{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:52WIVFQKIAW23A76CXXU5GQIX6","short_pith_number":"pith:52WIVFQK","schema_version":"1.0","canonical_sha256":"eeac8a960a402dad83fe15ef4e9a08bfbeb64de776b01e10fa4b679fc998f967","source":{"kind":"arxiv","id":"2412.20888","version":2},"attestation_state":"computed","paper":{"title":"Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Hao Li, Liuzhenghao Lv, Li Yuan, Yonghong Tian, Yu Wang, Zhiyuan Yan, Zijun Chen, Zongying Lin","submitted_at":"2024-12-30T11:54:22Z","abstract_excerpt":"Chemical language models (CLMs) are prominent for their effectiveness in exploring chemical space and enabling molecular engineering. However, while exploring chemical-linguistic space, CLMs suffer from the gap between natural language and molecular representations. This challenge is primarily due to the inherent modeling differences between molecules and texts: molecules operate unified modeling to learn chemical space, while natural language sequentially models the semantic space. Additionally, the limited availability of high-quality text-to-molecule datasets further exacerbates this challe"},"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":"2412.20888","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-12-30T11:54:22Z","cross_cats_sorted":[],"title_canon_sha256":"b85c02d3847bd757241a118c71719f072419eeafee80fe05c5cae60d4757910b","abstract_canon_sha256":"ffb90c72786405b93da74fedb9e9b13cb6eb8419c22f63cca10e66107f7fe88f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:24.626128Z","signature_b64":"IXKxaDGBInf8BQrRQG8I/I8orMW+1piQM3geCw8TYDFoAZFEMM3ZsDum/9aMYQFYV8niu1W5afD5eFtSzK02Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeac8a960a402dad83fe15ef4e9a08bfbeb64de776b01e10fa4b679fc998f967","last_reissued_at":"2026-07-05T09:57:24.625563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:24.625563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Hao Li, Liuzhenghao Lv, Li Yuan, Yonghong Tian, Yu Wang, Zhiyuan Yan, Zijun Chen, Zongying Lin","submitted_at":"2024-12-30T11:54:22Z","abstract_excerpt":"Chemical language models (CLMs) are prominent for their effectiveness in exploring chemical space and enabling molecular engineering. However, while exploring chemical-linguistic space, CLMs suffer from the gap between natural language and molecular representations. This challenge is primarily due to the inherent modeling differences between molecules and texts: molecules operate unified modeling to learn chemical space, while natural language sequentially models the semantic space. Additionally, the limited availability of high-quality text-to-molecule datasets further exacerbates this challe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20888","kind":"arxiv","version":2},"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/2412.20888/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":"2412.20888","created_at":"2026-07-05T09:57:24.625626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20888v2","created_at":"2026-07-05T09:57:24.625626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20888","created_at":"2026-07-05T09:57:24.625626+00:00"},{"alias_kind":"pith_short_12","alias_value":"52WIVFQKIAW2","created_at":"2026-07-05T09:57:24.625626+00:00"},{"alias_kind":"pith_short_16","alias_value":"52WIVFQKIAW23A76","created_at":"2026-07-05T09:57:24.625626+00:00"},{"alias_kind":"pith_short_8","alias_value":"52WIVFQK","created_at":"2026-07-05T09:57:24.625626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16480","citing_title":"MoleCode unlocks structural intelligence in large language models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6","json":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6.json","graph_json":"https://pith.science/api/pith-number/52WIVFQKIAW23A76CXXU5GQIX6/graph.json","events_json":"https://pith.science/api/pith-number/52WIVFQKIAW23A76CXXU5GQIX6/events.json","paper":"https://pith.science/paper/52WIVFQK"},"agent_actions":{"view_html":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6","download_json":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6.json","view_paper":"https://pith.science/paper/52WIVFQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20888&json=true","fetch_graph":"https://pith.science/api/pith-number/52WIVFQKIAW23A76CXXU5GQIX6/graph.json","fetch_events":"https://pith.science/api/pith-number/52WIVFQKIAW23A76CXXU5GQIX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6/action/storage_attestation","attest_author":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6/action/author_attestation","sign_citation":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6/action/citation_signature","submit_replication":"https://pith.science/pith/52WIVFQKIAW23A76CXXU5GQIX6/action/replication_record"}},"created_at":"2026-07-05T09:57:24.625626+00:00","updated_at":"2026-07-05T09:57:24.625626+00:00"}