.030798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17604v4","created_at":"2026-07-05T10:52:40.030798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17604","created_at":"2026-07-05T10:52:40.030798+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS7GBZ5OO7IB","created_at":"2026-07-05T10:52:40.030798+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS7GBZ5OO7IB26NE","created_at":"2026-07-05T10:52:40.030798+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS7GBZ5O","created_at":"2026-07-05T10:52:40.030798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23273","citing_title":"Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11810","citing_title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2510.19225","citing_title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD","json":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD.json","graph_json":"https://pith.science/api/pith-number/LS7GBZ5OO7IB26NEZNOGFXJDOD/graph.json","events_json":"https://pith.science/api/pith-number/LS7GBZ5OO7IB26NEZNOGFXJDOD/events.json","paper":"https://pith.science/paper/LS7GBZ5O"},"agent_actions":{"view_html":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD","download_json":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD.json","view_paper":"https://pith.science/paper/LS7GBZ5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17604&json=true","fetch_graph":"https://pith.science/api/pith-number/LS7GBZ5OO7IB26NEZNOGFXJDOD/graph.json","fetch_events":"https://pith.science/api/pith-number/LS7GBZ5OO7IB26NEZNOGFXJDOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD/action/storage_attestation","attest_author":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD/action/author_attestation","sign_citation":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD/action/citation_signature","submit_replication":"https://pith.science/pith/LS7GBZ5OO7IB26NEZNOGFXJDOD/action/replication_record"}},"created_at":"2026-07-05T10:52:40.030798+00:00","updated_at":"2026-07-05T10:52:40.030798+00:00"}