{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SCLE2WS5K5UMFKJLNZ7YB2RJUW","short_pith_number":"pith:SCLE2WS5","canonical_record":{"source":{"id":"2405.03799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T19:09:37Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"038861f4d090f4f443fe9077d2e4804dafe82f9651a7d622d11b2ac086cdac55","abstract_canon_sha256":"3873089906b964e0961bbec1e8e86e1ed9531a0489ed21dce26bc5b3e01d9a57"},"schema_version":"1.0"},"canonical_sha256":"90964d5a5d5768c2a92b6e7f80ea29a59239c7ce499b597bf22e10a7eb8dd2de","source":{"kind":"arxiv","id":"2405.03799","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03799","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03799v1","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03799","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"SCLE2WS5K5UM","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"SCLE2WS5K5UMFKJL","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"SCLE2WS5","created_at":"2026-07-05T08:16:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SCLE2WS5K5UMFKJLNZ7YB2RJUW","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T19:09:37Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"038861f4d090f4f443fe9077d2e4804dafe82f9651a7d622d11b2ac086cdac55","abstract_canon_sha256":"3873089906b964e0961bbec1e8e86e1ed9531a0489ed21dce26bc5b3e01d9a57"},"schema_version":"1.0"},"canonical_sha256":"90964d5a5d5768c2a92b6e7f80ea29a59239c7ce499b597bf22e10a7eb8dd2de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:10.920539Z","signature_b64":"uHqsoU70wKAXATv8nTskg3IvTv6q5+H+2QwzHgYevteJVHZGyacplBUFKLdl0hUoE4rl8zMGSL66HnG3aPjdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90964d5a5d5768c2a92b6e7f80ea29a59239c7ce499b597bf22e10a7eb8dd2de","last_reissued_at":"2026-07-05T08:16:10.920064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:10.920064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03799","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":"2026-07-05T08:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMD8m4FIM2uKgklHZVWTzpfg4lBuNMvnVsHWE6Uotlom4ifFtC29OqZxJSSQCWGZB0honTso4hzSi9vGf9NPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:26:41.305293Z"},"content_sha256":"25f95c4add9ed06ecf7535dec08679e5d017ba203658a16eed053559162d822c","schema_version":"1.0","event_id":"sha256:25f95c4add9ed06ecf7535dec08679e5d017ba203658a16eed053559162d822c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SCLE2WS5K5UMFKJLNZ7YB2RJUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic Data from Diffusion Models Improve Drug Discovery Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Anita Layton, Ashish Saragadam, Bing Hu, Helen Chen","submitted_at":"2024-05-06T19:09:37Z","abstract_excerpt":"Artificial intelligence (AI) is increasingly used in every stage of drug development. Continuing breakthroughs in AI-based methods for drug discovery require the creation, improvement, and refinement of drug discovery data. We posit a new data challenge that slows the advancement of drug discovery AI: datasets are often collected independently from each other, often with little overlap, creating data sparsity. Data sparsity makes data curation difficult for researchers looking to answer key research questions requiring values posed across multiple datasets. We propose a novel diffusion GNN mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03799","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/2405.03799/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":"2026-07-05T08:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nA0b6jj3EOBjx6ke4d9COTQolD3NBn+znsZRRqrKtCXOSQkeFCPO2Lqq93SmP1dGbbOynD2W5M/6E0UoxwoEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:26:41.305860Z"},"content_sha256":"b1beec0164a8ab72ab84bea33e4c472bf9195fef76076fe3573705a85dd18b0d","schema_version":"1.0","event_id":"sha256:b1beec0164a8ab72ab84bea33e4c472bf9195fef76076fe3573705a85dd18b0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SCLE2WS5K5UMFKJLNZ7YB2RJUW/bundle.json","state_url":"https://pith.science/pith/SCLE2WS5K5UMFKJLNZ7YB2RJUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SCLE2WS5K5UMFKJLNZ7YB2RJUW/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":"2026-08-20T04:26:41Z","links":{"resolver":"https://pith.science/pith/SCLE2WS5K5UMFKJLNZ7YB2RJUW","bundle":"https://pith.science/pith/SCLE2WS5K5UMFKJLNZ7YB2RJUW/bundle.json","state":"https://pith.science/pith/SCLE2WS5K5UMFKJLNZ7YB2RJUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SCLE2WS5K5UMFKJLNZ7YB2RJUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SCLE2WS5K5UMFKJLNZ7YB2RJUW","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":"3873089906b964e0961bbec1e8e86e1ed9531a0489ed21dce26bc5b3e01d9a57","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T19:09:37Z","title_canon_sha256":"038861f4d090f4f443fe9077d2e4804dafe82f9651a7d622d11b2ac086cdac55"},"schema_version":"1.0","source":{"id":"2405.03799","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03799","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03799v1","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03799","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"SCLE2WS5K5UM","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"SCLE2WS5K5UMFKJL","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"SCLE2WS5","created_at":"2026-07-05T08:16:10Z"}],"graph_snapshots":[{"event_id":"sha256:b1beec0164a8ab72ab84bea33e4c472bf9195fef76076fe3573705a85dd18b0d","target":"graph","created_at":"2026-07-05T08:16:10Z","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/2405.03799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial intelligence (AI) is increasingly used in every stage of drug development. Continuing breakthroughs in AI-based methods for drug discovery require the creation, improvement, and refinement of drug discovery data. We posit a new data challenge that slows the advancement of drug discovery AI: datasets are often collected independently from each other, often with little overlap, creating data sparsity. Data sparsity makes data curation difficult for researchers looking to answer key research questions requiring values posed across multiple datasets. We propose a novel diffusion GNN mod","authors_text":"Anita Layton, Ashish Saragadam, Bing Hu, Helen Chen","cross_cats":["cs.AI","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T19:09:37Z","title":"Synthetic Data from Diffusion Models Improve Drug Discovery Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03799","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":"sha256:25f95c4add9ed06ecf7535dec08679e5d017ba203658a16eed053559162d822c","target":"record","created_at":"2026-07-05T08:16:10Z","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":"3873089906b964e0961bbec1e8e86e1ed9531a0489ed21dce26bc5b3e01d9a57","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T19:09:37Z","title_canon_sha256":"038861f4d090f4f443fe9077d2e4804dafe82f9651a7d622d11b2ac086cdac55"},"schema_version":"1.0","source":{"id":"2405.03799","kind":"arxiv","version":1}},"canonical_sha256":"90964d5a5d5768c2a92b6e7f80ea29a59239c7ce499b597bf22e10a7eb8dd2de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90964d5a5d5768c2a92b6e7f80ea29a59239c7ce499b597bf22e10a7eb8dd2de","first_computed_at":"2026-07-05T08:16:10.920064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:10.920064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uHqsoU70wKAXATv8nTskg3IvTv6q5+H+2QwzHgYevteJVHZGyacplBUFKLdl0hUoE4rl8zMGSL66HnG3aPjdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:10.920539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03799","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25f95c4add9ed06ecf7535dec08679e5d017ba203658a16eed053559162d822c","sha256:b1beec0164a8ab72ab84bea33e4c472bf9195fef76076fe3573705a85dd18b0d"],"state_sha256":"5a52f0bcf85c97a89c1dff91a19f7671c7db1b99ddb583d40dde232bfd9f954a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1UtgARV1STwez0an4djFvlPRPD6HVGOWUwM7DQ+3UdH2RwElG6peui8FcgLf/ZAhw2BwQdB4iS72YauoXzMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:26:41.309447Z","bundle_sha256":"a4fcba0b257e96e5055aeb69d442e6038ca0a4a0a214f2e910eb113f3adc9c59"}}