{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NHBJILOLSG7YQ4LJIV4MAYIDZE","short_pith_number":"pith:NHBJILOL","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"},"canonical_sha256":"69c2942dcb91bf8871694578c06103c90a72dd8ab4088965aff99300dc269842","source":{"kind":"arxiv","id":"2412.01564","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01564","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01564v1","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01564","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"pith_short_12","alias_value":"NHBJILOLSG7Y","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"pith_short_16","alias_value":"NHBJILOLSG7YQ4LJ","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"pith_short_8","alias_value":"NHBJILOL","created_at":"2026-07-05T09:43:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NHBJILOLSG7YQ4LJIV4MAYIDZE","target":"record","payload":{"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"},"canonical_sha256":"69c2942dcb91bf8871694578c06103c90a72dd8ab4088965aff99300dc269842","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"},"source_kind":"arxiv","source_id":"2412.01564","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:43:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QHshCanBBUWaEtdylUNWn2AxZF2ci+9iplceYEW7BR99YYimcTW3tq3MFMPDr8h1FgHYlLvHvEINVupBNAGpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:16.647927Z"},"content_sha256":"c96b5f39721d989304d2cfa6dcb8442780b6092a5ee30f24e6e986cea7b8efa3","schema_version":"1.0","event_id":"sha256:c96b5f39721d989304d2cfa6dcb8442780b6092a5ee30f24e6e986cea7b8efa3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NHBJILOLSG7YQ4LJIV4MAYIDZE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:43:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A34xq8Y//kPyan4pJPRoPi2daTeLZjQYoz6hxNTao/McgrEiTr/Ke/KozT+UtnREnaOrebyWaoFcF/CU75jzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:16.648411Z"},"content_sha256":"c86bb60dbea660462d43a32a3ffc4fdb2993910f115a09b5c470c427a3e2c399","schema_version":"1.0","event_id":"sha256:c86bb60dbea660462d43a32a3ffc4fdb2993910f115a09b5c470c427a3e2c399"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/bundle.json","state_url":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/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":"2026-08-04T06:06:16Z","links":{"resolver":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE","bundle":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/bundle.json","state":"https://pith.science/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHBJILOLSG7YQ4LJIV4MAYIDZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NHBJILOLSG7YQ4LJIV4MAYIDZE","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":"25f7b8eab1f0a41a004ac96a01a82da08655c96b4b3da38581f4fc66e886f07a","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T14:50:44Z","title_canon_sha256":"fdf6c7975026cffced9241fa517d49cf387e7f1be6dd31fba843a88e420cf0d3"},"schema_version":"1.0","source":{"id":"2412.01564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01564","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01564v1","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01564","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"pith_short_12","alias_value":"NHBJILOLSG7Y","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"pith_short_16","alias_value":"NHBJILOLSG7YQ4LJ","created_at":"2026-07-05T09:43:15Z"},{"alias_kind":"pith_short_8","alias_value":"NHBJILOL","created_at":"2026-07-05T09:43:15Z"}],"graph_snapshots":[{"event_id":"sha256:c86bb60dbea660462d43a32a3ffc4fdb2993910f115a09b5c470c427a3e2c399","target":"graph","created_at":"2026-07-05T09:43:15Z","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/2412.01564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haoxiang Guan, John E. Hopcroft, Kaiyuan Gao, Kun He, Lijun Wu, Qizhi Pei, Yusong Wang, Zun Wang","cross_cats":["q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T14:50:44Z","title":"Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01564","kind":"arxiv","version":1},"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:c96b5f39721d989304d2cfa6dcb8442780b6092a5ee30f24e6e986cea7b8efa3","target":"record","created_at":"2026-07-05T09:43:15Z","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":"25f7b8eab1f0a41a004ac96a01a82da08655c96b4b3da38581f4fc66e886f07a","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T14:50:44Z","title_canon_sha256":"fdf6c7975026cffced9241fa517d49cf387e7f1be6dd31fba843a88e420cf0d3"},"schema_version":"1.0","source":{"id":"2412.01564","kind":"arxiv","version":1}},"canonical_sha256":"69c2942dcb91bf8871694578c06103c90a72dd8ab4088965aff99300dc269842","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69c2942dcb91bf8871694578c06103c90a72dd8ab4088965aff99300dc269842","first_computed_at":"2026-07-05T09:43:15.154966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:15.154966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IJfo9xo7LsvU4qEMe2BCpfEKy7Y2ieR8euDAErV7mrPPby0+70ks0TJh9W+UXJ4m1LVUuZt97VL17FEf1o3hBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:15.155427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c96b5f39721d989304d2cfa6dcb8442780b6092a5ee30f24e6e986cea7b8efa3","sha256:c86bb60dbea660462d43a32a3ffc4fdb2993910f115a09b5c470c427a3e2c399"],"state_sha256":"89a52104d2078ba4035742daab0e2898b2f4abeb66aeaf21dde6ed436b78a980"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GuhhfWhMoryhoysnO0KxQ9rEBI9yhsvfQLmAwJdyw+L3Rkkji+l1Yco1kfKWB6aMbnLFuuEuVe/MjAuuW+wgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:06:16.652307Z","bundle_sha256":"b637a210f8c2dbcde863ecde68c1cec57a8ec2bbb2f2ee91fd5293ade8784dc0"}}