{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q6BPIWONO25L4D4K36ABR27UWC","short_pith_number":"pith:Q6BPIWON","canonical_record":{"source":{"id":"2408.09730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-08-19T06:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"3304b86f71e0a2a068c3ff09b69a67ea68a7f3739c149d9984652ba2ef100dd6","abstract_canon_sha256":"44ed024a28c6d3e8cbab61f2567c54e4c6f7c8343780bf78af7b75a5c091f65b"},"schema_version":"1.0"},"canonical_sha256":"8782f459cd76babe0f8adf8018ebf4b0b1ca7741b6d46893327a27c1be10d6f1","source":{"kind":"arxiv","id":"2408.09730","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09730","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09730v1","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09730","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"pith_short_12","alias_value":"Q6BPIWONO25L","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"pith_short_16","alias_value":"Q6BPIWONO25L4D4K","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"pith_short_8","alias_value":"Q6BPIWON","created_at":"2026-07-05T08:56:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q6BPIWONO25L4D4K36ABR27UWC","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-08-19T06:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"3304b86f71e0a2a068c3ff09b69a67ea68a7f3739c149d9984652ba2ef100dd6","abstract_canon_sha256":"44ed024a28c6d3e8cbab61f2567c54e4c6f7c8343780bf78af7b75a5c091f65b"},"schema_version":"1.0"},"canonical_sha256":"8782f459cd76babe0f8adf8018ebf4b0b1ca7741b6d46893327a27c1be10d6f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:36.270705Z","signature_b64":"0kQoAlD1G7ZNiuVf/s4BmM6j9NJsLPTCpBs9uGTPXANEmUfKXTGbjZLSUsrksZp6w1kTUHCvphkn8uxuboc0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8782f459cd76babe0f8adf8018ebf4b0b1ca7741b6d46893327a27c1be10d6f1","last_reissued_at":"2026-07-05T08:56:36.270264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:36.270264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09730","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":"2026-07-05T08:56:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K3Jf1H+2o+Pzt2rXO4IL4IjKJQJFj3tBMeN8hJYPU2Td4BRfm7s5Kjcq3HIVmch9P1z1P3jbQ682CE5RsSINAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:02:33.028017Z"},"content_sha256":"a7d141553b59aaf76a52c1dc3464b69a595e7859bb8372f8e0c9c8bbd900d43d","schema_version":"1.0","event_id":"sha256:a7d141553b59aaf76a52c1dc3464b69a595e7859bb8372f8e0c9c8bbd900d43d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q6BPIWONO25L4D4K36ABR27UWC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.BM","authors_text":"Blake Olson, Cong Fu, Heng Ji, Shuiwang Ji, Xiner Li","submitted_at":"2024-08-19T06:33:43Z","abstract_excerpt":"Structure-based drug design (SBDD) is crucial for developing specific and effective therapeutics against protein targets but remains challenging due to complex protein-ligand interactions and vast chemical space. Although language models (LMs) have excelled in natural language processing, their application in SBDD is underexplored. To bridge this gap, we introduce a method, known as Frag2Seq, to apply LMs to SBDD by generating molecules in a fragment-based manner in which fragments correspond to functional modules. We transform 3D molecules into fragment-informed sequences using SE(3)-equivari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09730","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/2408.09730/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":"2026-07-05T08:56:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F1UP272dIrPnLV44BUQMejsGBEJC/rltxocWanvfivgxTEM/TlP16OkfaK+0ZGzBMShM/nTAuLskSvgD8HjXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:02:33.028528Z"},"content_sha256":"40fdc7e7e93072d2e9bbf36e36c761a890ff759cb8a8c3aebe42eb581a47ecfa","schema_version":"1.0","event_id":"sha256:40fdc7e7e93072d2e9bbf36e36c761a890ff759cb8a8c3aebe42eb581a47ecfa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6BPIWONO25L4D4K36ABR27UWC/bundle.json","state_url":"https://pith.science/pith/Q6BPIWONO25L4D4K36ABR27UWC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6BPIWONO25L4D4K36ABR27UWC/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":"2026-08-09T22:02:33Z","links":{"resolver":"https://pith.science/pith/Q6BPIWONO25L4D4K36ABR27UWC","bundle":"https://pith.science/pith/Q6BPIWONO25L4D4K36ABR27UWC/bundle.json","state":"https://pith.science/pith/Q6BPIWONO25L4D4K36ABR27UWC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6BPIWONO25L4D4K36ABR27UWC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q6BPIWONO25L4D4K36ABR27UWC","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":"44ed024a28c6d3e8cbab61f2567c54e4c6f7c8343780bf78af7b75a5c091f65b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-08-19T06:33:43Z","title_canon_sha256":"3304b86f71e0a2a068c3ff09b69a67ea68a7f3739c149d9984652ba2ef100dd6"},"schema_version":"1.0","source":{"id":"2408.09730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09730","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09730v1","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09730","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"pith_short_12","alias_value":"Q6BPIWONO25L","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"pith_short_16","alias_value":"Q6BPIWONO25L4D4K","created_at":"2026-07-05T08:56:36Z"},{"alias_kind":"pith_short_8","alias_value":"Q6BPIWON","created_at":"2026-07-05T08:56:36Z"}],"graph_snapshots":[{"event_id":"sha256:40fdc7e7e93072d2e9bbf36e36c761a890ff759cb8a8c3aebe42eb581a47ecfa","target":"graph","created_at":"2026-07-05T08:56:36Z","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/2408.09730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structure-based drug design (SBDD) is crucial for developing specific and effective therapeutics against protein targets but remains challenging due to complex protein-ligand interactions and vast chemical space. Although language models (LMs) have excelled in natural language processing, their application in SBDD is underexplored. To bridge this gap, we introduce a method, known as Frag2Seq, to apply LMs to SBDD by generating molecules in a fragment-based manner in which fragments correspond to functional modules. We transform 3D molecules into fragment-informed sequences using SE(3)-equivari","authors_text":"Blake Olson, Cong Fu, Heng Ji, Shuiwang Ji, Xiner Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-08-19T06:33:43Z","title":"Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09730","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:a7d141553b59aaf76a52c1dc3464b69a595e7859bb8372f8e0c9c8bbd900d43d","target":"record","created_at":"2026-07-05T08:56:36Z","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":"44ed024a28c6d3e8cbab61f2567c54e4c6f7c8343780bf78af7b75a5c091f65b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-08-19T06:33:43Z","title_canon_sha256":"3304b86f71e0a2a068c3ff09b69a67ea68a7f3739c149d9984652ba2ef100dd6"},"schema_version":"1.0","source":{"id":"2408.09730","kind":"arxiv","version":1}},"canonical_sha256":"8782f459cd76babe0f8adf8018ebf4b0b1ca7741b6d46893327a27c1be10d6f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8782f459cd76babe0f8adf8018ebf4b0b1ca7741b6d46893327a27c1be10d6f1","first_computed_at":"2026-07-05T08:56:36.270264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:36.270264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0kQoAlD1G7ZNiuVf/s4BmM6j9NJsLPTCpBs9uGTPXANEmUfKXTGbjZLSUsrksZp6w1kTUHCvphkn8uxuboc0AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:36.270705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7d141553b59aaf76a52c1dc3464b69a595e7859bb8372f8e0c9c8bbd900d43d","sha256:40fdc7e7e93072d2e9bbf36e36c761a890ff759cb8a8c3aebe42eb581a47ecfa"],"state_sha256":"c40b1426c3b4fc93c521f3924ba407e8e59ad6d7b6d85b6b3a827ed098340ade"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KywciwxJCSs6PkpekZAGlSSoqOvEA6zysBHW3pwIZwjTxZNqUnps8SU+nzdeW1nv4ydpRrSD4IQJejWjxz6uAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:02:33.033757Z","bundle_sha256":"63761e63af73f864686db0f6fcaefb1b9d74b95b18c75a7ccccbc22218cf1f52"}}