{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NHBJILOLSG7YQ4LJIV4MAYIDZE","short_pith_number":"pith:NHBJILOL","schema_version":"1.0","canonical_sha256":"69c2942dcb91bf8871694578c06103c90a72dd8ab4088965aff99300dc269842","source":{"kind":"arxiv","id":"2412.01564","version":1},"attestation_state":"computed","paper":{"title":"Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Haoxiang Guan, John E. Hopcroft, Kaiyuan Gao, Kun He, Lijun Wu, Qizhi Pei, Yusong Wang, Zun Wang","submitted_at":"2024-12-02T14:50:44Z","abstract_excerpt":"The application of language models (LMs) to molecular structure generation using line notations such as SMILES and SELFIES has been well-established in the field of cheminformatics. However, extending these models to generate 3D molecular structures presents significant challenges. Two primary obstacles emerge: (1) the difficulty in designing a 3D line notation that ensures SE(3)-invariant atomic coordinates, and (2) the non-trivial task of tokenizing continuous coordinates for use in LMs, which inherently require discrete inputs. To address these challenges, we propose Mol-StrucTok, a novel m"},"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":"2412.01564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T14:50:44Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"fdf6c7975026cffced9241fa517d49cf387e7f1be6dd31fba843a88e420cf0d3","abstract_canon_sha256":"25f7b8eab1f0a41a004ac96a01a82da08655c96b4b3da38581f4fc66e886f07a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:15.155427Z","signature_b64":"IJfo9xo7LsvU4qEMe2BCpfEKy7Y2ieR8euDAErV7mrPPby0+70ks0TJh9W+UXJ4m1LVUuZt97VL17FEf1o3hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c2942dcb91bf8871694578c06103c90a72dd8ab4088965aff99300dc269842","last_reissued_at":"2026-07-05T09:43:15.154966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:15.154966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Haoxiang Guan, John E. Hopcroft, Kaiyuan Gao, Kun He, Lijun Wu, Qizhi Pei, Yusong Wang, Zun Wang","submitted_at":"2024-12-02T14:50:44Z","abstract_excerpt":"The application of language models (LMs) to molecular structure generation using line notations such as SMILES and SELFIES has been well-established in the field of cheminformatics. However, extending these models to generate 3D molecular structures presents significant challenges. Two primary obstacles emerge: (1) the difficulty in designing a 3D line notation that ensures SE(3)-invariant atomic coordinates, and (2) the non-trivial task of tokenizing continuous coordinates for use in LMs, which inherently require discrete inputs. To address these challenges, we propose Mol-StrucTok, a novel m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01564","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/2412.01564/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":"2412.01564","created_at":"2026-07-05T09:43:15.155020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01564v1","created_at":"2026-07-05T09:43:15.155020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01564","created_at":"2026-07-05T09:43:15.155020+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHBJILOLSG7Y","created_at":"2026-07-05T09:43:15.155020+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHBJILOLSG7YQ4LJ","created_at":"2026-07-05T09:43:15.155020+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHBJILOL","created_at":"2026-07-05T09:43:15.155020+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/NHBJILOLSG7YQ4LJIV4MAYIDZE","json":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE.json","graph_json":"https://pith.science/api/pith-number/NHBJILOLSG7YQ4LJIV4MAYIDZE/graph.json","events_json":"https://pith.science/api/pith-number/NHBJILOLSG7YQ4LJIV4MAYIDZE/events.json","paper":"https://pith.science/paper/NHBJILOL"},"agent_actions":{"view_html":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE","download_json":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE.json","view_paper":"https://pith.science/paper/NHBJILOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01564&json=true","fetch_graph":"https://pith.science/api/pith-number/NHBJILOLSG7YQ4LJIV4MAYIDZE/graph.json","fetch_events":"https://pith.science/api/pith-number/NHBJILOLSG7YQ4LJIV4MAYIDZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/action/storage_attestation","attest_author":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/action/author_attestation","sign_citation":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/action/citation_signature","submit_replication":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/action/replication_record"}},"created_at":"2026-07-05T09:43:15.155020+00:00","updated_at":"2026-07-05T09:43:15.155020+00:00"}