{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N4UROPULFQY4PECXMQEDXKUYDL","short_pith_number":"pith:N4UROPUL","canonical_record":{"source":{"id":"2406.18045","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T03:43:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c45dcfda9f6fa555d7bff1971decec6ef6c01f10c74231c112ff71aeeaea335","abstract_canon_sha256":"c9fe1ea65a642cda7999586a92c2045a206fd93c506e5424891bc3a5cca4d3a8"},"schema_version":"1.0"},"canonical_sha256":"6f29173e8b2c31c7905764083baa981add145a1f32476a61bd74d438985d662d","source":{"kind":"arxiv","id":"2406.18045","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18045","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18045v3","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18045","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"pith_short_12","alias_value":"N4UROPULFQY4","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"pith_short_16","alias_value":"N4UROPULFQY4PECX","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"pith_short_8","alias_value":"N4UROPUL","created_at":"2026-07-05T08:41:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N4UROPULFQY4PECXMQEDXKUYDL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18045","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T03:43:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c45dcfda9f6fa555d7bff1971decec6ef6c01f10c74231c112ff71aeeaea335","abstract_canon_sha256":"c9fe1ea65a642cda7999586a92c2045a206fd93c506e5424891bc3a5cca4d3a8"},"schema_version":"1.0"},"canonical_sha256":"6f29173e8b2c31c7905764083baa981add145a1f32476a61bd74d438985d662d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:46.049966Z","signature_b64":"ohA0YA47ZwRWO2E1mQzx+0jarEpEGYgeJNxKzJf/1X7M7m/IQ6pxIviz3AOt7j0lf0vfpjMrsP1Abe737Dn4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f29173e8b2c31c7905764083baa981add145a1f32476a61bd74d438985d662d","last_reissued_at":"2026-07-05T08:41:46.049510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:46.049510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18045","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:41:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GTTexH8vFfYdxzsEfl4Rrub4KokFbA3ZXld7Ab2DJ15/DmzaS5CGSRdEltF9d0M5InbFpwzYoLJCto9DKyNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:00.719216Z"},"content_sha256":"67834051671227c977773c38f5bfd7a7e078b296439db0981cf822d9ffdbd783","schema_version":"1.0","event_id":"sha256:67834051671227c977773c38f5bfd7a7e078b296439db0981cf822d9ffdbd783"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N4UROPULFQY4PECXMQEDXKUYDL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PharmaGPT: Domain-Specific Large Language Models for Bio-Pharmaceutical and Chemistry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyang Tu, Chaobo Xu, Chaochao Wang, Cheng Sun, Fei Gao, Fu Bian, Haoran Hua, Haowen Liu, Jianping Lu, Jie Fang, Jing Sun, Jin Liu, Licong Xu, Lidong Pei, Linqing Chen, Lin Tie, Lisha Zhang, Lizhi Zhou, Lu Jin, Meng Hu, Peng Xu, Qijun Cai, Ran Hu, ruiji zhang, Shengjie Yang, Tian Qiu, Weilei Wang, Wentao Wu, Xiuwen Li, Yan Fang, Yixin Wang, Yuancheng LI, Yubin Xia, Yufu Wang, Zhongkai Ye, Zilong Bai","submitted_at":"2024-06-26T03:43:09Z","abstract_excerpt":"Large language models (LLMs) have revolutionized Natural Language Processing (NLP) by minimizing the need for complex feature engineering. However, the application of LLMs in specialized domains like biopharmaceuticals and chemistry remains largely unexplored. These fields are characterized by intricate terminologies, specialized knowledge, and a high demand for precision areas where general purpose LLMs often fall short. In this study, we introduce PharmaGPT, a suite of domain specilized LLMs with 13 billion and 70 billion parameters, specifically trained on a comprehensive corpus tailored to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18045","kind":"arxiv","version":3},"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/2406.18045/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":"2026-07-05T08:41:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tcUmodT0CMR6WIGStqzU7MnABRVPCd52ZkuGjn6Q/x/CeITLqG/m+stWuVl7eaGqANs0SXWROD5J5scwQco7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:00.719623Z"},"content_sha256":"972b91383fef310fc80d07d70555918b657bcba9b921d26da92d2d049f958b45","schema_version":"1.0","event_id":"sha256:972b91383fef310fc80d07d70555918b657bcba9b921d26da92d2d049f958b45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N4UROPULFQY4PECXMQEDXKUYDL/bundle.json","state_url":"https://pith.science/pith/N4UROPULFQY4PECXMQEDXKUYDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N4UROPULFQY4PECXMQEDXKUYDL/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":"2026-07-06T18:46:00Z","links":{"resolver":"https://pith.science/pith/N4UROPULFQY4PECXMQEDXKUYDL","bundle":"https://pith.science/pith/N4UROPULFQY4PECXMQEDXKUYDL/bundle.json","state":"https://pith.science/pith/N4UROPULFQY4PECXMQEDXKUYDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N4UROPULFQY4PECXMQEDXKUYDL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N4UROPULFQY4PECXMQEDXKUYDL","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":"c9fe1ea65a642cda7999586a92c2045a206fd93c506e5424891bc3a5cca4d3a8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T03:43:09Z","title_canon_sha256":"4c45dcfda9f6fa555d7bff1971decec6ef6c01f10c74231c112ff71aeeaea335"},"schema_version":"1.0","source":{"id":"2406.18045","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18045","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18045v3","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18045","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"pith_short_12","alias_value":"N4UROPULFQY4","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"pith_short_16","alias_value":"N4UROPULFQY4PECX","created_at":"2026-07-05T08:41:46Z"},{"alias_kind":"pith_short_8","alias_value":"N4UROPUL","created_at":"2026-07-05T08:41:46Z"}],"graph_snapshots":[{"event_id":"sha256:972b91383fef310fc80d07d70555918b657bcba9b921d26da92d2d049f958b45","target":"graph","created_at":"2026-07-05T08:41:46Z","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/2406.18045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have revolutionized Natural Language Processing (NLP) by minimizing the need for complex feature engineering. However, the application of LLMs in specialized domains like biopharmaceuticals and chemistry remains largely unexplored. These fields are characterized by intricate terminologies, specialized knowledge, and a high demand for precision areas where general purpose LLMs often fall short. In this study, we introduce PharmaGPT, a suite of domain specilized LLMs with 13 billion and 70 billion parameters, specifically trained on a comprehensive corpus tailored to","authors_text":"Changyang Tu, Chaobo Xu, Chaochao Wang, Cheng Sun, Fei Gao, Fu Bian, Haoran Hua, Haowen Liu, Jianping Lu, Jie Fang, Jing Sun, Jin Liu, Licong Xu, Lidong Pei, Linqing Chen, Lin Tie, Lisha Zhang, Lizhi Zhou, Lu Jin, Meng Hu, Peng Xu, Qijun Cai, Ran Hu, ruiji zhang, Shengjie Yang, Tian Qiu, Weilei Wang, Wentao Wu, Xiuwen Li, Yan Fang, Yixin Wang, Yuancheng LI, Yubin Xia, Yufu Wang, Zhongkai Ye, Zilong Bai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T03:43:09Z","title":"PharmaGPT: Domain-Specific Large Language Models for Bio-Pharmaceutical and Chemistry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18045","kind":"arxiv","version":3},"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":"sha256:67834051671227c977773c38f5bfd7a7e078b296439db0981cf822d9ffdbd783","target":"record","created_at":"2026-07-05T08:41:46Z","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":"c9fe1ea65a642cda7999586a92c2045a206fd93c506e5424891bc3a5cca4d3a8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T03:43:09Z","title_canon_sha256":"4c45dcfda9f6fa555d7bff1971decec6ef6c01f10c74231c112ff71aeeaea335"},"schema_version":"1.0","source":{"id":"2406.18045","kind":"arxiv","version":3}},"canonical_sha256":"6f29173e8b2c31c7905764083baa981add145a1f32476a61bd74d438985d662d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f29173e8b2c31c7905764083baa981add145a1f32476a61bd74d438985d662d","first_computed_at":"2026-07-05T08:41:46.049510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:46.049510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ohA0YA47ZwRWO2E1mQzx+0jarEpEGYgeJNxKzJf/1X7M7m/IQ6pxIviz3AOt7j0lf0vfpjMrsP1Abe737Dn4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:46.049966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18045","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67834051671227c977773c38f5bfd7a7e078b296439db0981cf822d9ffdbd783","sha256:972b91383fef310fc80d07d70555918b657bcba9b921d26da92d2d049f958b45"],"state_sha256":"a62925870066e13599fb66237c468b073b61835b83bbc1768061950c1e5c70b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/EK3rOdHI9vmyfGFrJyHLaEBCIubnY1DrF/jYLoVRhYTDG0RcQ9vB3mo0/I77xmWfy4GG+IyGnS0wL9TqrMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:46:00.721604Z","bundle_sha256":"f0423e63b544a9cb7b289b4d899fd75f3d912444ec4fe5f770bd79409de335ce"}}