{"as_of":"2026-08-09T06:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:29cbbb3652a01c89f36fb334be9927aee0d52826d8b257d8d7e18d8db87a626c","coverage":[{"denominator":188,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:45:57.493434Z","state":"measured"},{"denominator":106,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":106,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T08:48:26.638924Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T21:06:13.646446Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20743","snapshot_observed_at":"2026-08-04T08:48:26.638924Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.18860","last_updated":"2025-10-21T17:53:56Z","snapshot_observed_at":"2026-08-09T01:41:22.629913Z","submitted_at":"2025-10-21T17:53:56Z","title":"An Encoder-Decoder Foundation Chemical Language Model for Generative Polymer Design","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T08:48:26.638924Z"},"links":{"cited_paper":"/paper/2506.20743","citing_paper":"/paper/2510.18860"},"observation_digest":"sha256:3d2ec6a2c86ee49ab22c5c9ebccaf27c782de07460da8d135c6d9fb2f90ffd78","observation_id":"fb115e51-6f44-4aed-83d7-db00cedcfdf8","resolution":{"observed_at":"2026-08-04T08:48:26.638924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20743","snapshot_observed_at":"2026-08-02T23:41:44.325186Z","title":"A survey of AI for materials science: Foundation models, LLM agents, datasets, and tools.CoRR, abs/2506.20743, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.12984","last_updated":"2026-05-30T12:51:16Z","snapshot_observed_at":"2026-08-08T22:51:28.920174Z","submitted_at":"2026-02-13T14:58:18Z","title":"SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T23:41:44.325186Z"},"links":{"cited_paper":"/paper/2506.20743","citing_paper":"/paper/2602.12984"},"observation_digest":"sha256:6783c9f56c56474510727565c1016680b3adc8e7538e0048b3ff1cfa1e1ac967","observation_id":"51aa645c-fae6-4fa5-a76c-97b7b2b589f8","resolution":{"observed_at":"2026-08-02T23:41:44.325186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"cited_work":{"arxiv_id":"2506.20743","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.20743","snapshot_observed_at":"2026-07-01T21:06:13.646446Z","title":"A survey of ai for materials science: Foundation models, llm agents, datasets, and tools","venue":null,"work_id":"495fa3e3-c26e-4297-8336-6a2e9e177fcc","year":2025},"citing_paper":{"arxiv_id":"2604.11229","last_updated":"2026-04-13T09:29:55Z","snapshot_observed_at":"2026-08-08T16:18:57.986873Z","submitted_at":"2026-04-13T09:29:55Z","title":"RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T16:07:18.732576Z"},"links":{"cited_paper":"/paper/2506.20743","citing_paper":"/paper/2604.11229"},"observation_digest":"sha256:93bec296b28a1002f64ac98efbadbf486f332ce94817d1490d6370a721e14e4b","observation_id":"45f94dee-6ed4-4db1-b62c-dc73acf0319d","resolution":{"observed_at":"2026-05-11T09:16:04.690204Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"cited_work":{"arxiv_id":"2506.20743","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.20743","snapshot_observed_at":"2026-07-01T21:06:13.646446Z","title":"A survey of ai for materials science: Foundation models, llm agents, datasets, and tools","venue":null,"work_id":"495fa3e3-c26e-4297-8336-6a2e9e177fcc","year":2025},"citing_paper":{"arxiv_id":"2605.31495","last_updated":"2026-05-29T16:16:30Z","snapshot_observed_at":"2026-08-07T22:59:14.265315Z","submitted_at":"2026-05-29T16:16:30Z","title":"General-purpose LLMs as Constrained Crystal Composition Generators","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T21:53:29.062019Z"},"links":{"cited_paper":"/paper/2506.20743","citing_paper":"/paper/2605.31495"},"observation_digest":"sha256:5dac902aee0aa8249dc251e81092778e57366b6c93a061bd2950294a02172aeb","observation_id":"a409af16-0446-4735-a8b7-8090f9a846d8","resolution":{"observed_at":"2026-07-01T19:56:11.230832Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"cited_work":{"arxiv_id":"2506.20743","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.20743","snapshot_observed_at":"2026-07-01T21:06:13.646446Z","title":"A survey of ai for materials science: Foundation models, llm agents, datasets, and tools","venue":null,"work_id":"495fa3e3-c26e-4297-8336-6a2e9e177fcc","year":2025},"citing_paper":{"arxiv_id":"2606.01012","last_updated":"2026-05-31T05:04:03Z","snapshot_observed_at":"2026-07-06T23:41:39.172310Z","submitted_at":"2026-05-31T05:04:03Z","title":"Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T17:30:28.329639Z"},"links":{"cited_paper":"/paper/2506.20743","citing_paper":"/paper/2606.01012"},"observation_digest":"sha256:4c66fdcaf233ca3b5e807c22a5db033b50257ee6b9143a9eba9b9d8af7d8dffe","observation_id":"38ef3b8f-fd53-4f9f-9abe-69019a8b3452","resolution":{"observed_at":"2026-07-01T21:06:13.648123Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20743","snapshot_observed_at":"2026-07-14T12:06:28.342674Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.10388","last_updated":"2026-07-11T16:35:14Z","snapshot_observed_at":"2026-08-09T00:25:30.976841Z","submitted_at":"2026-07-11T16:35:14Z","title":"The evolution of AI from image interpretation toward scientific inference in nanoparticle electron microscopy","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-14T12:06:28.342674Z"},"links":{"cited_paper":"/paper/2506.20743","citing_paper":"/paper/2607.10388"},"observation_digest":"sha256:e104794c5070d03e24939b4c3fff646e6e6331903ff18fd33737834fbeca80ba","observation_id":"08ff4769-c6ed-4edc-b29d-2d5ccbb8f7c2","resolution":{"observed_at":"2026-07-14T12:06:28.342674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.20743/citation-record","integrity":"/paper/2506.20743/integrity","json":"/paper/2506.20743/citation-record.json","paper":"/paper/2506.20743"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:45:49.042703Z","title":"Foundation models for materials discovery–current state and future directions.npj Computational Materials, 11(1):61, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.042703Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:c3e99fdf5225247f89eedee1662efaa482c065e75b47f8d6dd8a18f8f493005a","observation_id":"de85b6d5-007e-4032-9732-33ca316ce060","resolution":{"observed_at":"2026-08-06T22:45:49.042703Z","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":"2026-08-06T22:45:49.102968Z","title":"Crystalline material discovery in the era of artificial intelligence.arXiv preprint arXiv:2408.08044, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.102968Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:f5a4a272ac43bfc83a334eb69fefb0230cf8776ac08700d5b7a7c569ea84848c","observation_id":"d8b5ccd7-5672-4fdf-a036-8c1cfb9a21da","resolution":{"observed_at":"2026-08-06T22:45:49.102968Z","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":"2026-08-06T22:45:49.158973Z","title":"Ai-driven inverse design of materials: Past, present and future.Chinese Physics Letters, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.158973Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:49470e71dec795bf7ce745151869ecccf5b4d6cb6ce1aef8ca8233fc0e7b8b3a","observation_id":"abd20430-5f03-42fd-89f6-b5ca9b7fc3f9","resolution":{"observed_at":"2026-08-06T22:45:49.158973Z","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":"2026-08-06T22:45:49.220492Z","title":"A review of large language models and autonomous agents in chemistry.Chemical Science, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.220492Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:68eaa7056c093523d862a1b03f0408c4b37be4b69836c2f129dba646d3c93d93","observation_id":"81e95799-2177-451e-b04c-e5500609b328","resolution":{"observed_at":"2026-08-06T22:45:49.220492Z","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":"2026-08-06T22:45:49.269793Z","title":"A strategic approach to machine learning for material science: how to tackle real-world challenges and avoid pitfalls.Chemistry of Materials, 34(17): 7650–7665, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.269793Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:12e94a073c678c56707d87439f23adffae4f33eef2f3faa8bfd5fa8c58476b94","observation_id":"c9e68cec-296d-4efa-966c-39d6d9a51c0a","resolution":{"observed_at":"2026-08-06T22:45:49.269793Z","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":"2026-08-06T22:45:49.310184Z","title":"Scope of machine learning in materials research—a review.Applied Surface Science Advances, 18:100523, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.310184Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b6fde0e677271e165deae4f7b4071ab73c20d2f2beaef50637b48f6a7c8ef756","observation_id":"daf25ad4-a0bf-495b-8005-def41ca670cf","resolution":{"observed_at":"2026-08-06T22:45:49.310184Z","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":"2026-08-06T22:45:49.407677Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.407677Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:15f1a98fedde0aa9a22aa6b8744456696284fd04f9015d32104f7ca5a37c9d7a","observation_id":"3e484c85-3b16-4d86-83f8-767477e8eb0f","resolution":{"observed_at":"2026-08-06T22:45:49.407677Z","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":"2026-08-06T22:45:49.466208Z","title":"Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.466208Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:98d798c13e30e6936ac3cb896622ed0924cff2a91e565342cb8741a1b9074b3a","observation_id":"18eafc7f-dc03-47fd-bc76-7b8cd0b0b35e","resolution":{"observed_at":"2026-08-06T22:45:49.466208Z","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":"2026-08-06T22:45:49.557945Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.557945Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:127e4035811509878e3a6b026d86a53ac688327e961c2f4f622bb93b79978850","observation_id":"f7c1976f-8591-45c8-99b2-af8564e4e6c6","resolution":{"observed_at":"2026-08-06T22:45:49.557945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","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":"2026-08-06T22:45:49.650742Z","title":"Gpt-4 technical report.arXiv preprint arXiv:2303.08774, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.650742Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:db9d493788b4682d53f8f66b90411796e8808c59c2996187c9724f1288174f1a","observation_id":"f003670e-ecb4-4e43-aee3-750bb56e4993","resolution":{"observed_at":"2026-08-06T22:45:49.650742Z","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":"2026-08-06T22:45:49.744243Z","title":"Palm: Scaling language modeling with pathways.Journal of Machine Learning Research, 24(240):1–113, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.744243Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:5d295e0cb13d06a8aad02292830d7123e5acef2d01ad0331b9bf8b015f7c20e0","observation_id":"592669b5-2cae-4d1f-a682-df699c04fe9b","resolution":{"observed_at":"2026-08-06T22:45:49.744243Z","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":"2026-08-06T22:45:49.814048Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.814048Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:a2fd1da48ed5686ba092bbd7aea27a6d6e9e7bf6ea889a050f57043aa8c65d40","observation_id":"96278f75-5473-46c6-be09-19f3077321e4","resolution":{"observed_at":"2026-08-06T22:45:49.814048Z","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":"2026-08-06T22:45:49.906861Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.906861Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:e79ccce06b77e79e4e13cc957899441338e27f5a7d46f2ab98df3d2ffb78acdc","observation_id":"a3e4ee5b-5262-4761-a74f-6845de595cfd","resolution":{"observed_at":"2026-08-06T22:45:49.906861Z","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":"2026-08-06T22:45:49.981683Z","title":"Scaling deep learning for materials discovery.Nature, 624(7990):80–85, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:49.981683Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:a7dc31f2f94929221b7f6d1ba0abb7725d3c264bee4ba02b0730b31419d975c8","observation_id":"b9b6a810-4441-4cbf-84c2-efa320cb212b","resolution":{"observed_at":"2026-08-06T22:45:49.981683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04967","last_updated":"2024-05-10T16:49:52Z","snapshot_observed_at":"2026-08-06T05:52:39.645210Z","submitted_at":"2024-05-08T11:13:30Z","title":"MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.04967","snapshot_observed_at":"2026-08-06T22:45:50.063999Z","title":"Mattersim: A deep learning atomistic model across elements, temperatures and pressures","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.063999Z"},"links":{"cited_paper":"/paper/2405.04967","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:04b63a0a3808103766d401811f591427c037f2e81b60e5c2b07a5b2c4dd8100f","observation_id":"fc9edab3-c646-4fec-a8bd-492f73d349d4","resolution":{"observed_at":"2026-08-06T22:45:50.063999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.00096","last_updated":"2025-09-04T13:50:21Z","snapshot_observed_at":"2026-08-04T22:35:15.439821Z","submitted_at":"2023-12-29T23:08:59Z","title":"A foundation model for atomistic materials chemistry","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.00096","snapshot_observed_at":"2026-08-06T22:45:50.114085Z","title":"A foundation model for atomistic materials chemistry.arXiv preprint arXiv:2401.00096, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.114085Z"},"links":{"cited_paper":"/paper/2401.00096","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:1ee7ef2297e9a75305dc5b3c673e118dd6b78959f430e4104d8cd0f7c75a81f4","observation_id":"8778ab22-6165-4dbf-ac38-38885a8333c1","resolution":{"observed_at":"2026-08-06T22:45:50.114085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03687","last_updated":"2024-01-29T16:02:46Z","snapshot_observed_at":"2026-08-05T09:41:41.305633Z","submitted_at":"2023-12-06T18:52:16Z","title":"MatterGen: a generative model for inorganic materials design","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03687","snapshot_observed_at":"2026-08-06T22:45:50.199192Z","title":"Mattergen: a generative model for inorganic materials design","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.199192Z"},"links":{"cited_paper":"/paper/2312.03687","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:5d5685fc0b1c6d3c29247472e3c7129ed45c4e1e8acfc94ee59ee4ace506fdac","observation_id":"6b0514c8-f340-42c9-a1ec-706b5f82bb56","resolution":{"observed_at":"2026-08-06T22:45:50.199192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03992","last_updated":"2024-04-08T04:44:23Z","snapshot_observed_at":"2026-08-09T05:29:56.541225Z","submitted_at":"2024-02-06T13:45:01Z","title":"Space Group Constrained Crystal Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03992","snapshot_observed_at":"2026-08-06T22:45:50.263429Z","title":"Space group constrained crystal generation.arXiv preprint arXiv:2402.03992, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.263429Z"},"links":{"cited_paper":"/paper/2402.03992","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:2393ef32e027b79d2912f09e63e823358868bb457c4f6bb679208dfbe09064e3","observation_id":"3a852c62-0e41-48e2-b91a-89f8c571f5e2","resolution":{"observed_at":"2026-08-06T22:45:50.263429Z","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":"2026-08-06T22:45:50.309363Z","title":"Space group informed transformer for crystalline materials generation.arXiv preprint arXiv:2403.15734, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.309363Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:c5f0ad1fbbb78b654e695346b33a8f3f5f69baf93e756ea8d6d7272a5716ed6b","observation_id":"d5a34b86-2e8f-4fee-b4c3-efa37ffa92e2","resolution":{"observed_at":"2026-08-06T22:45:50.309363Z","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":"2026-08-06T22:45:50.371459Z","title":"nach0: multimodal natural and chemical languages foundation model.Chemical Science, 15(22):8380–8389, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.371459Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:d9df78ef741685c0d45e30da86790518907706aca2d974e49de6f23e6de93fa7","observation_id":"962ebd04-fd39-4f6d-95c8-4f7bcefc6fb7","resolution":{"observed_at":"2026-08-06T22:45:50.371459Z","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":"2026-08-06T22:45:50.433371Z","title":"Multimodal foundation models for material property prediction and discovery.Newton, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.433371Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:400581f01dfeb370bd31ebf3cbe796ac358bf4699f3902e0e24421ab538d1e2d","observation_id":"bdaf4384-18ec-4824-8555-dbbe5500086b","resolution":{"observed_at":"2026-08-06T22:45:50.433371Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13107","last_updated":"2025-04-26T03:31:50Z","snapshot_observed_at":"2026-08-07T18:07:36.716503Z","submitted_at":"2025-02-18T18:19:36Z","title":"MatterChat: A Multi-Modal LLM for Material Science","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13107","snapshot_observed_at":"2026-08-06T22:45:50.476132Z","title":"Matterchat: A multi-modal llm for material science.arXiv preprint arXiv:2502.13107, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.476132Z"},"links":{"cited_paper":"/paper/2502.13107","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:7b31b1861c5b62773aff06676e856afb95959f0d0abf98e695385c950ce483f4","observation_id":"31273d3d-26ef-4641-8961-5846f501f74b","resolution":{"observed_at":"2026-08-06T22:45:50.476132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12289","last_updated":"2023-11-21T02:02:46Z","snapshot_observed_at":"2026-08-08T01:18:46.470273Z","submitted_at":"2023-11-21T02:02:46Z","title":"ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12289","snapshot_observed_at":"2026-08-06T22:45:50.531047Z","title":"Atlantic: Structure-aware retrieval-augmented language model for interdisciplinary science.arXiv preprint arXiv:2311.12289, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.531047Z"},"links":{"cited_paper":"/paper/2311.12289","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:81cd9bd3d846462c33a4ff0bfacef6fb198188c9b5f9da36114e0c63a6b790b4","observation_id":"2062caa3-5286-43c5-8524-2ab43890a0bf","resolution":{"observed_at":"2026-08-06T22:45:50.531047Z","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":"2026-08-06T22:45:50.596388Z","title":"Crystal structure generation with autoregressive large language modeling.Nature Communications, 15(1):1–16, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.596388Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:fbe58fda17032bf940d6fd6f3a7e8bd002c9f915dc7d1f9b69e2036e9a178684","observation_id":"4c58933b-7a4e-423f-93c8-ae4fb9753856","resolution":{"observed_at":"2026-08-06T22:45:50.596388Z","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":"2026-08-06T22:45:50.644106Z","title":"Accelerating material design with the generative toolkit for scientific discovery.npj Computational Materials, 9(1):69, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.644106Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:54011f1ab345a20fa4784d75c9158e98e686975ed31295e8d14b335840054e5e","observation_id":"ff129ba8-3784-4054-a0e1-498b71e34163","resolution":{"observed_at":"2026-08-06T22:45:50.644106Z","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":"2026-08-06T22:45:50.714674Z","title":"An autonomous laboratory for the accelerated synthesis of novel materials.Nature, 624(7990):86–91, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.714674Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:9c2e291981495df7adbd9936414e0d79a237308406449fea4e18aa0e5f3a310e","observation_id":"9d77f4c0-6808-47cc-bfa4-6fd676c8b49a","resolution":{"observed_at":"2026-08-06T22:45:50.714674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.08354","last_updated":"2024-11-13T05:58:21Z","snapshot_observed_at":"2026-08-05T03:02:25.053288Z","submitted_at":"2024-11-13T05:58:21Z","title":"Developing a Foundation Model for Predicting Material Failure","version":1},"cited_work":{"arxiv_id":"2411.08354","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.08354","snapshot_observed_at":"2026-08-06T22:46:01.853965Z","title":"Developing a Foundation Model for Predicting Material Failure","venue":"physics.geo-ph","work_id":"9b79ee2d-a6e8-4afc-8a40-dbc165055462","year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.812450Z"},"links":{"cited_paper":"/paper/2411.08354","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:9e949ac5b43483a717e24badfb38040f8377ce058229904b1d09574bdf7d8d82","observation_id":"ee437606-14b5-4f10-b659-f74905bc54b3","resolution":{"observed_at":"2026-08-06T22:46:01.859232Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T22:45:50.861191Z","title":"Foundation models for the process industry: Challenges and opportunities.Engineering, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.861191Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:47a0cf2f50885bd56a911fd8cfe073af713f78a337f652d39fbe3ac30621e752","observation_id":"db983615-41aa-488c-b55b-4ecf3bc09ae9","resolution":{"observed_at":"2026-08-06T22:45:50.861191Z","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":"2026-08-06T22:45:50.938616Z","title":"A perspective on foundation models in chemistry.JACS Au, 5(4):1499–1518, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:50.938616Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:fd2b0e095a1c4efb8c0d551a1d8e980a031b826cb5aa2cf24306affe8f54efc9","observation_id":"14104b6d-f2c1-43f9-b9d4-2a5ce7e1bef7","resolution":{"observed_at":"2026-08-06T22:45:50.938616Z","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":"2026-08-06T22:45:51.011604Z","title":"Towards foundation models for materials science: The open matsci ml toolkit","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.011604Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:34ed0663f9ae7d504479d6ec9cdd49b9097c2c1fe00b9bdd38f29f8430a851d0","observation_id":"2ae85726-d864-4c6a-b640-f96da6fd4a9e","resolution":{"observed_at":"2026-08-06T22:45:51.011604Z","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":"2026-08-06T22:45:51.092693Z","title":"Atomgpt: Atomistic generative pretrained transformer for forward and inverse materials design.The Journal of Physical Chemistry Letters, 15(27):6909–6917, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.092693Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:f2a4db46eca925635077817a9ebd74f6b21c8edc4c8cd39d1b5061fc98d94942","observation_id":"8d19c16e-07eb-440b-8563-f480d1e96e7c","resolution":{"observed_at":"2026-08-06T22:45:51.092693Z","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":"2026-08-06T22:45:51.162993Z","title":"Multi-view mixture-of-experts for predicting molecular properties using smiles, selfies, and graph-based representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.162993Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:7d78f05269a12e4d48d1d1b3e32ff51e5871541975e70a4645ab66b72d8247bb","observation_id":"88e40ee5-4dbb-4292-b5fc-7d3a091ba0d4","resolution":{"observed_at":"2026-08-06T22:45:51.162993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14818","last_updated":"2025-07-02T11:25:33Z","snapshot_observed_at":"2026-07-06T17:20:53.860993Z","submitted_at":"2024-01-26T12:45:55Z","title":"Developing ChemDFM as a large language foundation model for chemistry","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14818","snapshot_observed_at":"2026-08-06T22:45:51.198241Z","title":"Chemdfm: A large language foundation model for chemistry.arXiv preprint arXiv:2401.14818, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.198241Z"},"links":{"cited_paper":"/paper/2401.14818","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:849b5083a96c70f2973d7217247b680a3e4f6829918b5e929216ffc89b5b68a6","observation_id":"db604da4-a9e2-44e9-b7ee-a0753193b23d","resolution":{"observed_at":"2026-08-06T22:45:51.198241Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09560","last_updated":"2025-01-28T13:17:29Z","snapshot_observed_at":"2026-08-02T08:27:01.549714Z","submitted_at":"2024-12-12T18:46:38Z","title":"Foundational Large Language Models for Materials Research","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09560","snapshot_observed_at":"2026-08-06T22:45:51.267103Z","title":"Foundational large language models for materials research.arXiv preprint arXiv:2412.09560, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.267103Z"},"links":{"cited_paper":"/paper/2412.09560","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:f4b52d9c1dc6e337e8fad82d57978f38d6a4bd43f8b29f1f992f5c5c182b3d31","observation_id":"de72df31-bb33-4798-b9c9-fcf4e62cf108","resolution":{"observed_at":"2026-08-06T22:45:51.267103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01139","last_updated":"2026-04-13T04:11:05Z","snapshot_observed_at":"2026-08-08T18:17:36.506207Z","submitted_at":"2023-07-03T16:25:49Z","title":"SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01139","snapshot_observed_at":"2026-08-06T22:45:51.336005Z","title":"Scitune: Aligning large language models with scientific multimodal instructions.arXiv preprint arXiv:2307.01139, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.336005Z"},"links":{"cited_paper":"/paper/2307.01139","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:64a1ab4d59c1f5b515831c308391f48de45f7de13e3e13164b4ab975543c9d81","observation_id":"94d753fa-73f9-4295-a2c0-a5f8524eaa9c","resolution":{"observed_at":"2026-08-06T22:45:51.336005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00135","last_updated":"2024-08-29T15:38:40Z","snapshot_observed_at":"2026-08-07T20:04:51.152453Z","submitted_at":"2024-08-29T15:38:40Z","title":"HoneyComb: A Flexible LLM-Based Agent System for Materials Science","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00135","snapshot_observed_at":"2026-08-06T22:45:51.422557Z","title":"Honeycomb: A flexible llm-based agent system for materials science.arXiv preprint arXiv:2409.00135, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.422557Z"},"links":{"cited_paper":"/paper/2409.00135","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:ac208b8f2fcc248f90b13d0add86f7ff43b94d619c3630333a4c76d27d843158","observation_id":"3955247d-bc47-40b9-9549-d521278cb1f0","resolution":{"observed_at":"2026-08-06T22:45:51.422557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13163","last_updated":"2024-06-19T02:35:02Z","snapshot_observed_at":"2026-07-06T18:33:24.206083Z","submitted_at":"2024-06-19T02:35:02Z","title":"LLMatDesign: Autonomous Materials Discovery with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13163","snapshot_observed_at":"2026-08-06T22:45:51.562826Z","title":"Llmatdesign: Autonomous materials discovery with large language models.arXiv preprint arXiv:2406.13163, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.562826Z"},"links":{"cited_paper":"/paper/2406.13163","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:63108823174c026edfa5f5687b1fa9c56ee3304d325828f805422456b8a3d687","observation_id":"e54bd8bd-0364-4acf-b95c-69d2ebb3f8de","resolution":{"observed_at":"2026-08-06T22:45:51.562826Z","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":"2026-08-06T22:45:51.645891Z","title":"Chatmof: an artificial intelligence system for predicting and generating metal-organic frameworks using large language models.Nature communications, 15(1):4705, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.645891Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:d030806eecf49269955da4c602794e0032448e6ea93c0d4cb2a40d482c0b6eb0","observation_id":"3f757b0a-45ec-4f29-b173-c319fc680afc","resolution":{"observed_at":"2026-08-06T22:45:51.645891Z","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":"2026-08-06T22:45:51.744821Z","title":"Matagent: A human-in-the-loop multi-agent llm framework for accelerating the material science discovery cycle","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.744821Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:29ceff08649cb4f820f5f4f8fcfa0c079501b78741c94eaaf7f013f626bbfe4c","observation_id":"da7aab8c-c223-44ce-abe6-1842f6a66e6f","resolution":{"observed_at":"2026-08-06T22:45:51.744821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.08063","last_updated":"2024-11-10T12:23:44Z","snapshot_observed_at":"2026-08-09T02:33:09.443394Z","submitted_at":"2024-11-10T12:23:44Z","title":"MatPilot: an LLM-enabled AI Materials Scientist under the Framework of Human-Machine Collaboration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.08063","snapshot_observed_at":"2026-08-06T22:45:51.887367Z","title":"Matpilot: an llm-enabled ai materials scientist under the framework of human-machine collaboration.arXiv preprint arXiv:2411.08063, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.887367Z"},"links":{"cited_paper":"/paper/2411.08063","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:8cc6c7cece47e16f9d829b4d66b1e25e3b32e70484853d4404204fa302cef34f","observation_id":"ce74b8bb-2990-40e5-8d7f-5a2294a8edea","resolution":{"observed_at":"2026-08-06T22:45:51.887367Z","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":"2026-08-06T22:45:51.962834Z","title":"Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, and Philippe Schwaller","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:51.962834Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:7cd6381391296f2b3c964320dcc9dd3ee835c749a1c35db7846056b776fff1f1","observation_id":"864dcd74-82b4-4b50-91fe-100865af5224","resolution":{"observed_at":"2026-08-06T22:45:51.962834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17484","last_updated":"2022-10-31T17:11:36Z","snapshot_observed_at":"2026-07-06T14:12:41.054904Z","submitted_at":"2022-10-31T17:11:36Z","title":"The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science","version":1},"cited_work":{"arxiv_id":"2210.17484","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.17484","snapshot_observed_at":"2026-08-06T22:46:01.733065Z","title":"The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science","venue":"cs.LG","work_id":"09994e8e-e038-46ca-a623-3d0f39d9f914","year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.048784Z"},"links":{"cited_paper":"/paper/2210.17484","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:889b4119ed92679129a696ca96200b98dec898caa67eded41c8ff7f083e15892","observation_id":"7a40b8d1-c7c8-4be0-86ea-1fcbf9f908df","resolution":{"observed_at":"2026-08-06T22:46:01.739585Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T22:45:52.115548Z","title":"Forge: Pre-training open foundation models for science","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.115548Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:640140cf392d6cb03c59fa39bb84ffb4bddb741421eca5763be754d2c25940f9","observation_id":"30c0005e-4e48-4578-85db-470ffeed9431","resolution":{"observed_at":"2026-08-06T22:45:52.115548Z","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":"2026-08-06T22:45:52.194623Z","title":"Attention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.194623Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:f3f3ea6d3b97fd5655cc499fd8b9290dcaf69e8d6cd0fdde10a0d79fc8e6da31","observation_id":"6fd04638-fc6d-453f-9c4b-85cb398c9d2e","resolution":{"observed_at":"2026-08-06T22:45:52.194623Z","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":"2026-08-06T22:45:52.259198Z","title":"Improving language understanding by generative pre-training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.259198Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:e3a657caf34bdf7c23676247c5537c9040ba3b4b498fa9b79a3a9998c6f7da84","observation_id":"e5fb8f41-71fa-4009-98c0-9b2d8a3cb96f","resolution":{"observed_at":"2026-08-06T22:45:52.259198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-06T22:45:52.363980Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.363980Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:c4607f953e912821220cb83beb4b59a8e6dd090dda7a57f0a2121b5611caab71","observation_id":"92f6daca-9fcb-457f-9ee2-c49e23813efa","resolution":{"observed_at":"2026-08-06T22:45:52.363980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-06T22:45:52.427238Z","title":"Llama: Open and efficient foundation language models.arXiv preprint arXiv:2302.13971, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.427238Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:9980c000c426e495e133e8daf6ddac9aa23b91de80abf1be01127ff0d4a3b555","observation_id":"f0cd7433-6967-4f92-a450-34f5a650fddf","resolution":{"observed_at":"2026-08-06T22:45:52.427238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.13461","last_updated":"2019-10-29T18:01:00Z","snapshot_observed_at":"2026-07-06T08:33:12.534026Z","submitted_at":"2019-10-29T18:01:00Z","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.13461","snapshot_observed_at":"2026-08-06T22:45:52.499208Z","title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension.arXiv preprint arXiv:1910.13461, 2019","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.499208Z"},"links":{"cited_paper":"/paper/1910.13461","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:a84e59cd676a7699cc1b96407d225e860a66db635a0e2e3418c8b3557af8fc42","observation_id":"e7cbc9b0-bf05-4cce-9c63-84fd25b3cf1b","resolution":{"observed_at":"2026-08-06T22:45:52.499208Z","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":"2026-08-06T22:45:52.593830Z","title":"React: Synergizing reasoning and acting in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.593830Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:36446361c25ca23b1c5b0fa3bb19647796a4b72c53f4130acc5cd74d1c3be023","observation_id":"f44fbb91-8b9d-4e06-b166-3b33e11381a1","resolution":{"observed_at":"2026-08-06T22:45:52.593830Z","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":"2026-08-06T22:45:52.670724Z","title":"Llm-planner: Few-shot grounded planning for embodied agents with large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.670724Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:eb836297fa71f2c11085c2437e9dad6c0fe176f20ef2399d9cba08f7bdc233e0","observation_id":"e974ae42-3cb5-4776-8281-e13aeb892ea3","resolution":{"observed_at":"2026-08-06T22:45:52.670724Z","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":"2026-08-06T22:45:52.746077Z","title":"Tree of thoughts: Deliberate problem solving with large language models.Advances in neural information processing systems, 36:11809–11822, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.746077Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:441d41b19d4df63dde835b2112478c428109bd07f34cd758102d0eaa5a98e28c","observation_id":"34a34422-22ac-4424-b66c-96ae23c277bf","resolution":{"observed_at":"2026-08-06T22:45:52.746077Z","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":"2026-08-06T22:45:52.791319Z","title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.791319Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b0a51460745a7716e07217cdffa8be2dae35113e61231cb0a0962216f83b2965","observation_id":"3ec49521-1b7a-4402-9cd0-2687d8ea5983","resolution":{"observed_at":"2026-08-06T22:45:52.791319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02083","last_updated":"2024-11-04T19:51:53Z","snapshot_observed_at":"2026-08-07T09:50:45.770227Z","submitted_at":"2023-02-04T03:50:01Z","title":"Evaluating Large Language Models in Theory of Mind Tasks","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.02083","snapshot_observed_at":"2026-08-06T22:45:52.871383Z","title":"Theory of mind may have spontaneously emerged in large language models.arXiv preprint arXiv:2302.02083, 4:169, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.871383Z"},"links":{"cited_paper":"/paper/2302.02083","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:d9fe56a520816edfa95104161505459199a374ecc3af6914af6deb26d80d6daf","observation_id":"3db051cc-f060-4333-ac85-9e32efa28e73","resolution":{"observed_at":"2026-08-06T22:45:52.871383Z","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":"2026-08-06T22:45:52.921416Z","title":"Role play with large language models.Nature, 623 (7987):493–498, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:52.921416Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:be8f0116ba30b49b3688309cd0b79674fc05e1262ee70d74364f9e89bf1001af","observation_id":"77247bf9-b6ca-45a0-aa6a-efe6bab912f3","resolution":{"observed_at":"2026-08-06T22:45:52.921416Z","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":"2026-08-06T22:45:53.046538Z","title":"A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.046538Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:ff00a819a567c73bea01386c44536a73fe00014588c77682a5775fe1f13d25c8","observation_id":"8e36f138-d6d3-469f-852d-556d50bf106a","resolution":{"observed_at":"2026-08-06T22:45:53.046538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08511","last_updated":"2023-10-12T17:06:19Z","snapshot_observed_at":"2026-08-04T03:08:46.541373Z","submitted_at":"2023-10-12T17:06:19Z","title":"HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science","version":1},"cited_work":{"arxiv_id":"2310.08511","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.08511","snapshot_observed_at":"2026-08-06T22:46:01.645308Z","title":"HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science","venue":"cs.CL","work_id":"fcf333e2-a120-428b-88f5-fe9817c05642","year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.164887Z"},"links":{"cited_paper":"/paper/2310.08511","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:8759fd466c2309bdd656fa3b5903e6dd353e05286b0971f4959a907f9a612155","observation_id":"c882da2a-ff03-43db-a930-b09979ed6be2","resolution":{"observed_at":"2026-08-06T22:46:01.650991Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T22:45:53.257495Z","title":"Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties.Physical review letters, 120(14):145301, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.257495Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:f4b8c3f614ad6e9ba565ff50c804c221d8eaf115ad6aba39be763fd812726694","observation_id":"eddafb64-7803-44c8-9d2d-9520e9d37d21","resolution":{"observed_at":"2026-08-06T22:45:53.257495Z","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":"2026-08-06T22:45:53.400425Z","title":"Graph networks as a universal machine learning framework for molecules and crystals.Chemistry of Materials, 31(9):3564–3572, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.400425Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:3d25a8cff21af81ecf9a79fc5905fed59a8534bcb56594c1f4240c401504d9f9","observation_id":"92612b4b-833c-4864-a93c-74132de4649f","resolution":{"observed_at":"2026-08-06T22:45:53.400425Z","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":"2026-08-06T22:45:53.535233Z","title":"Catalyst energy prediction with catberta: Unveiling feature exploration strategies through large language models.ACS Catalysis, 13(24):16032–16044, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.535233Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:28e946760cc0cfe63cb8fff69ab22d4d41ee5d7d014dad28966dcf6425713790","observation_id":"93c3fda0-bf1b-422c-8c9c-6b2e9428a3c8","resolution":{"observed_at":"2026-08-06T22:45:53.535233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10688","last_updated":"2023-05-26T04:35:46Z","snapshot_observed_at":"2026-07-06T15:29:01.076710Z","submitted_at":"2023-05-18T03:58:19Z","title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10688","snapshot_observed_at":"2026-08-06T22:45:53.648250Z","title":"Molxpt: Wrapping molecules with text for generative pre-training.arXiv preprint arXiv:2305.10688, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.648250Z"},"links":{"cited_paper":"/paper/2305.10688","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:6632d7c29c866134e95919529f8cc28c7359c9c1fbe2f925c099024d051e18f0","observation_id":"ddffe5e8-10d5-4d5c-8c55-ab2bccbed9a1","resolution":{"observed_at":"2026-08-06T22:45:53.648250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06197","last_updated":"2022-03-14T13:36:09Z","snapshot_observed_at":"2026-08-02T15:20:57.263348Z","submitted_at":"2021-10-12T17:49:49Z","title":"Crystal Diffusion Variational Autoencoder for Periodic Material Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06197","snapshot_observed_at":"2026-08-06T22:45:53.799738Z","title":"Crystal diffusion variational autoencoder for periodic material generation.arXiv preprint arXiv:2110.06197, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.799738Z"},"links":{"cited_paper":"/paper/2110.06197","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:676f6f36946e2dbf1b3f76d3a7ef8146e4f99452b9c3e8b1cb430e7bf101470a","observation_id":"125f0c09-4390-4b95-aaec-dc00b93dd9ad","resolution":{"observed_at":"2026-08-06T22:45:53.799738Z","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":"2026-08-06T22:45:53.938840Z","title":"Crystal structure prediction by joint equivariant diffusion.Advances in Neural Information Processing Systems, 36:17464–17497, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:53.938840Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:7818d2b61144db9bc918e462239e1b1bc84fedd664774440e8bbbeefc96673e0","observation_id":"bdce9d7e-03e9-467d-8db8-72214f82b27c","resolution":{"observed_at":"2026-08-06T22:45:53.938840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04912","last_updated":"2025-03-31T18:16:41Z","snapshot_observed_at":"2026-07-06T18:11:26.210335Z","submitted_at":"2024-04-04T16:20:06Z","title":"GP-MoLFormer: A Foundation Model For Molecular Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.04912","snapshot_observed_at":"2026-08-06T22:45:54.037903Z","title":"Gp-molformer: A foundation model for molecular generation.arXiv preprint arXiv:2405.04912, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.037903Z"},"links":{"cited_paper":"/paper/2405.04912","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:7e0b172695d52e3fff0d5d1dfc5eafe56c0cc9874433edc2ecae499d7847baf1","observation_id":"89f6ccfc-f768-4d46-a89c-ca8e535a493a","resolution":{"observed_at":"2026-08-06T22:45:54.037903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.07608","last_updated":"2024-08-14T15:12:05Z","snapshot_observed_at":"2026-08-03T23:46:52.589180Z","submitted_at":"2024-08-14T15:12:05Z","title":"MatterGPT: A Generative Transformer for Multi-Property Inverse Design of Solid-State Materials","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.07608","snapshot_observed_at":"2026-08-06T22:45:54.140188Z","title":"Mattergpt: A generative transformer for multi-property inverse design of solid-state materials.arXiv preprint arXiv:2408.07608, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.140188Z"},"links":{"cited_paper":"/paper/2408.07608","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:d0946ebe28aad026304d2147cdc646f6895078d3863b1ce35c0118000b4824c3","observation_id":"5f260832-e7a6-402f-ab3a-b1f88b3cfe2e","resolution":{"observed_at":"2026-08-06T22:45:54.140188Z","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":"2026-08-06T22:45:54.242408Z","title":"Chemformer: a pre-trained transformer for computational chemistry.Machine Learning: Science and Technology, 3(1):015022, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.242408Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:6876efe9bbcdac6005fef7e4e7584dd731c8329e52adfa93ef21a0f46f3537eb","observation_id":"877b84a4-dc8b-44ed-88f7-6d1a2ce05a65","resolution":{"observed_at":"2026-08-06T22:45:54.242408Z","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":"2026-08-06T22:45:54.397001Z","title":"Flowllm: Flow matching for material generation with large language models as base distributions.Advances in Neural Information Processing Systems, 37:46025–46046, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.397001Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:1add752c4682b11bc368ae420b933fbd7985f922107de276b07ca8b9227f4d7a","observation_id":"81dd21de-4f72-46f5-ac42-bd4d9aea8eca","resolution":{"observed_at":"2026-08-06T22:45:54.397001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07016","last_updated":"2024-07-09T16:35:12Z","snapshot_observed_at":"2026-08-04T17:27:04.448914Z","submitted_at":"2024-07-09T16:35:12Z","title":"Is Large Language Model All You Need to Predict the Synthesizability and Precursors of Crystal Structures?","version":1},"cited_work":{"arxiv_id":"2407.07016","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.07016","snapshot_observed_at":"2026-08-06T22:46:01.555907Z","title":"Is Large Language Model All You Need to Predict the Synthesizability and Precursors of Crystal Structures?","venue":"cond-mat.mtrl-sci","work_id":"815be215-d93e-491b-99da-f8278d1b7fb3","year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.508214Z"},"links":{"cited_paper":"/paper/2407.07016","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:298d7fb060b2c9b761898b2f50d8b67bfde4d0e64c9d73a99b4be9c3fd937be9","observation_id":"53e55b7f-3144-4f95-bc89-1fb8e0dbb6be","resolution":{"observed_at":"2026-08-06T22:46:01.561043Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01022","last_updated":"2025-03-02T21:13:04Z","snapshot_observed_at":"2026-08-07T17:35:24.164175Z","submitted_at":"2025-03-02T21:13:04Z","title":"LLM-Fusion: A Novel Multimodal Fusion Model for Accelerated Material Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01022","snapshot_observed_at":"2026-08-06T22:45:54.611509Z","title":"Llm-fusion: A novel multimodal fusion model for accelerated material discovery.arXiv preprint arXiv:2503.01022, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.611509Z"},"links":{"cited_paper":"/paper/2503.01022","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:fae6d840a611a4cf53fbd2cc5c3ca78e85f67717e7a6b80236a2164564e3e00f","observation_id":"a028b6b1-4f19-49ba-8d58-59289ea6da14","resolution":{"observed_at":"2026-08-06T22:45:54.611509Z","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":"2026-08-06T22:45:54.771536Z","title":"Unifying molecular and textual representations via multi-task language modelling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.771536Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:4a05f8279481e5e8ed18792296a42ec7d533c98794f6ea6407f39270774a6875","observation_id":"de484a9c-3e0f-495c-abd9-9c1a1db39feb","resolution":{"observed_at":"2026-08-06T22:45:54.771536Z","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":"2026-08-06T22:45:54.925336Z","title":"Quantifying the advantage of domain-specific pre-training on named entity recognition tasks in materials science.Patterns, 3(4), 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:54.925336Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:269c4d94c5120ffc9bdd26d93b69608bdd37c07db900875363567b00f6a1f660","observation_id":"72c25cbe-bfff-4d1c-8040-6a0c691622e3","resolution":{"observed_at":"2026-08-06T22:45:54.925336Z","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":"2026-08-06T22:45:55.081602Z","title":"Matscibert: A materials domain language model for text mining and information extraction.npj Computational Materials, 8(1):102, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.081602Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b02b7fdb6258b1ca312e09d2c0403ed1c35a84982541163f32344db21f8d5de4","observation_id":"8860ba84-43ae-4137-a0d2-034640b0fd92","resolution":{"observed_at":"2026-08-06T22:45:55.081602Z","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":"2026-08-06T22:45:55.193413Z","title":"A general-purpose material property data extraction pipeline from large polymer corpora using natural language processing.npj Computational Materials, 9(1):52, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.193413Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:54348fb3fc7428d6c5221f6c1efa15769c4a3f3cc599737d8dbd9923da8d3856","observation_id":"d6348a59-d30c-4a5c-99a2-4685e0d17b16","resolution":{"observed_at":"2026-08-06T22:45:55.193413Z","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":"2026-08-06T22:45:55.330128Z","title":"Molscribe: robust molecular structure recognition with image-to-graph generation.Journal of Chemical Information and Modeling, 63(7):1925–1934, 2023","venue":null,"work_id":null,"year":1925},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.330128Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:4f1d52d91c27fbc3e7b77f7d21743973e6e3226ce89f06a4e4fc409b1cb6e821","observation_id":"c652167d-9bc8-494d-b13d-0db67c566682","resolution":{"observed_at":"2026-08-06T22:45:55.330128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10505","last_updated":"2023-05-23T18:28:39Z","snapshot_observed_at":"2026-08-08T00:11:52.450834Z","submitted_at":"2022-12-20T18:20:50Z","title":"DePlot: One-shot visual language reasoning by plot-to-table translation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10505","snapshot_observed_at":"2026-08-06T22:45:55.410946Z","title":"Deplot: One-shot visual language reasoning by plot-to- table translation.arXiv preprint arXiv:2212.10505, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.410946Z"},"links":{"cited_paper":"/paper/2212.10505","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b2535145034706907405a9be0a071189b16a0b43d5df7be8dc2bb7a2ecfac6dd","observation_id":"83a5b0ae-e232-422b-9490-08a87f2f54ab","resolution":{"observed_at":"2026-08-06T22:45:55.410946Z","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":"2026-08-06T22:45:55.477279Z","title":"Mascqa: investigating materials science knowledge of large language models.Digital Discovery, 3(2):313–327, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.477279Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:5e8a985b0313927cea7272ca3ecbd7406dcceb48a222233bbeed0f4c5ea5be6a","observation_id":"248367ef-bf4e-4f3c-ac39-214dc973adc3","resolution":{"observed_at":"2026-08-06T22:45:55.477279Z","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":"2026-08-06T22:45:55.551437Z","title":"Assessment of fine-tuned large language models for real-world chemistry and material science applications.Chemical science, 16(2):670–684, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.551437Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:1fb90e254c3bbf3eb9a197a1877406c23c52845b061c473204a034e5ca7ab6fc","observation_id":"850b9e21-d4ec-400b-9678-6838fbd07a53","resolution":{"observed_at":"2026-08-06T22:45:55.551437Z","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":"2026-08-06T22:45:55.650008Z","title":"Gpt-j-6b: A 6 billion parameter autoregressive language model, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.650008Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:978e9dfeb9af2f934e20c2d4b8e65d3c1c5506ab3a0cd36a719b75006f37b2a8","observation_id":"492b5158-2234-4f0c-9eb2-234cba9797d7","resolution":{"observed_at":"2026-08-06T22:45:55.650008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","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":"2026-08-06T22:45:55.730130Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.730130Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:f4a07d828e2c6c7a3eaf2f723aecad35658e62a9e5cc93bf996fb97b1f56c687","observation_id":"23c553ec-7b33-4346-b63e-55c7231a0671","resolution":{"observed_at":"2026-08-06T22:45:55.730130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-06T22:45:55.792600Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.792600Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:4c19ba47d0b1e737148bc67ca404cf2de7c0430c39cf9ee94140203a83d85279","observation_id":"05b99a8b-a83f-4b8a-b3ac-0814cb5e8262","resolution":{"observed_at":"2026-08-06T22:45:55.792600Z","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":"2026-08-06T22:45:55.908626Z","title":"Smiles, a chemical language and information system","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:55.908626Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:e2bc5c0d65687bf928546984a9f76a9d9e9f9177a29042d0f87b9792d09fccd2","observation_id":"5bcbda94-a38e-472f-9045-f457d098933a","resolution":{"observed_at":"2026-08-06T22:45:55.908626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.10301","last_updated":"2024-06-15T16:03:29Z","snapshot_observed_at":"2026-08-05T04:37:35.956612Z","submitted_at":"2024-03-15T13:43:47Z","title":"Uni-SMART: Universal Science Multimodal Analysis and Research Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.10301","snapshot_observed_at":"2026-08-06T22:45:56.001030Z","title":"Uni-smart: Universal science multimodal analysis and research transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.001030Z"},"links":{"cited_paper":"/paper/2403.10301","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:9d657b293f63f0bbf76d2675ce17037285de364094f9515e636050d249a0a77b","observation_id":"124f8404-92a4-49ad-9188-80f421c1b2f3","resolution":{"observed_at":"2026-08-06T22:45:56.001030Z","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":"2026-08-06T22:45:56.069072Z","title":"The claude 3 model family: Opus, sonnet, haiku","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.069072Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:983c09a65ae93dd2186292dc15b8a85908d0d5f6587180601dbab3e2addcc7a6","observation_id":"099be7b0-622a-413d-95ba-d98da1c0289b","resolution":{"observed_at":"2026-08-06T22:45:56.069072Z","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":"2026-08-06T22:45:56.164059Z","title":"Do transformers really perform badly for graph representation?Advances in neural information processing systems, 34:28877–28888, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.164059Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:af02e14fe8472e36a4df7d9387b48c9dc3b9f1235801b81eef99ca271a5f163a","observation_id":"07feffc6-4759-4837-a162-d560c75f8a85","resolution":{"observed_at":"2026-08-06T22:45:56.164059Z","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":"2026-08-06T22:45:56.232681Z","title":"Mace: Higher order equivariant message passing neural networks for fast and accurate force fields.Advances in neural information processing systems, 35:11423–11436, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.232681Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b045ac92fb7f3b601d5da5de0d30ed348def08de32f1427ac0d2e61967457f53","observation_id":"66d1c0d4-22c3-45c8-b753-8d122c28df05","resolution":{"observed_at":"2026-08-06T22:45:56.232681Z","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":"2026-08-06T22:45:56.348327Z","title":"Ani-1: an extensible neural network potential with dft accuracy at force field computational cost.Chemical science, 8(4):3192–3203, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.348327Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:14c8d19af5847b8c774c3efbbd6a3579bc8da787cef5ac4bf0274c44f411360a","observation_id":"fb7e1593-fd00-40df-851e-ddf34d687953","resolution":{"observed_at":"2026-08-06T22:45:56.348327Z","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":"2026-08-06T22:45:56.447586Z","title":"Generalized neural-network representation of high-dimensional potential- energy surfaces.Physical review letters, 98(14):146401, 2007","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.447586Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:808fb0684e89cb9b64d8dbe94d5dd8af5ce63d779625f701de05ada11f06c167","observation_id":"c886f328-1c0f-4504-827d-5b379decfbea","resolution":{"observed_at":"2026-08-06T22:45:56.447586Z","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":"2026-08-06T22:45:56.540743Z","title":"Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network.Science advances, 5(8):eaav6490, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.540743Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:1e3c60599490e68b9ad2067bd92cf373e351112fc71df65d0c9d4ca58b06e3c2","observation_id":"6e2e015a-fa79-4b35-9034-4dafcf065d75","resolution":{"observed_at":"2026-08-06T22:45:56.540743Z","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":"2026-08-06T22:45:56.654888Z","title":"Aimnet2: a neural network potential to meet your neutral, charged, organic, and elemental-organic needs.Chemical Science, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.654888Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:1b64be4318d72c498f0e9adad8d552244c9c42155fef643ec0484100e38c6e52","observation_id":"deda823a-f9ca-4085-a205-ee77d3d2a412","resolution":{"observed_at":"2026-08-06T22:45:56.654888Z","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":"2026-08-06T22:45:56.719996Z","title":"The graph neural network model.IEEE transactions on neural networks, 20(1):61–80, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.719996Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b39c697301743c7e685fb48ee138f6afa5645b69a251665df3808b2a05cd847d","observation_id":"2cd0e5d7-16e8-43aa-94b6-0ec39a5a6b4d","resolution":{"observed_at":"2026-08-06T22:45:56.719996Z","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":"2026-08-06T22:45:56.808611Z","title":"Self-referencing embedded strings (selfies): A 100% robust molecular string representation.Machine Learning: Science and Technology, 1(4):045024, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.808611Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:e393107a76b29450272813b039c91620429353d45f8f4a3ed969ac4316bf8852","observation_id":"1798da98-80b4-4601-a9da-e7ac9d6a09ed","resolution":{"observed_at":"2026-08-06T22:45:56.808611Z","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":"2026-08-06T22:45:56.877984Z","title":"Zinc 15–ligand discovery for everyone.Journal of chemical information and modeling, 55(11):2324–2337, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.877984Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:d34373c040da5ccf52ddedbb256fb6da37cdc6075acdf684df306e560e6bf022","observation_id":"02007e70-d8a0-4ee0-9476-d7aafa5d6119","resolution":{"observed_at":"2026-08-06T22:45:56.877984Z","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":"2026-08-06T22:45:56.964415Z","title":"Zinc20—a free ultralarge-scale chemical database for ligand discovery.Journal of chemical information and modeling, 60(12):6065–6073, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:56.964415Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:e15f1630692c45df73a9a31c26ed6735ae9141225609d6680e56d537fe1d51a8","observation_id":"932be6fe-ec6c-4f7c-a75a-ebfdb1e46b79","resolution":{"observed_at":"2026-08-06T22:45:56.964415Z","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":"2026-08-06T22:45:57.030908Z","title":"The chembl database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods.Nucleic acids research, 52(D1): D1180–D1192, 2024","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.030908Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b7c31a4ab7ea372731daf1a3a32bba54562a1c30468c32679a2e6327dc86e4e8","observation_id":"b5f04dc2-41b3-496d-b45b-14ad2253c7be","resolution":{"observed_at":"2026-08-06T22:45:57.030908Z","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":"2026-08-06T22:45:57.099822Z","title":"Chembl web services: streamlining access to drug discovery data and utilities","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.099822Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:d48dd99960a4a623763081d4486d1aac16bc5861a8a6270bcdfad1798756e27c","observation_id":"02b087c5-d218-4fab-9b2b-ba267792a9f7","resolution":{"observed_at":"2026-08-06T22:45:57.099822Z","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":"2026-08-06T22:45:57.179816Z","title":"Schnet–a deep learning architecture for molecules and materials.The Journal of Chemical Physics, 148(24), 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.179816Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:f0a691173e921e7482a0a3368c2cb99dacda1c3277a49d52300f60f4ec0878d5","observation_id":"e78b9df7-d785-4384-ad5e-2bf67253329f","resolution":{"observed_at":"2026-08-06T22:45:57.179816Z","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":"2026-08-06T22:45:57.228598Z","title":"Commentary: The materials project: A materials genome approach to accelerating materials innovation.APL materials, 1(1), 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.228598Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:8ffaabb496d5c85b36b9028414a702d8f33401f6f6c89c7ff072267e1f6b9d44","observation_id":"c409da0a-d472-4877-a9ce-6dd4a16046fc","resolution":{"observed_at":"2026-08-06T22:45:57.228598Z","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":"2026-08-06T22:45:57.311642Z","title":"Enumeration of 166 billion organic small molecules in the chemical universe database gdb-17.Journal of chemical information and modeling, 52(11):2864–2875, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.311642Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:2bc8310eda3ac8bc46fdd11bc3feb4a0d510bb8c60b53bcb07c36fd4300d64be","observation_id":"c4be6679-2617-42fb-9cdb-dafb40f4a399","resolution":{"observed_at":"2026-08-06T22:45:57.311642Z","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":"2026-08-06T22:45:57.380541Z","title":"Quantum chemistry structures and properties of 134 kilo molecules.Scientific data, 1(1):1–7, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.380541Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:dcc93140ab2d3a5eff5cf6b045aacfb70a94eafe6559e36f3c34b306470c5d07","observation_id":"091dcb15-506a-46c9-a82c-d63d9b142b46","resolution":{"observed_at":"2026-08-06T22:45:57.380541Z","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":"2026-08-06T22:45:57.421724Z","title":"A compact review of molecular property prediction with graph neural networks.Drug Discovery Today: Technologies, 37:1–12, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.421724Z"},"links":{"citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:b079e764a30601ec9f2941ab25a1edb9e872b1a2ce0eb1192d9e5c8be731b3cb","observation_id":"f0d9f27f-4076-4c48-9572-3c479ca20568","resolution":{"observed_at":"2026-08-06T22:45:57.421724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.09885","last_updated":"2020-10-23T04:22:37Z","snapshot_observed_at":"2026-08-08T06:02:13.053327Z","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":"2026-08-06T22:45:57.493434Z","title":"Chemberta: large-scale self-supervised pretraining for molecular property prediction.arXiv preprint arXiv:2010.09885, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-06T22:45:57.493434Z"},"links":{"cited_paper":"/paper/2010.09885","citing_paper":"/paper/2506.20743"},"observation_digest":"sha256:2942b5bfdd098c0173fa0ce86a94c4b3d40fa02a9e5d52fc572a8aef5f58b454","observation_id":"e3c972b3-5b69-4c08-a5a8-a3d823334119","resolution":{"observed_at":"2026-08-06T22:45:57.493434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.20743","last_updated":"2025-06-25T18:10:30Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T03:07:30.066886Z","submitted_at":"2025-06-25T18:10:30Z","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":96,"verified_exact":4,"verified_fuzzy":0},"total_outbound_references":188},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 100 of 188 outbound references and 6 inbound Pith citation observations for arXiv:2506.20743."}