{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XYGLGOPHPXBGHFSAHVJ5FZLDPZ","short_pith_number":"pith:XYGLGOPH","schema_version":"1.0","canonical_sha256":"be0cb339e77dc26396403d53d2e5637e6da28383f03aa0e21b67d37df2a73591","source":{"kind":"arxiv","id":"2505.05616","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Large Language Models for enzymatic reaction prediction and characterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Jana Marie Weber, Lorenzo Di Fruscia","submitted_at":"2025-05-08T19:53:53Z","abstract_excerpt":"Predicting enzymatic reactions is crucial for applications in biocatalysis, metabolic engineering, and drug discovery, yet it remains a complex and resource-intensive task. Large Language Models (LLMs) have recently demonstrated remarkable success in various scientific domains, e.g., through their ability to generalize knowledge, reason over complex structures, and leverage in-context learning strategies. In this study, we systematically evaluate the capability of LLMs, particularly the Llama-3.1 family (8B and 70B), across three core biochemical tasks: Enzyme Commission number prediction, for"},"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":"2505.05616","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-08T19:53:53Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"ce880617ce423a3dd6956cebc155e8c9ed77911fcb0c4c590d9cc569ffc9bbec","abstract_canon_sha256":"ff50d8f654378fb8dc4c459fff098f14eaf8e131b15bebc5fdd9964943710e14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:29.159241Z","signature_b64":"6qIBaazQu46oM3ow7RfmctYgLAU323H3bQsPPv/FT0xN30JK2R90qW3U5hjt3ZdhGJZfzhPk/ceTg9yQFRf0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be0cb339e77dc26396403d53d2e5637e6da28383f03aa0e21b67d37df2a73591","last_reissued_at":"2026-07-05T11:00:29.158766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:29.158766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models for enzymatic reaction prediction and characterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Jana Marie Weber, Lorenzo Di Fruscia","submitted_at":"2025-05-08T19:53:53Z","abstract_excerpt":"Predicting enzymatic reactions is crucial for applications in biocatalysis, metabolic engineering, and drug discovery, yet it remains a complex and resource-intensive task. Large Language Models (LLMs) have recently demonstrated remarkable success in various scientific domains, e.g., through their ability to generalize knowledge, reason over complex structures, and leverage in-context learning strategies. In this study, we systematically evaluate the capability of LLMs, particularly the Llama-3.1 family (8B and 70B), across three core biochemical tasks: Enzyme Commission number prediction, for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05616","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/2505.05616/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":"2505.05616","created_at":"2026-07-05T11:00:29.158823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05616v1","created_at":"2026-07-05T11:00:29.158823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05616","created_at":"2026-07-05T11:00:29.158823+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYGLGOPHPXBG","created_at":"2026-07-05T11:00:29.158823+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYGLGOPHPXBGHFSA","created_at":"2026-07-05T11:00:29.158823+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYGLGOPH","created_at":"2026-07-05T11:00:29.158823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ","json":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ.json","graph_json":"https://pith.science/api/pith-number/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/graph.json","events_json":"https://pith.science/api/pith-number/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/events.json","paper":"https://pith.science/paper/XYGLGOPH"},"agent_actions":{"view_html":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ","download_json":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ.json","view_paper":"https://pith.science/paper/XYGLGOPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05616&json=true","fetch_graph":"https://pith.science/api/pith-number/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/action/storage_attestation","attest_author":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/action/author_attestation","sign_citation":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/action/citation_signature","submit_replication":"https://pith.science/pith/XYGLGOPHPXBGHFSAHVJ5FZLDPZ/action/replication_record"}},"created_at":"2026-07-05T11:00:29.158823+00:00","updated_at":"2026-07-05T11:00:29.158823+00:00"}