{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YVQNLN63J5ZBDTTFYHWC4S3G3","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":"2a4a04a25eced311eaf0b47291df9e39b1d7250820fdd815a39f78c043040b27","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-12-08T03:43:07Z","title_canon_sha256":"3ba6fe54edd5fcca9dbc80c80d9f70cf39edda2afc28630a9e58a2494d6c5e06"},"schema_version":"1.0","source":{"id":"2412.06847","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06847","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06847v2","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06847","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"3YVQNLN63J5Z","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"pith_short_16","alias_value":"3YVQNLN63J5ZBDTT","created_at":"2026-07-05T10:31:51Z"},{"alias_kind":"pith_short_8","alias_value":"3YVQNLN6","created_at":"2026-07-05T10:31:51Z"}],"graph_snapshots":[{"event_id":"sha256:9a4a0700680a09e76ed74b88e70a32606c134e9859424bda5f73091f90680f36","target":"graph","created_at":"2026-07-05T10:31:51Z","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/2412.06847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces M$^{3}$-20M, a large-scale Multi-Modal Molecule dataset that contains over 20 million molecules, with the data mainly being integrated from existing databases and partially generated by large language models. Designed to support AI-driven drug design and discovery, M$^{3}$-20M is 71 times more in the number of molecules than the largest existing dataset, providing an unprecedented scale that can highly benefit the training or fine-tuning of models, including large language models for drug design and discovery tasks. This dataset integrates one-dimensional SMILES, two-dime","authors_text":"Chang Jin, Han Peng, Huayang Shi, Jihong Guan, Jinxian Wang, Lexuan Wang, Shuigeng Zhou, Siyuan Guo, Wengen Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-12-08T03:43:07Z","title":"M$^{3}$-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06847","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":"sha256:2817c3c74aeabdfad3cd1db2b64c4d48d2a8e23daae7d119574bc34fb7bb6f81","target":"record","created_at":"2026-07-05T10:31:51Z","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":"2a4a04a25eced311eaf0b47291df9e39b1d7250820fdd815a39f78c043040b27","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-12-08T03:43:07Z","title_canon_sha256":"3ba6fe54edd5fcca9dbc80c80d9f70cf39edda2afc28630a9e58a2494d6c5e06"},"schema_version":"1.0","source":{"id":"2412.06847","kind":"arxiv","version":2}},"canonical_sha256":"de2b06adbeda7b908e732e0f61725b36db7ea5834ea8942ca5c314561a95c981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de2b06adbeda7b908e732e0f61725b36db7ea5834ea8942ca5c314561a95c981","first_computed_at":"2026-07-05T10:31:51.578341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:51.578341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0DsqbvqRlubhRKZr7Xk/lz4nzFbYBSuGzK/FB4DTO6DBULGrq2F7ilq0ZaavJlSW9qMfMFKQ04PofhTOvMgECA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:51.579233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06847","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2817c3c74aeabdfad3cd1db2b64c4d48d2a8e23daae7d119574bc34fb7bb6f81","sha256:9a4a0700680a09e76ed74b88e70a32606c134e9859424bda5f73091f90680f36"],"state_sha256":"4f71e927394da41ed4eb1bfc7d69c73a4f43d1cb6cf7119c6f242d96988b52dd"}