{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KGBRIBDDVPXGZJHXOW7A2FIU5X","short_pith_number":"pith:KGBRIBDD","canonical_record":{"source":{"id":"2107.08987","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2021-07-19T16:00:05Z","cross_cats_sorted":["cs.LG","physics.bio-ph"],"title_canon_sha256":"2aac0bdabf3b37c970a3ec32c312ac834dd9e5cd45a200b981d0a0d02e4ebefb","abstract_canon_sha256":"f24bea20bbf43513f2142e5ee2de8fcbe198971ed1dcae45a89aa52da5f44a55"},"schema_version":"1.0"},"canonical_sha256":"5183140463abee6ca4f775be0d1514edead002bd9cd20aeff8d3744db27bf65f","source":{"kind":"arxiv","id":"2107.08987","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.08987","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2107.08987v3","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08987","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"KGBRIBDDVPXG","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"KGBRIBDDVPXGZJHX","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"KGBRIBDD","created_at":"2026-07-05T03:11:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KGBRIBDDVPXGZJHXOW7A2FIU5X","target":"record","payload":{"canonical_record":{"source":{"id":"2107.08987","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2021-07-19T16:00:05Z","cross_cats_sorted":["cs.LG","physics.bio-ph"],"title_canon_sha256":"2aac0bdabf3b37c970a3ec32c312ac834dd9e5cd45a200b981d0a0d02e4ebefb","abstract_canon_sha256":"f24bea20bbf43513f2142e5ee2de8fcbe198971ed1dcae45a89aa52da5f44a55"},"schema_version":"1.0"},"canonical_sha256":"5183140463abee6ca4f775be0d1514edead002bd9cd20aeff8d3744db27bf65f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:13.705734Z","signature_b64":"hxTdhbnQnlJQUqZrVQWEKy//fdKWwypVpWG49R/vv6lSagb632KSkR9dDX3APz06b5nPDBSZzoLdVVZWkbo1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5183140463abee6ca4f775be0d1514edead002bd9cd20aeff8d3744db27bf65f","last_reissued_at":"2026-07-05T03:11:13.705342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:13.705342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.08987","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T33iJkBeVNTan+4I/Y7TQhrvtmJ6zbEGhl7mPV1reTdQO/CUK52Iub1HxghXd4hzbaxjZikRHB+EzAXTXVd2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:08:09.777139Z"},"content_sha256":"48be8ac8ed9053319025901ab068f2e31b295f923138c3574c62536b0e5cdd97","schema_version":"1.0","event_id":"sha256:48be8ac8ed9053319025901ab068f2e31b295f923138c3574c62536b0e5cdd97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KGBRIBDDVPXGZJHXOW7A2FIU5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder -- Insights for practical AI-driven molecule generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.bio-ph"],"primary_cat":"q-bio.BM","authors_text":"Jeffrey K. Weber, Joseph A. Morrone, Seung-gu Kang, Wendy D. Cornell","submitted_at":"2021-07-19T16:00:05Z","abstract_excerpt":"The application of deep learning to generative molecule design has shown early promise for accelerating lead series development. However, questions remain concerning how factors like training, dataset, and seed bias impact the technology's utility to medicine and computational chemists. In this work, we analyze the impact of seed and training bias on the output of an activity-conditioned graph-based variational autoencoder (VAE). Leveraging a massive, labeled dataset corresponding to the dopamine D2 receptor, our graph-based generative model is shown to excel in producing desired conditioned a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08987","kind":"arxiv","version":3},"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/2107.08987/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":"2026-07-05T03:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TI/MKudo4d+FXYZuzADxsdFf21/pt/Xm8yoPqlkKFsaeCXoW6FMnVEQ/cpsgfqd7fjEnJb/IXPZ2Ww9Bsw4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:08:09.777654Z"},"content_sha256":"54b104a248a385ac477cc15373bf8034e06bcd2db8cdd870edfadf541dbed39e","schema_version":"1.0","event_id":"sha256:54b104a248a385ac477cc15373bf8034e06bcd2db8cdd870edfadf541dbed39e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KGBRIBDDVPXGZJHXOW7A2FIU5X/bundle.json","state_url":"https://pith.science/pith/KGBRIBDDVPXGZJHXOW7A2FIU5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KGBRIBDDVPXGZJHXOW7A2FIU5X/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":"2026-08-23T18:08:09Z","links":{"resolver":"https://pith.science/pith/KGBRIBDDVPXGZJHXOW7A2FIU5X","bundle":"https://pith.science/pith/KGBRIBDDVPXGZJHXOW7A2FIU5X/bundle.json","state":"https://pith.science/pith/KGBRIBDDVPXGZJHXOW7A2FIU5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KGBRIBDDVPXGZJHXOW7A2FIU5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KGBRIBDDVPXGZJHXOW7A2FIU5X","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":"f24bea20bbf43513f2142e5ee2de8fcbe198971ed1dcae45a89aa52da5f44a55","cross_cats_sorted":["cs.LG","physics.bio-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2021-07-19T16:00:05Z","title_canon_sha256":"2aac0bdabf3b37c970a3ec32c312ac834dd9e5cd45a200b981d0a0d02e4ebefb"},"schema_version":"1.0","source":{"id":"2107.08987","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.08987","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2107.08987v3","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08987","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"KGBRIBDDVPXG","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"KGBRIBDDVPXGZJHX","created_at":"2026-07-05T03:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"KGBRIBDD","created_at":"2026-07-05T03:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:54b104a248a385ac477cc15373bf8034e06bcd2db8cdd870edfadf541dbed39e","target":"graph","created_at":"2026-07-05T03:11:13Z","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/2107.08987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application of deep learning to generative molecule design has shown early promise for accelerating lead series development. However, questions remain concerning how factors like training, dataset, and seed bias impact the technology's utility to medicine and computational chemists. In this work, we analyze the impact of seed and training bias on the output of an activity-conditioned graph-based variational autoencoder (VAE). Leveraging a massive, labeled dataset corresponding to the dopamine D2 receptor, our graph-based generative model is shown to excel in producing desired conditioned a","authors_text":"Jeffrey K. Weber, Joseph A. Morrone, Seung-gu Kang, Wendy D. Cornell","cross_cats":["cs.LG","physics.bio-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2021-07-19T16:00:05Z","title":"Analysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder -- Insights for practical AI-driven molecule generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08987","kind":"arxiv","version":3},"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":"sha256:48be8ac8ed9053319025901ab068f2e31b295f923138c3574c62536b0e5cdd97","target":"record","created_at":"2026-07-05T03:11:13Z","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":"f24bea20bbf43513f2142e5ee2de8fcbe198971ed1dcae45a89aa52da5f44a55","cross_cats_sorted":["cs.LG","physics.bio-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2021-07-19T16:00:05Z","title_canon_sha256":"2aac0bdabf3b37c970a3ec32c312ac834dd9e5cd45a200b981d0a0d02e4ebefb"},"schema_version":"1.0","source":{"id":"2107.08987","kind":"arxiv","version":3}},"canonical_sha256":"5183140463abee6ca4f775be0d1514edead002bd9cd20aeff8d3744db27bf65f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5183140463abee6ca4f775be0d1514edead002bd9cd20aeff8d3744db27bf65f","first_computed_at":"2026-07-05T03:11:13.705342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:13.705342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hxTdhbnQnlJQUqZrVQWEKy//fdKWwypVpWG49R/vv6lSagb632KSkR9dDX3APz06b5nPDBSZzoLdVVZWkbo1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:13.705734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.08987","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48be8ac8ed9053319025901ab068f2e31b295f923138c3574c62536b0e5cdd97","sha256:54b104a248a385ac477cc15373bf8034e06bcd2db8cdd870edfadf541dbed39e"],"state_sha256":"7b78e976b297b6f6abfa3ab4357fdf503a3d84555bed19f84dca3526b2c18628"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jh4t1o2ebHdhBCr4G6aYws6fdjimNOOAbrZgmWRcnvfrwzCN6swFGCKP5viwDzSHmYZQnmg54zZdNcwJ6zS1AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:08:09.783256Z","bundle_sha256":"cf0952f6e5b42d6f8b75f5dad21d255dd28556b145ef8db6fff6b85688f41099"}}