{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LWUXMX44I253TBOD5RDNYADGER","short_pith_number":"pith:LWUXMX44","canonical_record":{"source":{"id":"2412.14642","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T08:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"cdc6c637e421000c6d4fa0fbc6d251086ff2f7763d9753924b1a2c1feefe8bff","abstract_canon_sha256":"d9906cba0e008c1f18418fb9045727f99a090e85ce2c2368fb800a952e1db768"},"schema_version":"1.0"},"canonical_sha256":"5da9765f9c46bbb985c3ec46dc00662475e537256ba388a57de951bba9dbe0bd","source":{"kind":"arxiv","id":"2412.14642","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14642","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14642v4","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14642","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"pith_short_12","alias_value":"LWUXMX44I253","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"pith_short_16","alias_value":"LWUXMX44I253TBOD","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"pith_short_8","alias_value":"LWUXMX44","created_at":"2026-05-25T02:02:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LWUXMX44I253TBOD5RDNYADGER","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14642","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T08:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"cdc6c637e421000c6d4fa0fbc6d251086ff2f7763d9753924b1a2c1feefe8bff","abstract_canon_sha256":"d9906cba0e008c1f18418fb9045727f99a090e85ce2c2368fb800a952e1db768"},"schema_version":"1.0"},"canonical_sha256":"5da9765f9c46bbb985c3ec46dc00662475e537256ba388a57de951bba9dbe0bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:06.129197Z","signature_b64":"F41oeoEcuk+jEUBuzb7+kbEpxFwnj/Kh2O+N+YSVK2+bKaqCQpaggUuI88IU6wgu9YvK2Wqxnr90leuc6tN7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5da9765f9c46bbb985c3ec46dc00662475e537256ba388a57de951bba9dbe0bd","last_reissued_at":"2026-05-25T02:02:06.128255Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:06.128255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14642","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":"2026-05-25T02:02:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJKFmz4Y/YL7uUx5iw+QINVLsB7g6BzF3NmZv2TmQKcXFok9Gr4I+utH6EdHeVMFOj78Z25A40vOMVDosOLwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T07:53:28.073032Z"},"content_sha256":"e130267403d06a852483c3b051ccaa26ec4dc7844122cf25b61adba9eec05413","schema_version":"1.0","event_id":"sha256:e130267403d06a852483c3b051ccaa26ec4dc7844122cf25b61adba9eec05413"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LWUXMX44I253TBOD5RDNYADGER","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changmeng Zheng, Dongzhan Zhou, Jiatong Li, Junxian Li, Qing Li, Weida Wang, Xiao-Yong Wei, Yatao Bian, Yunqing Liu","submitted_at":"2024-12-19T08:51:16Z","abstract_excerpt":"Recently, Large Language Models (LLMs) have demonstrated great potential in natural language-driven molecule discovery. However, existing datasets and benchmarks for molecule-text alignment are predominantly built on one-to-one mappings, measuring LLMs' ability to retrieve a single, pre-defined answer, rather than their creative potential to generate diverse, yet equally valid, molecular candidates. To address this critical gap, we propose Speak-to-Structure (S^2-Bench), the first benchmark to evaluate LLMs in open-domain natural language-driven molecule generation. S^2-Bench is specifically d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14642","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/2412.14642/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":"2026-05-25T02:02:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vxoFpI1zR+v/PCXnX9Qp30E2UyNva5mQ1ioQvDOrDYiCI06A/ocjn+wDBr00Y45g/b+qMSfGRwwCS+66lwYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T07:53:28.073464Z"},"content_sha256":"1511636b237010315ff6c4923d087d9f33c0bf125d2ffb7b0c7b2760814c9164","schema_version":"1.0","event_id":"sha256:1511636b237010315ff6c4923d087d9f33c0bf125d2ffb7b0c7b2760814c9164"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWUXMX44I253TBOD5RDNYADGER/bundle.json","state_url":"https://pith.science/pith/LWUXMX44I253TBOD5RDNYADGER/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWUXMX44I253TBOD5RDNYADGER/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":"2026-05-28T07:53:28Z","links":{"resolver":"https://pith.science/pith/LWUXMX44I253TBOD5RDNYADGER","bundle":"https://pith.science/pith/LWUXMX44I253TBOD5RDNYADGER/bundle.json","state":"https://pith.science/pith/LWUXMX44I253TBOD5RDNYADGER/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWUXMX44I253TBOD5RDNYADGER/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LWUXMX44I253TBOD5RDNYADGER","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":"d9906cba0e008c1f18418fb9045727f99a090e85ce2c2368fb800a952e1db768","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T08:51:16Z","title_canon_sha256":"cdc6c637e421000c6d4fa0fbc6d251086ff2f7763d9753924b1a2c1feefe8bff"},"schema_version":"1.0","source":{"id":"2412.14642","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14642","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14642v4","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14642","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"pith_short_12","alias_value":"LWUXMX44I253","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"pith_short_16","alias_value":"LWUXMX44I253TBOD","created_at":"2026-05-25T02:02:06Z"},{"alias_kind":"pith_short_8","alias_value":"LWUXMX44","created_at":"2026-05-25T02:02:06Z"}],"graph_snapshots":[{"event_id":"sha256:1511636b237010315ff6c4923d087d9f33c0bf125d2ffb7b0c7b2760814c9164","target":"graph","created_at":"2026-05-25T02:02:06Z","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/2412.14642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Large Language Models (LLMs) have demonstrated great potential in natural language-driven molecule discovery. However, existing datasets and benchmarks for molecule-text alignment are predominantly built on one-to-one mappings, measuring LLMs' ability to retrieve a single, pre-defined answer, rather than their creative potential to generate diverse, yet equally valid, molecular candidates. To address this critical gap, we propose Speak-to-Structure (S^2-Bench), the first benchmark to evaluate LLMs in open-domain natural language-driven molecule generation. S^2-Bench is specifically d","authors_text":"Changmeng Zheng, Dongzhan Zhou, Jiatong Li, Junxian Li, Qing Li, Weida Wang, Xiao-Yong Wei, Yatao Bian, Yunqing Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T08:51:16Z","title":"Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14642","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:e130267403d06a852483c3b051ccaa26ec4dc7844122cf25b61adba9eec05413","target":"record","created_at":"2026-05-25T02:02:06Z","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":"d9906cba0e008c1f18418fb9045727f99a090e85ce2c2368fb800a952e1db768","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T08:51:16Z","title_canon_sha256":"cdc6c637e421000c6d4fa0fbc6d251086ff2f7763d9753924b1a2c1feefe8bff"},"schema_version":"1.0","source":{"id":"2412.14642","kind":"arxiv","version":4}},"canonical_sha256":"5da9765f9c46bbb985c3ec46dc00662475e537256ba388a57de951bba9dbe0bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5da9765f9c46bbb985c3ec46dc00662475e537256ba388a57de951bba9dbe0bd","first_computed_at":"2026-05-25T02:02:06.128255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:06.128255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F41oeoEcuk+jEUBuzb7+kbEpxFwnj/Kh2O+N+YSVK2+bKaqCQpaggUuI88IU6wgu9YvK2Wqxnr90leuc6tN7AA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:06.129197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14642","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e130267403d06a852483c3b051ccaa26ec4dc7844122cf25b61adba9eec05413","sha256:1511636b237010315ff6c4923d087d9f33c0bf125d2ffb7b0c7b2760814c9164"],"state_sha256":"3063d17d4b26da83088e0dd8fcf43a3131789992c9e9f5d08741d87d49e87a1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+nUyRHPMaL8SrroFhnwaY/mt5+qdt8NGwje8thpJaXAa4dr8tVrdZtlVKMjWvmEqZGJRcKP3yNZKeoqlcmHnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T07:53:28.075921Z","bundle_sha256":"700e9bdec31374ed8ae9d479bb5a9b45305fbef58826d9ded23eec45ddae8464"}}