{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X5GEEHNO4JSZO2X4CAQYWYYCUF","short_pith_number":"pith:X5GEEHNO","canonical_record":{"source":{"id":"2402.09391","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T18:42:25Z","cross_cats_sorted":["cs.CE","cs.CL"],"title_canon_sha256":"0530136ebea5629a56f07fda620ff7ea7fe6cbc887f39115e4e020ab5b0d8c81","abstract_canon_sha256":"0ce0a3fa162774e4e74e31cfecd65a3303a570e46913a178a51cde7b4dcbd73d"},"schema_version":"1.0"},"canonical_sha256":"bf4c421daee265976afc10218b6302a16e001e42c6861e6149eaaca81c42ca6c","source":{"kind":"arxiv","id":"2402.09391","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09391","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09391v4","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09391","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"X5GEEHNO4JSZ","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"X5GEEHNO4JSZO2X4","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"X5GEEHNO","created_at":"2026-07-05T08:54:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X5GEEHNO4JSZO2X4CAQYWYYCUF","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09391","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T18:42:25Z","cross_cats_sorted":["cs.CE","cs.CL"],"title_canon_sha256":"0530136ebea5629a56f07fda620ff7ea7fe6cbc887f39115e4e020ab5b0d8c81","abstract_canon_sha256":"0ce0a3fa162774e4e74e31cfecd65a3303a570e46913a178a51cde7b4dcbd73d"},"schema_version":"1.0"},"canonical_sha256":"bf4c421daee265976afc10218b6302a16e001e42c6861e6149eaaca81c42ca6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:07.152211Z","signature_b64":"buoweowf5RLk1Ya6+KOErZDBugIkHgjcPLQt7fTek0rWJrHtAPtYfhHLUr7doD9wuGSHzj5czDQM7u0MDNkzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf4c421daee265976afc10218b6302a16e001e42c6861e6149eaaca81c42ca6c","last_reissued_at":"2026-07-05T08:54:07.151808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:07.151808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09391","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ut1oj96Twyyxk3IYqXT/oxS26TC0rc/DllHfj38O/ifdC0ZXuqIMqf1QbI08nePc7esZaA7RFiYuIueuL8T/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:15:27.886563Z"},"content_sha256":"a426e68b0735e21e7215284d7b94d2e33ec22344fb7ba3b95f0275386ceb096c","schema_version":"1.0","event_id":"sha256:a426e68b0735e21e7215284d7b94d2e33ec22344fb7ba3b95f0275386ceb096c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X5GEEHNO4JSZO2X4CAQYWYYCUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.CL"],"primary_cat":"cs.AI","authors_text":"Botao Yu, Frazier N. Baker, Huan Sun, Xia Ning, Ziqi Chen","submitted_at":"2024-02-14T18:42:25Z","abstract_excerpt":"Chemistry plays a crucial role in many domains, such as drug discovery and material science. While large language models (LLMs) such as GPT-4 exhibit remarkable capabilities on natural language processing tasks, existing research indicates that their performance on chemistry tasks is discouragingly low. In this paper, however, we demonstrate that our developed LLMs can achieve very strong results on a comprehensive set of chemistry tasks, outperforming the most advanced GPT-4 and Claude 3 Opus by a substantial margin. To accomplish this, we propose SMolInstruct, a large-scale, comprehensive, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09391","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/2402.09391/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":"2026-07-05T08:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cKI9uWFGkjV3lRfYDLNXmd1MqnzaQqxUUXKN+h4B3Ic8wBZyw1RrIKPL5MYGSfO02jaYlNhoLOUQt5ZEJmHjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:15:27.887090Z"},"content_sha256":"4f83289f589ce3af78bec5f106171cb07d909e6b30fe67501afae0bcb5993d86","schema_version":"1.0","event_id":"sha256:4f83289f589ce3af78bec5f106171cb07d909e6b30fe67501afae0bcb5993d86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5GEEHNO4JSZO2X4CAQYWYYCUF/bundle.json","state_url":"https://pith.science/pith/X5GEEHNO4JSZO2X4CAQYWYYCUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5GEEHNO4JSZO2X4CAQYWYYCUF/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":"2026-08-04T21:15:27Z","links":{"resolver":"https://pith.science/pith/X5GEEHNO4JSZO2X4CAQYWYYCUF","bundle":"https://pith.science/pith/X5GEEHNO4JSZO2X4CAQYWYYCUF/bundle.json","state":"https://pith.science/pith/X5GEEHNO4JSZO2X4CAQYWYYCUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5GEEHNO4JSZO2X4CAQYWYYCUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X5GEEHNO4JSZO2X4CAQYWYYCUF","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":"0ce0a3fa162774e4e74e31cfecd65a3303a570e46913a178a51cde7b4dcbd73d","cross_cats_sorted":["cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T18:42:25Z","title_canon_sha256":"0530136ebea5629a56f07fda620ff7ea7fe6cbc887f39115e4e020ab5b0d8c81"},"schema_version":"1.0","source":{"id":"2402.09391","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09391","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09391v4","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09391","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"X5GEEHNO4JSZ","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"X5GEEHNO4JSZO2X4","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"X5GEEHNO","created_at":"2026-07-05T08:54:07Z"}],"graph_snapshots":[{"event_id":"sha256:4f83289f589ce3af78bec5f106171cb07d909e6b30fe67501afae0bcb5993d86","target":"graph","created_at":"2026-07-05T08:54:07Z","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/2402.09391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chemistry plays a crucial role in many domains, such as drug discovery and material science. While large language models (LLMs) such as GPT-4 exhibit remarkable capabilities on natural language processing tasks, existing research indicates that their performance on chemistry tasks is discouragingly low. In this paper, however, we demonstrate that our developed LLMs can achieve very strong results on a comprehensive set of chemistry tasks, outperforming the most advanced GPT-4 and Claude 3 Opus by a substantial margin. To accomplish this, we propose SMolInstruct, a large-scale, comprehensive, a","authors_text":"Botao Yu, Frazier N. Baker, Huan Sun, Xia Ning, Ziqi Chen","cross_cats":["cs.CE","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T18:42:25Z","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09391","kind":"arxiv","version":4},"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:a426e68b0735e21e7215284d7b94d2e33ec22344fb7ba3b95f0275386ceb096c","target":"record","created_at":"2026-07-05T08:54:07Z","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":"0ce0a3fa162774e4e74e31cfecd65a3303a570e46913a178a51cde7b4dcbd73d","cross_cats_sorted":["cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T18:42:25Z","title_canon_sha256":"0530136ebea5629a56f07fda620ff7ea7fe6cbc887f39115e4e020ab5b0d8c81"},"schema_version":"1.0","source":{"id":"2402.09391","kind":"arxiv","version":4}},"canonical_sha256":"bf4c421daee265976afc10218b6302a16e001e42c6861e6149eaaca81c42ca6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf4c421daee265976afc10218b6302a16e001e42c6861e6149eaaca81c42ca6c","first_computed_at":"2026-07-05T08:54:07.151808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:07.151808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"buoweowf5RLk1Ya6+KOErZDBugIkHgjcPLQt7fTek0rWJrHtAPtYfhHLUr7doD9wuGSHzj5czDQM7u0MDNkzDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:07.152211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09391","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a426e68b0735e21e7215284d7b94d2e33ec22344fb7ba3b95f0275386ceb096c","sha256:4f83289f589ce3af78bec5f106171cb07d909e6b30fe67501afae0bcb5993d86"],"state_sha256":"f09ca2774bd2bcb1349a9c77088a8a502ea3c6d853cfcaac2862cc50b238c894"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y50SwmaxGkxT+hg1F6GwBXyUAXdXrM79F+2QKvq/ggpLu3PL95mAbj16AM5CndsEYAlV6Fo9ab+FNc4BsmemCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:15:27.892087Z","bundle_sha256":"55255f79204e3453a05f3a92492298293fbfc7cbccf3f1216f29b428f9090118"}}