{"as_of":"2026-08-23T05:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e8ac739d0334cbf89c850a5adea418529b6d401802dbbcc358370e15b7ead59","coverage":[{"denominator":65,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":65,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:23:44.680955Z","state":"measured"},{"denominator":65,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":65,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.06847/citation-record","integrity":"/paper/2412.06847/integrity","json":"/paper/2412.06847/citation-record.json","paper":"/paper/2412.06847"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-11T20:23:44.417701Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.417701Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:a54ca8ccf27a08af80aca5f731e90b4014bbe7ca2643d3e8bbb14b0f0db1690a","observation_id":"342daa81-8659-4066-b498-dd6470753374","resolution":{"observed_at":"2026-08-11T20:23:44.417701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.577623Z","title":"Extracting structured data from organic synthesis procedures using a fine-tuned large language model","venue":null,"work_id":"aec7f435-3fc7-4bc8-a531-274a1dd73fee","year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.422831Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:e178ed9d23238104ff6c69780dc328fd4b52e505ce8131f560b8ed2c11e25160","observation_id":"07784057-0b44-410a-bc0e-1daacc8182d3","resolution":{"observed_at":"2026-08-11T20:23:45.582393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.563474Z","title":"Geom, energy-annotated molecular conformations for property prediction and molecular generation","venue":null,"work_id":"f864ee7d-b0d5-41af-b76e-359d6db6938b","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.427228Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:82c2c616f1d5ca7847602b52a44dba99077d66172f6283b2d47eee5a39ecd4b5","observation_id":"4a3b9a83-05fc-43a8-a73c-61518deea8b6","resolution":{"observed_at":"2026-08-11T20:23:45.567816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.550155Z","title":"New substructure filters for removal of pan assay interference compounds (pains) from screening libraries and for their exclusion in bioassays","venue":null,"work_id":"6d6786a9-d70a-4d98-b42b-88c99261e2a8","year":2010},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.431425Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:b6068dd8c4b674b39ea5095432814e8b7f68ade9518a8493fcd36655212b9639","observation_id":"540235d1-ff45-40f0-9c30-f81749cdef03","resolution":{"observed_at":"2026-08-11T20:23:45.554267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.537044Z","title":"Molgpt: molecular generation using a transformer-decoder model","venue":null,"work_id":"fd61080e-18eb-4a8b-9fe0-71e26fa82f3b","year":2021},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.435884Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:121361760bc75111a568dca6abd4e39c6f09b86f5699177a7fb0291f634e25af","observation_id":"be893793-b677-432f-842d-b77c9430985e","resolution":{"observed_at":"2026-08-11T20:23:45.541099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04292","last_updated":"2023-10-18T11:06:43Z","snapshot_observed_at":"2026-08-16T20:42:48.577474Z","submitted_at":"2023-10-06T14:51:17Z","title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04292","snapshot_observed_at":"2026-08-11T20:23:44.440078Z","title":"Towards foundational models for molecular learning on large-scale multi-task datasets","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.440078Z"},"links":{"cited_paper":"/paper/2310.04292","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:89593731c3c66f61061855ae5124190d1ca1cf83e24bebdd3a7442957e111d9e","observation_id":"da527c5d-ec37-45e9-ae77-8a6cbd17f570","resolution":{"observed_at":"2026-08-11T20:23:44.440078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.444692Z","title":"The properties of known drugs","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.444692Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:1d915c8e4418bee4c70653db87db2ce7632571730300ca7039c237efc2ee7a4b","observation_id":"09940e0d-5097-4bdd-adbd-2a5f517ef732","resolution":{"observed_at":"2026-08-11T20:23:44.444692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.449037Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.449037Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:6b8ec00366e3e9b967fd2744f0898b5dadc00ae8c1b83d9f31fb389b2f56d884","observation_id":"3f0c9f1b-da99-486b-aad5-4801871d6692","resolution":{"observed_at":"2026-08-11T20:23:44.449037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.506590Z","title":"Artificial intelligence for drug discovery: Resources, methods, and applications","venue":null,"work_id":"51814789-9786-4bbf-8e84-e2b21c528bd9","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.452939Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:8a88db7f6c5bde941d66438091d8c47605cf5b292ea7c317de90f49248d22f5f","observation_id":"75913119-1b1c-4923-ba9d-5e6ea9d9e5f3","resolution":{"observed_at":"2026-08-11T20:23:45.510806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.09885","last_updated":"2020-10-23T04:22:37Z","snapshot_observed_at":"2026-08-16T19:12:16.763797Z","submitted_at":"2020-10-19T21:41:41Z","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.09885","snapshot_observed_at":"2026-08-11T20:23:44.456519Z","title":"Chemberta: large-scale self-supervised pretraining for molecular property prediction","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.456519Z"},"links":{"cited_paper":"/paper/2010.09885","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:71408d1e8c8fc18fcb8ba3f63f27e9e63bd5e7df3b5ab96f059e3efe54706878","observation_id":"721c348c-1c92-48ec-97d7-f66ebb602927","resolution":{"observed_at":"2026-08-11T20:23:44.456519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.493427Z","title":"Molecular representations in ai-driven drug discovery: a review and practical guide","venue":null,"work_id":"e518d4bb-072e-4acb-a198-817625dcc65f","year":2020},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.460380Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:4bbf1aac2e479236783ac0497f4eac554f779975abce485e6bf061d2ba49cf4c","observation_id":"efe2a610-3d06-441c-a760-36516f855850","resolution":{"observed_at":"2026-08-11T20:23:45.497819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.479628Z","title":"On the art of compiling and using’drug-like’chemical fragment spaces","venue":null,"work_id":"4582b4fa-efc5-4d93-b111-173def2364d6","year":2008},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.464009Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:66c52fb0515826242cbfd3f9320749ffa2ce6ee00bc877ae7da5006faa1bfecf","observation_id":"e97d978f-01d2-41a1-b65a-5ee4159f295c","resolution":{"observed_at":"2026-08-11T20:23:45.484240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.466186Z","title":"Glm: General language model pretraining with autoregressive blank infilling","venue":null,"work_id":"d55f8d42-7174-4886-b8bd-de9a4064b680","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.467861Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:ba561f63385a9335b96fcf5081c1a2b6a0f01613b3caad11d91cbf2d9dec0fb0","observation_id":"41c05bca-f8fb-42d4-a8e3-829f766f67d5","resolution":{"observed_at":"2026-08-11T20:23:45.470561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-11T20:23:44.471361Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.471361Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:73a6f465b621b90f6fd705a4825242d06b1027b6b9ebb77b547fbf9861996dc6","observation_id":"f7126646-71b5-4ddf-b8e8-514af8053689","resolution":{"observed_at":"2026-08-11T20:23:44.471361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.452763Z","title":"Molecular structure input on the web","venue":null,"work_id":"f5850f5f-11c4-4714-b2a6-bdd3e2d9ab34","year":2010},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.475673Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:11f143b32b54a6041e1c118ba44028e0a1ab3d86ed79cd0822d71f4c4e01c0af","observation_id":"649c5fca-a46f-4de9-8e79-2747b6faa2d2","resolution":{"observed_at":"2026-08-11T20:23:45.457116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13230","last_updated":"2020-11-26T10:55:05Z","snapshot_observed_at":"2026-08-17T15:24:56.424326Z","submitted_at":"2020-11-26T10:55:05Z","title":"Molecular representation learning with language models and domain-relevant auxiliary tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13230","snapshot_observed_at":"2026-08-11T20:23:44.479766Z","title":"Molecular representation learning with language models and domain-relevant auxiliary tasks","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.479766Z"},"links":{"cited_paper":"/paper/2011.13230","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:e5bec24e2eeb919b9f402afea3a9edb9cdc17855612a3072b17ed7e7b232c83d","observation_id":"01dff2ad-aba4-4f00-8d0a-74dfdce009e8","resolution":{"observed_at":"2026-08-11T20:23:44.479766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.438721Z","title":null,"venue":null,"work_id":"7729945d-0914-4aec-8328-099d706ad5f9","year":null},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.484280Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:e7f53b3a18966faf0634af50e5ab66830690ebefe0f016129b24a8806839321a","observation_id":"ad8680e8-2070-432b-bea9-c88b45b81ac1","resolution":{"observed_at":"2026-08-11T20:23:45.443144Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.424146Z","title":"Probabilistic transformer: Modelling ambiguities and distributions for rna folding and molecule design","venue":null,"work_id":"8411bc17-4b6c-4791-af3a-018e0849d479","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.488414Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:9b83b4637b67f2ea3f49b9e4285c1f0aa4cb8b40d1312ee050efce589ecff19f","observation_id":"5dd08907-e680-4ff1-9fb5-0b1ec54e1a65","resolution":{"observed_at":"2026-08-11T20:23:45.429111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.409191Z","title":"Admetlab 3.0: an updated comprehensive online admet prediction platform enhanced with broader coverage, improved performance, api functionality and decision support","venue":null,"work_id":"256f6288-faca-4d86-b1e2-1644d44e21a1","year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.492592Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:42104e33889de4e5a75d8f966725b394c508b00b2a533c207264b46de862c7ef","observation_id":"47fceb73-e667-40e1-be9c-289ab20cbde1","resolution":{"observed_at":"2026-08-11T20:23:45.413861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.395665Z","title":"Sample efficiency matters: a benchmark for practical molecular optimization","venue":null,"work_id":"0992401b-a521-402a-aa16-7acc48da78de","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.496598Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:5e85332a4531e2d57a2a12faf2596fefce6526d01e5fca04d68feae219c95397","observation_id":"bf9b64c5-33dc-4448-842e-79ff154a2b0f","resolution":{"observed_at":"2026-08-11T20:23:45.399831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.382085Z","title":"Chembl: a large-scale bioactivity database for drug discovery","venue":null,"work_id":"82899299-6661-40c2-b15d-03aadae4bc34","year":2012},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.500932Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:83bc561db844ababc55d0b57e7cd53f78af2ea132b5a10b858d1e87c69433682","observation_id":"e753c78a-584c-41b8-80e8-e2cee12e4e44","resolution":{"observed_at":"2026-08-11T20:23:45.386159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.368545Z","title":"Prefix-tree decoding for predicting mass spectra from molecules","venue":null,"work_id":"19ca7296-108a-4f75-a45f-9018b504849d","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.504888Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:5f49bd566606a00f2fe12f48e4f11209d269a3dde239196c23b1aec451df8f38","observation_id":"47795c5b-3fb8-48c7-bebb-25752fb2b668","resolution":{"observed_at":"2026-08-11T20:23:45.373253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.354514Z","title":"Diffusing on two levels and optimizing for multiple properties: A novel approach to generating molecules with desirable properties","venue":null,"work_id":"3ffdf8d6-b923-4e9a-b3b8-50b6c9893849","year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.508912Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:005fcef9d597e1848bf5912b2bfb9b2101c44d7092de3bd8d6feb25d6f080ea0","observation_id":"c0d30177-c030-4647-b395-89f42807bad2","resolution":{"observed_at":"2026-08-11T20:23:45.359016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18365","last_updated":"2023-12-28T04:29:36Z","snapshot_observed_at":"2026-08-16T15:29:02.836233Z","submitted_at":"2023-05-27T14:17:33Z","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18365","snapshot_observed_at":"2026-08-11T20:23:44.512969Z","title":"What indeed can gpt models do in chemistry? a comprehensive benchmark on eight tasks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.512969Z"},"links":{"cited_paper":"/paper/2305.18365","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:df5c8ff161cb4330fddd100eb8c08799248ac177c2f2dcd00275fc7693c2d572","observation_id":"49abe2a6-c0e6-408c-b880-3ff61518f8f6","resolution":{"observed_at":"2026-08-11T20:23:44.512969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.517389Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.517389Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:649ce7e85dbb5f7f8b56ddbe27a1e2665cd361ec06767ead11adbd0d764a2438","observation_id":"0cb11ef7-0871-43c7-b92d-9d97eb350fb9","resolution":{"observed_at":"2026-08-11T20:23:44.517389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-20T11:47:17.477107Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-11T20:23:44.521340Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.521340Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:a8e63207b16564a64561abbfe4073ba4e954fde676366448f9e8c27dccea84a0","observation_id":"f25cfd4f-e920-4eb4-aa07-4772ebf5932a","resolution":{"observed_at":"2026-08-11T20:23:44.521340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.331264Z","title":"Principles of early drug discovery","venue":null,"work_id":"bfae3c31-f644-4d69-b56d-59c7bd706e8b","year":2011},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.525455Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:77555a43d852a066ecbc0c00fa9a8cd6c1f80b82e748d9e999c2fa57d2d3e296","observation_id":"14f42b1a-cb0e-4c26-af27-8d6c77ad801e","resolution":{"observed_at":"2026-08-11T20:23:45.335743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.317508Z","title":"Zinc- a free database of commercially available compounds for virtual screening","venue":null,"work_id":"362759e4-15f9-4fd6-8a05-a896e46a45bd","year":2005},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.529381Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:e6c85a7b06bc01fa353ea0b87f5c8b09e7d1678f49c0e840952da4256c82b924","observation_id":"a293946b-ca50-4e7b-bc96-733baf6a5d24","resolution":{"observed_at":"2026-08-11T20:23:45.322117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.303650Z","title":"Comprehensive assessment of nine target prediction web services: which should we choose for target fishing? Briefings in Bioinformatics, 24(2):bbad014, 2023","venue":null,"work_id":"ecc0c4c7-ec08-433a-acae-d3873af3997d","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.533664Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:9de8e0bd004a8a20320b4f20671b0e3b3c45fe8c5a89ed9cd0e071543706019d","observation_id":"1ec5520c-167f-48b3-b73a-8d603a777c18","resolution":{"observed_at":"2026-08-11T20:23:45.308360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.289776Z","title":"Pubchem substance and compound databases","venue":null,"work_id":"1fd13d0f-6925-41cc-b6f1-2de10005a6a7","year":2016},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.538396Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:ef4aeb83ea2c9848c77f2b122057777545e8c80bbf13a57ad521c626a0eb4e8f","observation_id":"5f5a8207-be54-4c65-b79f-5b912095d582","resolution":{"observed_at":"2026-08-11T20:23:45.294226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.275861Z","title":"Molecule generation by principal subgraph mining and assembling","venue":null,"work_id":"642a5451-0100-4c90-91d6-157acc143bec","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.542618Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:ccebb1bad837b4b6abfa674a27a2e16a07edf55435672b1e7d55d295823dade7","observation_id":"841adf63-1e00-455b-98fb-8af23f1e5175","resolution":{"observed_at":"2026-08-11T20:23:45.280413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.262298Z","title":"Natural questions: a benchmark for question answering research","venue":null,"work_id":"d69ba3b8-e3a4-435d-9b92-58f7a00388ea","year":2019},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.546773Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:2dcf22d46b4057ae50e0e96879acc91a0b370af25cb4b1abde5020e07af094c9","observation_id":"54518682-161b-469e-8369-aa872adfeeda","resolution":{"observed_at":"2026-08-11T20:23:45.266579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.249660Z","title":"Rdkit documentation","venue":null,"work_id":"54960a9d-0944-46ae-90f0-b9ec5ffd17f4","year":2013},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.550694Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:a6d84335cfb604c530f9492d85655d8a141cae07a59cdc58a6711ac16679d00d","observation_id":"621179b8-bc8a-4ce7-952c-22a20fe797c1","resolution":{"observed_at":"2026-08-11T20:23:45.253541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.235371Z","title":"Effective drug–target interaction prediction with mutual interaction neural network","venue":null,"work_id":"e8d72b49-6c73-486d-a653-48ce68cfefa8","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.554807Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:db9eff7f8a71c9b5c05598a60f05fc138026ac029dcc5e334a5d45d0ac70a571","observation_id":"6dfaa0c4-00aa-4847-8198-a652fb9157e1","resolution":{"observed_at":"2026-08-11T20:23:45.240334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.219700Z","title":"Deep learning methods for molecular representation and property prediction","venue":null,"work_id":"51801e60-6aee-466d-99db-552e376a2c26","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.558838Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:f55d732f22fb71a1a10213a031dca3bd5996516a94cc1abad4ffcad00c098f09","observation_id":"56f2991d-75e6-40e8-bacf-15d5d5f68835","resolution":{"observed_at":"2026-08-11T20:23:45.224604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.204847Z","title":"Git- mol: A multi-modal large language model for molecular science with graph, image, and text","venue":null,"work_id":"1abff81b-cebf-4058-b658-58a0f4b2f454","year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.563033Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:5d4d7fbc27c529462412e8069a12de356b8bc25ac99693861b2cb49949a118a4","observation_id":"3f9df5aa-31fd-46c6-818d-7eeeb29eeae7","resolution":{"observed_at":"2026-08-11T20:23:45.209398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.190678Z","title":"A quantitative analysis of knowledge-learning preferences in large language models in molecular science","venue":null,"work_id":"05e55fb4-a4a5-4247-8fbf-bd908f1ab541","year":2025},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.566716Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:abf885e389726e7390aa145ceffd232d07aa8ae9b7cf910ed5935a290c604566","observation_id":"6fe094ad-371e-494d-9022-476eaa1be388","resolution":{"observed_at":"2026-08-11T20:23:45.195249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.176534Z","title":"A group symmetric stochastic differential equation model for molecule multi-modal pretraining","venue":null,"work_id":"a6c3d68d-a1f7-47fd-b3e4-0d1ee796760c","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.570481Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:e4748d240468d1284dcbd2ac016d37c07b2ac8fb545b93bbc4e5416d4160068f","observation_id":"251e7753-0bf4-43ef-89f9-a2d3aae5681a","resolution":{"observed_at":"2026-08-11T20:23:45.181022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.162487Z","title":"Multi-modal molecule structure–text model for text-based retrieval and editing","venue":null,"work_id":"edd4bace-5be2-4d8b-89fe-b60398bc3b53","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.574198Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:a91ea781c4b391026a63c6ceae52e6b2971d3355325c7b3f948f9b6d082b0655","observation_id":"9d29448a-ca29-491f-8fa9-c21c3a1ae7b9","resolution":{"observed_at":"2026-08-11T20:23:45.167047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.148031Z","title":"Dynamicbind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model","venue":null,"work_id":"2c59d889-5f8f-41b2-afa4-e3950fb4aa01","year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.577971Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:cdd5f159ca0265e81341ab03cbae6560d9a816c68004b9b73bd9fc1abd0154a9","observation_id":"4c45f5c0-172e-4c23-8bae-54bcaed832c4","resolution":{"observed_at":"2026-08-11T20:23:45.152949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.02229","last_updated":"2022-12-06T16:53:52Z","snapshot_observed_at":"2026-08-18T15:27:54.928737Z","submitted_at":"2022-11-18T18:11:27Z","title":"GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.02229","snapshot_observed_at":"2026-08-11T20:23:44.581668Z","title":"Gps++: An optimised hybrid mpnn/transformer for molecular property prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.581668Z"},"links":{"cited_paper":"/paper/2212.02229","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:d2db77a2f1a4a69ace8da6224d5745826e148a89ccfc5a6293e5b94b76a31e07","observation_id":"4cceecc7-5b90-41e8-8fb5-7432a365fcb6","resolution":{"observed_at":"2026-08-11T20:23:44.581668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08730","last_updated":"2018-06-20T16:39:26Z","snapshot_observed_at":"2026-08-17T06:16:47.122449Z","submitted_at":"2018-06-20T16:39:26Z","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08730","snapshot_observed_at":"2026-08-11T20:23:44.585913Z","title":"The natural language decathlon: Multitask learning as question answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.585913Z"},"links":{"cited_paper":"/paper/1806.08730","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:4f4b127a908e360f008a585e2752bebdc318e939bdd74ebd826a4d9658b3dc70","observation_id":"c82e1d9d-0496-4e2c-8a02-5956d600d4ab","resolution":{"observed_at":"2026-08-11T20:23:44.585913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.03426","last_updated":"2020-09-18T01:56:41Z","snapshot_observed_at":"2026-08-02T15:32:07.466568Z","submitted_at":"2018-02-09T19:39:33Z","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.03426","snapshot_observed_at":"2026-08-11T20:23:44.590198Z","title":"Umap: Uniform manifold approximation and projection for dimension reduction","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.590198Z"},"links":{"cited_paper":"/paper/1802.03426","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:590b0a608ae5c8cedbfc09855649d857759b3a0ca1be610580ac5d3de7025a78","observation_id":"b0170017-0290-40f0-be88-91d6fdf5b6df","resolution":{"observed_at":"2026-08-11T20:23:44.590198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.594107Z","title":"Open babel: An open chemical toolbox","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.594107Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:bfdb64771381e780c70e52e9e1bc5ed68cc0b3a6fb68a159648212ca20d93bdb","observation_id":"a81f9f22-da2e-41ec-95ab-a0e3a97c388b","resolution":{"observed_at":"2026-08-11T20:23:44.594107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.598573Z","title":"Training language models to follow instructions with human feedback","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.598573Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:4b6fdbca4522a0966fc4e080f39bbdabe224874692fd847ff8174f51b9dc39bd","observation_id":"1781459a-1db6-4cbb-86a8-a95cc1426ad5","resolution":{"observed_at":"2026-08-11T20:23:44.598573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.116184Z","title":"Molecular sets (moses): a benchmarking platform for molecular generation models","venue":null,"work_id":"46a8bd99-8843-4b6e-a976-3af147411032","year":2020},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.602675Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:7a28c1095b1307f5d716eddb085be01d7dd5597508e67e3323856627fd08415a","observation_id":"4f54f228-a706-48b9-81ad-66745f0c1083","resolution":{"observed_at":"2026-08-11T20:23:45.120233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.08771","last_updated":"2018-09-12T14:13:33Z","snapshot_observed_at":"2026-08-14T19:22:47.534657Z","submitted_at":"2018-04-23T22:54:55Z","title":"A Call for Clarity in Reporting BLEU Scores","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.08771","snapshot_observed_at":"2026-08-11T20:23:44.606669Z","title":"A call for clarity in reporting bleu scores","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.606669Z"},"links":{"cited_paper":"/paper/1804.08771","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:f366efe8a2530deeba892baa324963143e32a9b19e5e0483922c60d3e1c0634f","observation_id":"ead41d8c-d4be-4397-bfd2-fd556f1f34f9","resolution":{"observed_at":"2026-08-11T20:23:44.606669Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.103143Z","title":"Quantum chemistry structures and properties of 134 kilo molecules","venue":null,"work_id":"adc5505a-ae23-4651-85eb-c7b374071b31","year":2014},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.610888Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:2323dd6ffb26a907094a3b4fcbc96ba20129a7e0038d528e22abbf31e0aa38fd","observation_id":"6bbaef10-8a6b-4ec7-b30d-21d901af7f35","resolution":{"observed_at":"2026-08-11T20:23:45.107326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.088620Z","title":"Self-supervised graph transformer on large-scale molecular data","venue":null,"work_id":"9d1c1b4c-ff51-4a91-a84a-ced92a139c5d","year":2020},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.615058Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:bbb32417aeebf9e4806da338b71edbd411086a388ffc19cf7487cb079f38174d","observation_id":"61ba9ff8-b6a9-452e-b6ea-31ed34c468f7","resolution":{"observed_at":"2026-08-11T20:23:45.093471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.074301Z","title":"Enumeration of 166 billion organic small molecules in the chemical universe database gdb-17","venue":null,"work_id":"a6488b37-e3ae-40e1-bd78-2ae23055cd7c","year":2012},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.619166Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:15f1338b1efdbbc920bd38618b779e9bf20df846337e8d377b5432fa976eca74","observation_id":"e0f1d78f-a1f0-4144-946f-d3fbb3fb7c87","resolution":{"observed_at":"2026-08-11T20:23:45.078940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.060084Z","title":"A comprehensive map of molecular drug targets","venue":null,"work_id":"c3add7bf-d879-4c7d-9057-4d90688a6f65","year":2017},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.623320Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:ff75ba1cd0d0d0a8ebd93b27f880a4e19a8e5388d411b8a207be5aa0453406c1","observation_id":"dea4ce02-d5a9-41c0-abf2-d120a41abfb7","resolution":{"observed_at":"2026-08-11T20:23:45.064868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.627447Z","title":"Equivariant flow matching with hybrid probability transport for 3d molecule generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.627447Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:fb6681a5e02d9abb2d4575a14cf9d41923884279cf223221eda0f80bf5e35ef6","observation_id":"54c61ef4-6e38-44fe-b54e-f7a1e7db5ae7","resolution":{"observed_at":"2026-08-11T20:23:44.627447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.036032Z","title":"Evidence-based absorption, distribution, metabolism, excretion (adme) and its interplay with alternative toxicity methods","venue":null,"work_id":"75854e1d-4b35-4073-9af3-ac7c8c341d8d","year":2016},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.631587Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:939ac4a83028e7b9d7ad6237d430d24c82c0da793ce224abc5a2f9b130e52fd1","observation_id":"64e0b337-53db-4f52-aed0-59a572294ecf","resolution":{"observed_at":"2026-08-11T20:23:45.040899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-08-16T09:50:11.319379Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-11T20:23:44.635762Z","title":"Glue: A multi- task benchmark and analysis platform for natural language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.635762Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:53596b305bec944340ce16d638276afb35aed01a25bc3235b192f92efb31e345","observation_id":"f6d4ca9e-25f1-440d-a945-f02d77584ce3","resolution":{"observed_at":"2026-08-11T20:23:44.635762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.021590Z","title":"Deep learning approaches for de novo drug design: An overview","venue":null,"work_id":"870d330e-430d-4d1b-b445-e9f1798a8c8b","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.640563Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:bc05264f2a302b4fc070330fb90ad636867bb95e229fd3989e239a08bc0f71e3","observation_id":"aecb832e-a49c-447d-a200-4cd90ae35831","resolution":{"observed_at":"2026-08-11T20:23:45.026238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:45.007446Z","title":"Multitask joint strategies of self- supervised representation learning on biomedical networks for drug discovery","venue":null,"work_id":"7d05f2c7-deca-48c4-9f0b-6dbc5573c976","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.644567Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:daacc45e4453f97e3d4086af43f77860b9e668b01669bbaf61860fb7b8127e24","observation_id":"cacbdd2e-2d84-4e15-801e-dd8fcbb64373","resolution":{"observed_at":"2026-08-11T20:23:45.011938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16666","last_updated":"2024-04-19T13:19:53Z","snapshot_observed_at":"2026-08-18T11:15:30.433577Z","submitted_at":"2023-11-28T10:28:35Z","title":"MultiModal-Learning for Predicting Molecular Properties: A Framework Based on Image and Graph Structures","version":2},"cited_work":{"arxiv_id":"2311.16666","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.16666","snapshot_observed_at":"2026-08-11T20:23:44.715125Z","title":"MultiModal-Learning for Predicting Molecular Properties: A Framework Based on Image and Graph Structures","venue":"cs.LG","work_id":"46136db9-369e-4655-9a88-a25c429d755d","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.648543Z"},"links":{"cited_paper":"/paper/2311.16666","citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:490d10a21f2178f9ec562f375f2033c2d9ec6ce0d0da3936f72bfb811265c7fb","observation_id":"820a7390-bed4-4b94-8261-a18a73d3c97d","resolution":{"observed_at":"2026-08-11T20:23:44.721154Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.993773Z","title":"Moleculenet: a benchmark for molecular machine learning","venue":null,"work_id":"628c5364-8525-4396-b5dc-bece2e431ff1","year":2018},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.652793Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:3070aab5a63d951d0781b65e1e44278f7f84bbe85579f9e918a1c2b0fca32cb6","observation_id":"49787b15-2cd1-409a-9e6c-2db199eccf78","resolution":{"observed_at":"2026-08-11T20:23:44.998084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.980195Z","title":"Hit and lead discovery with explorative rl and fragment-based molecule generation","venue":null,"work_id":"90f40f40-de00-4c13-b96f-202d4ec73620","year":2021},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.656760Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:28cb0b8c0eb0ae0848c90719c465f77e6251c5a04543bb0749f810403a6cb1f9","observation_id":"82e11962-525f-4820-a242-e8aebac133ff","resolution":{"observed_at":"2026-08-11T20:23:44.984715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.965472Z","title":"Quandb: a quantum chemical property database towards enhancing 3d molecular representation learning","venue":null,"work_id":"eefe3db4-171b-4c37-97c0-0d47a6bfe5cb","year":2024},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.660771Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:12acc8c0270b788fa351e9ee029bec56e8896062a45baa030760a3a3441e076e","observation_id":"78188a9b-8257-4aaa-b1d1-ce8cf87a8468","resolution":{"observed_at":"2026-08-11T20:23:44.969962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.950769Z","title":"Drugassist: A large language model for molecule optimization","venue":null,"work_id":"46d28b38-1ed0-493d-bd84-2ca461ccc44f","year":2025},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.665090Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:fe2e31bb72375b4d8830e20b51a2b31d61f6a47a67c6064f7ebb5834468d7e79","observation_id":"ff217361-f230-4c9e-9109-eb2ccbf8b6d9","resolution":{"observed_at":"2026-08-11T20:23:44.955140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.935973Z","title":"A unified drug–target interaction prediction framework based on knowledge graph and recommendation system","venue":null,"work_id":"e8339eae-14b2-4444-8fa4-dbd571b04584","year":2021},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.669042Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:45f7b3898672ef2e2b9beb6d8e5ba53ac767d7de21c8b010760df3a5a009f1a4","observation_id":"77d442c8-e3be-4e62-9325-205d4e5a274d","resolution":{"observed_at":"2026-08-11T20:23:44.941330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.922286Z","title":"Multimodal molecular pretraining via modality blending","venue":null,"work_id":"ba45bd80-9e03-4902-af87-206964a1008d","year":2023},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.673241Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:80e59e582ef2be400237fa94f9ae494504215a1f7b407f882dd7ff06179ecc61","observation_id":"1ba6f37b-9012-4b37-8d24-930721ef07cd","resolution":{"observed_at":"2026-08-11T20:23:44.926749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.908671Z","title":"Moflow: an invertible flow model for generating molecular graphs","venue":null,"work_id":"3f6e8bf0-0eb1-4efa-87cc-872ae4449fbb","year":2020},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.677270Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:4aab2c2cb4c8ae1415e1507d711e1c9d0c893b11bc394b41f523da4dfe5e11e4","observation_id":"85fd23a8-12c8-49d1-902c-8a6fb97c0548","resolution":{"observed_at":"2026-08-11T20:23:44.913107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:23:44.894090Z","title":"A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionals","venue":null,"work_id":"9ef29109-7167-41a9-815a-0079ede0030a","year":2022},"citing_paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:44.680955Z"},"links":{"citing_paper":"/paper/2412.06847"},"observation_digest":"sha256:252e6c594fc588edfaba340d3131ce3b0dec595e48b6d954b87a1c5816d5fd8c","observation_id":"1cf5ca1f-428b-49a2-9119-4089a62eb854","resolution":{"observed_at":"2026-08-11T20:23:44.898807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.06847","last_updated":"2025-03-16T12:37:49Z","latest_version":2,"primary_category":"q-bio.QM","snapshot_observed_at":"2026-08-16T19:35:51.758797Z","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"},"reference_resolution":{"displayed":65,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":45},"total_outbound_references":65},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 0 inbound Pith citation observations for arXiv:2412.06847."}