{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YJMG7FRSI3VER47QXOLGYNZA3N","short_pith_number":"pith:YJMG7FRS","canonical_record":{"source":{"id":"2407.07930","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-10T07:22:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e9d2019bacc6ec9d86db0fa46473b1e2502d4416fa06fa13aa79a93f0621498e","abstract_canon_sha256":"df987c9281f415129bf41364f944b696a24fc6a62109f2ff5a1668584e65e5d3"},"schema_version":"1.0"},"canonical_sha256":"c2586f963246ea48f3f0bb966c3720db7b71990c6a86eb3af4d6e62873485e84","source":{"kind":"arxiv","id":"2407.07930","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07930","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07930v2","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07930","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"YJMG7FRSI3VE","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"YJMG7FRSI3VER47Q","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"YJMG7FRS","created_at":"2026-07-05T08:56:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YJMG7FRSI3VER47QXOLGYNZA3N","target":"record","payload":{"canonical_record":{"source":{"id":"2407.07930","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-10T07:22:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e9d2019bacc6ec9d86db0fa46473b1e2502d4416fa06fa13aa79a93f0621498e","abstract_canon_sha256":"df987c9281f415129bf41364f944b696a24fc6a62109f2ff5a1668584e65e5d3"},"schema_version":"1.0"},"canonical_sha256":"c2586f963246ea48f3f0bb966c3720db7b71990c6a86eb3af4d6e62873485e84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:22.374736Z","signature_b64":"PRvhWa7NyAKkZXL0r9GTkLjgtxG4/n7og1G+cB3ggValKwWTnC3Pu8zKXvwywLfged5RVdk/2dkOb0q0lm9ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2586f963246ea48f3f0bb966c3720db7b71990c6a86eb3af4d6e62873485e84","last_reissued_at":"2026-07-05T08:56:22.374284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:22.374284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.07930","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1RM15CdLhERdOFPRy6slhIEppcjn2ZAslYoFNEMi0W3tGH49j+js5QHiQ3EzOn1/iVW+2AxN5/OluTJWfBrCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:54:21.524047Z"},"content_sha256":"e443fcc6964268c2a6b03c6d60f406402e0a5168710ff778aaf4fe774ac37266","schema_version":"1.0","event_id":"sha256:e443fcc6964268c2a6b03c6d60f406402e0a5168710ff778aaf4fe774ac37266"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YJMG7FRSI3VER47QXOLGYNZA3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Token-Mol 1.0: Tokenized drug design with large language model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Chang-Yu Hsieh, Chao Shen, Dejun Jiang, Huifeng Zhao, Jike Wang, Liwei Liu, Meijing Fang, Mingyang Wang, Odin Zhang, Qiaolin Gou, Qun Su, Rui Qin, Tingjun Hou, Xiaozhe Wan, Xujun Zhang, Yangyang Zhang, Yuchen Zhu, Yu Kang, Zhenxing Wu, Zhourui Wu","submitted_at":"2024-07-10T07:22:15Z","abstract_excerpt":"Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D) structures, thereby limiting their effectiveness in tasks that explicitly involve molecular conformations. In this study, we introduced Token-Mol, a token-only 3D drug design model. This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in dru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07930","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/2407.07930/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":"2026-07-05T08:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eU3toPNg7cHRBB0Gbp/wLFerbkIxm/ROOSWYqaNwJrnfMi1jL0mw7Uisj08mYunA+XTimGkVvRnbBTpyiFQ8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:54:21.524588Z"},"content_sha256":"5c5eff957ffef627811469080de1869b44986a71f9db8503c976a584b2422b7a","schema_version":"1.0","event_id":"sha256:5c5eff957ffef627811469080de1869b44986a71f9db8503c976a584b2422b7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJMG7FRSI3VER47QXOLGYNZA3N/bundle.json","state_url":"https://pith.science/pith/YJMG7FRSI3VER47QXOLGYNZA3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJMG7FRSI3VER47QXOLGYNZA3N/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":"2026-08-18T03:54:21Z","links":{"resolver":"https://pith.science/pith/YJMG7FRSI3VER47QXOLGYNZA3N","bundle":"https://pith.science/pith/YJMG7FRSI3VER47QXOLGYNZA3N/bundle.json","state":"https://pith.science/pith/YJMG7FRSI3VER47QXOLGYNZA3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJMG7FRSI3VER47QXOLGYNZA3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJMG7FRSI3VER47QXOLGYNZA3N","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":"df987c9281f415129bf41364f944b696a24fc6a62109f2ff5a1668584e65e5d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-10T07:22:15Z","title_canon_sha256":"e9d2019bacc6ec9d86db0fa46473b1e2502d4416fa06fa13aa79a93f0621498e"},"schema_version":"1.0","source":{"id":"2407.07930","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07930","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07930v2","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07930","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"YJMG7FRSI3VE","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"YJMG7FRSI3VER47Q","created_at":"2026-07-05T08:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"YJMG7FRS","created_at":"2026-07-05T08:56:22Z"}],"graph_snapshots":[{"event_id":"sha256:5c5eff957ffef627811469080de1869b44986a71f9db8503c976a584b2422b7a","target":"graph","created_at":"2026-07-05T08:56:22Z","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/2407.07930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D) structures, thereby limiting their effectiveness in tasks that explicitly involve molecular conformations. In this study, we introduced Token-Mol, a token-only 3D drug design model. This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in dru","authors_text":"Chang-Yu Hsieh, Chao Shen, Dejun Jiang, Huifeng Zhao, Jike Wang, Liwei Liu, Meijing Fang, Mingyang Wang, Odin Zhang, Qiaolin Gou, Qun Su, Rui Qin, Tingjun Hou, Xiaozhe Wan, Xujun Zhang, Yangyang Zhang, Yuchen Zhu, Yu Kang, Zhenxing Wu, Zhourui Wu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-10T07:22:15Z","title":"Token-Mol 1.0: Tokenized drug design with large language model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07930","kind":"arxiv","version":2},"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:e443fcc6964268c2a6b03c6d60f406402e0a5168710ff778aaf4fe774ac37266","target":"record","created_at":"2026-07-05T08:56:22Z","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":"df987c9281f415129bf41364f944b696a24fc6a62109f2ff5a1668584e65e5d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-10T07:22:15Z","title_canon_sha256":"e9d2019bacc6ec9d86db0fa46473b1e2502d4416fa06fa13aa79a93f0621498e"},"schema_version":"1.0","source":{"id":"2407.07930","kind":"arxiv","version":2}},"canonical_sha256":"c2586f963246ea48f3f0bb966c3720db7b71990c6a86eb3af4d6e62873485e84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2586f963246ea48f3f0bb966c3720db7b71990c6a86eb3af4d6e62873485e84","first_computed_at":"2026-07-05T08:56:22.374284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:22.374284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PRvhWa7NyAKkZXL0r9GTkLjgtxG4/n7og1G+cB3ggValKwWTnC3Pu8zKXvwywLfged5RVdk/2dkOb0q0lm9ADg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:22.374736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07930","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e443fcc6964268c2a6b03c6d60f406402e0a5168710ff778aaf4fe774ac37266","sha256:5c5eff957ffef627811469080de1869b44986a71f9db8503c976a584b2422b7a"],"state_sha256":"d054e5f32b21fb02df08db8f75d3339057db8becb18bad28d393a9491b8941c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+lehVqKdoyAI1NZ/siptziNHLDwBwWEHIeq+KT1Z5pK01SXi/VqO8GOdz3/LgpN/1vkH6tPfAKJvpnM3FdYHAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:54:21.583997Z","bundle_sha256":"add0b6634623f5d0403477e5b14a81f8d3b9b1b6015a103f2bc107bb9d2d153e"}}